From ab160fb9537dee34183e6a5cb730791b7e1791a0 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 25 Aug 2026 13:26:48 +0000 Subject: [PATCH 1/7] fix(model_prices): sync gpt-5.6-sol bedrock rates, add gpt-5.6-cyber, fix claude 3 1h cache writes Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 80 +++++++++++++------ model_prices_and_context_window.json | 80 +++++++++++++------ ..._cross_region_inference_profile_mapping.py | 24 +++--- ...bedrock_mantle_responses_transformation.py | 13 ++- 4 files changed, 131 insertions(+), 66 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 9f953e11df1..73e16715cf0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12282,7 +12282,7 @@ }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 5e-07, "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-04-20", "input_cost_per_token": 2.5e-07, @@ -12301,7 +12301,7 @@ }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2026-01-05", "input_cost_per_token": 1.5e-05, @@ -49007,14 +49007,14 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -49070,6 +49070,34 @@ "supports_tool_choice": true, "supports_vision": true }, + "bedrock_mantle/openai.gpt-5.6-cyber": { + "input_cost_per_token": 1.375e-05, + "cache_creation_input_token_cost": 1.71875e-05, + "cache_read_input_token_cost": 1.375e-06, + "output_cost_per_token": 8.25e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "bedrock_mantle/openai.gpt-5.6-luna": { "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, @@ -49103,14 +49131,14 @@ "supports_vision": true }, "us.openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -49128,14 +49156,14 @@ "supports_vision": true }, "global.openai.gpt-5.6-sol": { - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 9f953e11df1..73e16715cf0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -12282,7 +12282,7 @@ }, "claude-3-haiku-20240307": { "cache_creation_input_token_cost": 3e-07, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 5e-07, "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-04-20", "input_cost_per_token": 2.5e-07, @@ -12301,7 +12301,7 @@ }, "claude-3-opus-20240229": { "cache_creation_input_token_cost": 1.875e-05, - "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr": 3e-05, "cache_read_input_token_cost": 1.5e-06, "deprecation_date": "2026-01-05", "input_cost_per_token": 1.5e-05, @@ -49007,14 +49007,14 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_mantle", "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -49070,6 +49070,34 @@ "supports_tool_choice": true, "supports_vision": true }, + "bedrock_mantle/openai.gpt-5.6-cyber": { + "input_cost_per_token": 1.375e-05, + "cache_creation_input_token_cost": 1.71875e-05, + "cache_read_input_token_cost": 1.375e-06, + "output_cost_per_token": 8.25e-05, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "use_openai_responses_path": true, + "supported_endpoints": [ + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "bedrock_mantle/openai.gpt-5.6-luna": { "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, @@ -49103,14 +49131,14 @@ "supports_vision": true }, "us.openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -49128,14 +49156,14 @@ "supports_vision": true }, "global.openai.gpt-5.6-sol": { - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 128000, diff --git a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py index dbd31c7e81b..694ed109025 100644 --- a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py +++ b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py @@ -59,17 +59,17 @@ class GptProfile(NamedTuple): GPT_5_6_PROFILES = [ GptProfile( model_id="us.openai.gpt-5.6-sol", - input_cost=5.5e-06, input_cost_above_272k=1.1e-05, - cache_write=6.875e-06, cache_write_above_272k=1.375e-05, - cache_read=5.5e-07, cache_read_above_272k=1.1e-06, - output_cost=3.3e-05, output_cost_above_272k=4.95e-05, + input_cost=4.4e-06, input_cost_above_272k=8.8e-06, + cache_write=5.5e-06, cache_write_above_272k=1.1e-05, + cache_read=4.4e-07, cache_read_above_272k=8.8e-07, + output_cost=2.2e-05, output_cost_above_272k=3.3e-05, ), GptProfile( model_id="global.openai.gpt-5.6-sol", - input_cost=5e-06, input_cost_above_272k=1e-05, - cache_write=6.25e-06, cache_write_above_272k=1.25e-05, - cache_read=5e-07, cache_read_above_272k=1e-06, - output_cost=3e-05, output_cost_above_272k=4.5e-05, + input_cost=4e-06, input_cost_above_272k=8e-06, + cache_write=5e-06, cache_write_above_272k=1e-05, + cache_read=4e-07, cache_read_above_272k=8e-07, + output_cost=2e-05, output_cost_above_272k=3e-05, ), GptProfile( model_id="us.openai.gpt-5.6-terra", @@ -221,7 +221,7 @@ def test_bedrock_gpt_5_6_above_272k_tier_applies_to_cost(local_model_cost_map): custom_llm_provider="bedrock", ) - assert cost == pytest.approx((300000 * 1.1e-05) + (1000 * 4.95e-05), rel=1e-9) + assert cost == pytest.approx((300000 * 8.8e-06) + (1000 * 3.3e-05), rel=1e-9) def test_bedrock_gpt_5_6_bills_cache_read_tokens(local_model_cost_map): @@ -241,10 +241,10 @@ def test_bedrock_gpt_5_6_bills_cache_read_tokens(local_model_cost_map): custom_llm_provider="bedrock", ) - expected = (2 * 5.5e-06) + (15609 * 5.5e-07) + (5 * 3.3e-05) + expected = (2 * 4.4e-06) + (15609 * 4.4e-07) + (5 * 2.2e-05) assert cost == pytest.approx(expected, rel=1e-9) # Without cache_read_input_token_cost the cached prefix bills at zero. - assert cost > (15611 * 5.5e-06) * 0.1 + assert cost > (15611 * 4.4e-06) * 0.1 def test_bedrock_gpt_5_6_bills_cache_write_tokens(local_model_cost_map): @@ -263,7 +263,7 @@ def test_bedrock_gpt_5_6_bills_cache_write_tokens(local_model_cost_map): custom_llm_provider="bedrock", ) - expected = (2 * 5.5e-06) + (15609 * 6.875e-06) + (5 * 3.3e-05) + expected = (2 * 4.4e-06) + (15609 * 5.5e-06) + (5 * 2.2e-05) assert cost == pytest.approx(expected, rel=1e-9) diff --git a/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py b/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py index 9e05d48a18f..94c2d6ff6b3 100644 --- a/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py +++ b/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py @@ -1506,10 +1506,19 @@ class TestBedrockMantleResponsesPricing: assert info["cache_read_input_token_cost"] == pytest.approx(2.75e-07) assert info["max_input_tokens"] == 272000 + def test_gpt_5_6_cyber_pricing_and_mode(self, local_cost_map): + info = litellm.get_model_info("bedrock_mantle/openai.gpt-5.6-cyber") + assert info["mode"] == "responses" + assert info["input_cost_per_token"] == pytest.approx(1.375e-05) + assert info["cache_creation_input_token_cost"] == pytest.approx(1.71875e-05) + assert info["cache_read_input_token_cost"] == pytest.approx(1.375e-06) + assert info["output_cost_per_token"] == pytest.approx(8.25e-05) + assert info["max_input_tokens"] == 272000 + @pytest.mark.parametrize( "model, input_cost, cache_creation_cost, cache_read_cost, output_cost", [ - ("openai.gpt-5.6-sol", 5.5e-06, 6.875e-06, 5.5e-07, 3.3e-05), + ("openai.gpt-5.6-sol", 4.4e-06, 5.5e-06, 4.4e-07, 2.2e-05), ("openai.gpt-5.6-terra", 2.2e-06, 2.75e-06, 2.2e-07, 1.32e-05), ("openai.gpt-5.6-luna", 2.2e-07, 2.75e-07, 2.2e-08, 1.32e-06), ], @@ -1532,7 +1541,7 @@ class TestBedrockMantleResponsesPricing: @pytest.mark.parametrize( "model, input_cost, output_cost", [ - ("openai.gpt-5.6-sol", 5.5e-06, 3.3e-05), + ("openai.gpt-5.6-sol", 4.4e-06, 2.2e-05), ("openai.gpt-5.6-terra", 2.2e-06, 1.32e-05), ("openai.gpt-5.6-luna", 2.2e-07, 1.32e-06), ], From 310591f63c283633199cbc0d3249f3d911d0220a Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 25 Aug 2026 14:05:07 +0000 Subject: [PATCH 2/7] test(model_prices): pin claude 3 1h cache write rates to 2x base input Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...test_anthropic_sonnet_1hr_cache_pricing.py | 53 +++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/tests/test_litellm/test_anthropic_sonnet_1hr_cache_pricing.py b/tests/test_litellm/test_anthropic_sonnet_1hr_cache_pricing.py index f534b431508..11fcdf31dfc 100644 --- a/tests/test_litellm/test_anthropic_sonnet_1hr_cache_pricing.py +++ b/tests/test_litellm/test_anthropic_sonnet_1hr_cache_pricing.py @@ -87,3 +87,56 @@ def test_anthropic_sonnet_1hr_cache_write_pricing( ), f"{model_key}: long-context 1hr/5min ratio is {ratio_lc}, expected 1.6" else: assert "cache_creation_input_token_cost_above_1hr_above_200k_tokens" not in info + + +CLAUDE_3_EXPECTED = [ + ("claude-3-haiku-20240307", 5e-07), + ("claude-3-opus-20240229", 3e-05), +] + + +@pytest.mark.parametrize("model_key, expected_1hr", CLAUDE_3_EXPECTED) +def test_claude_3_1hr_cache_write_pricing(model_data, model_key, expected_1hr): + """Haiku 3 and Opus 3 both carried Sonnet's 6e-06 1hr rate, overbilling Haiku 3 + 1-hour cache writes 12x and underbilling Opus 3 5x.""" + info = model_data[model_key] + + assert info["cache_creation_input_token_cost_above_1hr"] == expected_1hr + + +@pytest.mark.parametrize("model_key, expected_1hr", CLAUDE_3_EXPECTED) +def test_backup_matches_main_for_claude_3_1hr_cache_write(model_key, expected_1hr): + json_path = os.path.join( + os.path.dirname(__file__), + "../../litellm/model_prices_and_context_window_backup.json", + ) + with open(json_path) as f: + backup = json.load(f) + + assert ( + backup[model_key]["cache_creation_input_token_cost_above_1hr"] == expected_1hr + ) + + +def test_first_party_anthropic_1hr_cache_writes_are_2x_base_input(model_data): + """Anthropic charges 1-hour cache writes at 2x base input for every first-party + model, so any entry that drifts off that multiple is a copy-paste error.""" + offenders = tuple( + ( + model_key, + info["input_cost_per_token"], + info["cache_creation_input_token_cost_above_1hr"], + ) + for model_key, info in model_data.items() + if isinstance(info, dict) + and info.get("litellm_provider") == "anthropic" + and info.get("input_cost_per_token") + and info.get("cache_creation_input_token_cost_above_1hr") + and abs( + info["cache_creation_input_token_cost_above_1hr"] + - 2 * info["input_cost_per_token"] + ) + > 1e-12 + ) + + assert offenders == (), f"1hr cache write is not 2x base input for: {offenders}" From fb15851f535dbb2bf68b85a0b73e3b4bf1065319 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 25 Aug 2026 19:16:14 +0000 Subject: [PATCH 3/7] fix(model_prices): verified Novita, DeepInfra, W&B, Gemini cache-read and Fireworks registry fixes Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 2340 ++++++++++++++++- model_prices_and_context_window.json | 2340 ++++++++++++++++- 2 files changed, 4406 insertions(+), 274 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 87b4b08ea62..e133f31cdac 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -16023,12 +16023,13 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 9e-08, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "max_tokens": 131072, @@ -16045,11 +16046,12 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 7e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { "max_tokens": 131072, @@ -16066,12 +16068,13 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3.9e-07, + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "max_tokens": 32768, @@ -16099,12 +16102,13 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 6e-08, + "input_cost_per_token": 1.2e-07, "output_cost_per_token": 2.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { "max_tokens": 40960, @@ -16122,11 +16126,12 @@ "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, - "output_cost_per_token": 6e-07, + "output_cost_per_token": 5.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -16143,23 +16148,25 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.9e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, + "input_cost_per_token": 8e-08, "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "max_tokens": 262144, @@ -16176,23 +16183,27 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 1.2e-06, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 1.4e-06, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_tokens": 262144, @@ -16219,11 +16230,12 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, + "input_cost_per_token": 8.5e-07, + "output_cost_per_token": 8.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { "max_tokens": 131072, @@ -16349,36 +16361,41 @@ "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 3.8e-07, + "input_cost_per_token": 3.2e-07, "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 8.8e-07, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "cache_read_input_token_cost": 1.35e-07, + "supports_prompt_caching": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 9.5e-07, "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_reasoning": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { "max_tokens": 163840, @@ -16432,33 +16449,36 @@ "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, + "input_cost_per_token": 8e-08, "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "max_tokens": 131072, @@ -16496,34 +16516,37 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.9e-07, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.2e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "max_tokens": 131072, @@ -16571,12 +16594,13 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_tokens": 131072, @@ -16594,11 +16618,12 @@ "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, - "output_cost_per_token": 3e-08, + "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { "max_tokens": 65536, @@ -16625,12 +16650,13 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 4e-08, + "input_cost_per_token": 1.9e-08, + "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "max_tokens": 32768, @@ -16712,14 +16738,16 @@ }, "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": { "max_input_tokens": 262144, - "input_cost_per_token": 5e-08, + "input_cost_per_token": 8e-08, "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat", - "source": "https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning", + "source": "https://deepinfra.com/pricing", "supports_tool_choice": true, "supports_function_calling": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "max_tokens": 131072, @@ -16736,23 +16764,25 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4.5e-07, + "input_cost_per_token": 3.7e-08, + "output_cost_per_token": 1.7e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.5e-07, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -20237,7 +20267,7 @@ "supports_image_size": false }, "gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", @@ -20247,7 +20277,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -20373,7 +20403,7 @@ }, "gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-language-models", @@ -20383,7 +20413,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -21953,7 +21983,7 @@ "supports_image_size": false }, "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-02-17", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -21965,7 +21995,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22001,7 +22031,7 @@ "supports_image_size": false }, "gemini/gemini-flash-latest": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", @@ -22012,7 +22042,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22047,7 +22077,7 @@ } }, "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -22058,7 +22088,7 @@ "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22094,7 +22124,7 @@ }, "gemini/gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -22105,7 +22135,7 @@ "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -42511,19 +42541,21 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.015, - "output_cost_per_token": 0.06, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.7e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/openai/gpt-oss-20b": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.005, - "output_cost_per_token": 0.02, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -42547,10 +42579,11 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 0.1, - "output_cost_per_token": 0.15, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 1.5e-06, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -42602,19 +42635,21 @@ "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.022, - "output_cost_per_token": 0.022, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 161000, "max_output_tokens": 128000, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.165, + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 1.65e-06, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-R1-0528": { "max_tokens": 161000, @@ -42638,10 +42673,11 @@ "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.071, - "output_cost_per_token": 0.071, + "input_cost_per_token": 7.1e-07, + "output_cost_per_token": 7.1e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 64000, @@ -46608,8 +46644,8 @@ "novita/xiaomimimo/mimo-v2-flash": { "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, "max_tokens": 32000, @@ -46618,8 +46654,8 @@ "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token_cache_hit": 2e-08, + "cache_read_input_token_cost": 2.4e-08, + "input_cost_per_token_cache_hit": 2.4e-08, "supports_reasoning": true }, "novita/zai-org/autoglm-phone-9b-multilingual": { @@ -46639,14 +46675,16 @@ "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true }, "novita/minimax/minimax-m2": { "litellm_provider": "novita", @@ -46662,7 +46700,8 @@ "supports_system_messages": true, "cache_read_input_token_cost": 3e-08, "input_cost_per_token_cache_hit": 3e-08, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/paddlepaddle/paddleocr-vl": { "litellm_provider": "novita", @@ -46700,7 +46739,9 @@ "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/zai-org/glm-4.6v": { "litellm_provider": "novita", @@ -46765,7 +46806,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_reasoning": true }, "novita/qwen/qwen3-next-80b-a3b-thinking": { "litellm_provider": "novita", @@ -46877,8 +46919,8 @@ "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -46888,8 +46930,8 @@ "novita/qwen/qwen3-coder-480b-a35b-instruct": { "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.3e-06, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, @@ -46935,8 +46977,8 @@ "input_cost_per_token": 5.7e-07, "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -46949,8 +46991,8 @@ "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -46997,7 +47039,8 @@ "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/google/gemma-3-12b-it": { "litellm_provider": "novita", @@ -47076,13 +47119,14 @@ "mode": "chat", "input_cost_per_token": 1.35e-07, "output_cost_per_token": 4e-07, - "max_input_tokens": 131072, - "max_output_tokens": 120000, - "max_tokens": 120000, + "max_input_tokens": 12288, + "max_output_tokens": 12288, + "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/qwen/qwen-2.5-72b-instruct": { "litellm_provider": "novita", @@ -47122,7 +47166,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528": { "litellm_provider": "novita", @@ -47162,7 +47207,8 @@ "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/microsoft/wizardlm-2-8x22b": { "litellm_provider": "novita", @@ -47172,7 +47218,8 @@ "max_input_tokens": 65535, "max_output_tokens": 8000, "max_tokens": 8000, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528-qwen3-8b": { "litellm_provider": "novita", @@ -47219,7 +47266,8 @@ "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "litellm_provider": "novita", @@ -47230,7 +47278,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "supports_vision": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/meta-llama/llama-4-scout-17b-16e-instruct": { "litellm_provider": "novita", @@ -47366,7 +47415,9 @@ "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/google/gemma-3-27b-it": { "litellm_provider": "novita", @@ -47404,7 +47455,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/Sao10K/L3-8B-Stheno-v3.2": { "litellm_provider": "novita", @@ -47472,7 +47524,9 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 2.5e-08, + "supports_prompt_caching": true }, "novita/qwen/qwen3-vl-30b-a3b-instruct": { "litellm_provider": "novita", @@ -47593,10 +47647,12 @@ "input_cost_per_token": 3e-08, "output_cost_per_token": 3e-08, "max_input_tokens": 128000, - "max_output_tokens": 20000, - "max_tokens": 20000, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/qwen/qwen2.5-7b-instruct": { "litellm_provider": "novita", @@ -47604,8 +47660,8 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 7e-08, "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -50838,14 +50894,14 @@ "supports_embedding_image_input": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": { - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 1.4e-07, + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "output_cost_per_token": 6.6e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -51152,5 +51208,2015 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "novita/zai-org/glm-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 1.3200000000000002e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/tencent/hy3": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 5.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5.2": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.499999999999999e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/mindai/macaron-v1-venti": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m3": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.35e-07, + "input_cost_per_token": 1.6000000000000001e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/inclusionai/ling-3.0-flash-fast": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/inclusionai/ling-3.0-flash": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/mindai/macaron-v1-tall": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4.5000000000000003e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.6e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/stepfun/step-3.7-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2.0000000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5.0000000000000004e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.0000000000000002e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/baidu/cobuddy": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "novita", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.13e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/xiaomimimo/mimo-v2.5": { + "cache_read_input_token_cost": 3.4e-09, + "input_cost_per_token": 1.6800000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.3600000000000004e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.7-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/xiaomimimo/mimo-v2.5-pro": { + "cache_read_input_token_cost": 4.3e-09, + "input_cost_per_token": 5.22e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.044e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.6-27b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.6000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/moonshotai/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 8.000000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.38e-06, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.7-highspeed": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/google/gemma-4-31b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "novita", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.7": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.5-highspeed": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.5-27b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-122b-a10b": { + "input_cost_per_token": 4.0000000000000003e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-35b-a3b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-397b-a17b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.6000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/minimax/minimax-m2.5": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5": { + "cache_read_input_token_cost": 2.0000000000000002e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "novita", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3-coder-next": { + "input_cost_per_token": 2.0000000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-ocr-2": { + "input_cost_per_token": 3e-08, + "litellm_provider": "novita", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://novita.ai/pricing", + "supports_vision": true + }, + "novita/moonshotai/kimi-k2.5": { + "cache_read_input_token_cost": 1.0000000000000001e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-4.7-h": { + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-4.7-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 7e-08, + "litellm_provider": "novita", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.48e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.4850000000000002e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek_v3": { + "input_cost_per_token": 8.900000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 8.900000000000001e-07, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-r1": { + "input_cost_per_token": 4e-06, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v3/community": { + "input_cost_per_token": 8.900000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 8.900000000000001e-07, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-r1/community": { + "input_cost_per_token": 4e-06, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/thudm/glm-4-32b-0414": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "novita", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.66e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "novita", + "max_input_tokens": 131000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2e-08, + "source": "https://api.novita.ai/v3/openai/models", + "supports_response_schema": true, + "supports_vision": false + }, + "wandb/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.15e-06, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/google/gemma-4-31B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/ibm-granite/granite-4.1-8b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/meta-llama/Llama-3.1-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/MiniMaxAI/MiniMax-M3": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 9.6e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.1e-07, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3.41e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2.5e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 2.75e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/OpenPipe/Qwen3-14B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.2e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.8-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.6-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 1.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.5-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/zai-org/GLM-5.2": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.6e-07, + "output_cost_per_token": 2.42e-06, + "cache_read_input_token_cost": 1.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "deepinfra/openai/gpt-oss-120b-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M2.7": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it-Ultra": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 7.6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.5": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 2.25e-06, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.7-Flash": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 1e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.6": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-4-8": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-sonnet-4-6": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.5-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/XiaomiMiMo/MiMo-V2.5": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it-turbo": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.4e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/thinkingmachines/Inkling-Small": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/meta-models/Muse-Glimmer-30B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-Max-Thinking": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8.8e-07, + "cache_read_input_token_cost": 1.1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 2.6e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 9.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-5": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/thinkingmachines/Inkling": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4.05e-06, + "cache_read_input_token_cost": 1.6e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 2.6e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.7-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 7.5e-06, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-mini": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M3": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 2.8e-07, + "output_cost_per_token": 1.1e-06, + "cache_read_input_token_cost": 5.6e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.1-flash-lite": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.7-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/inclusionAI/Ling-3.0-flash": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.2e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/stepfun-ai/Step-3.7-Flash": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.15e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-1.8": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/tencent/Hy3": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.8e-07, + "cache_read_input_token_cost": 3.5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-code": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-pro": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.08e-06, + "cache_read_input_token_cost": 1.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 2.5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6.8e-07, + "output_cost_per_token": 3.4e-06, + "cache_read_input_token_cost": 1.36e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-sonnet-5": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-397B-A17B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.6e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-E4B-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V3.2": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 3.8e-07, + "cache_read_input_token_cost": 1.3e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "cache_read_input_token_cost": 2.06e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-fable-5": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-122B-A10B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.9e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5.1": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 1.05e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 2.05e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 2.6e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 8.5e-08, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5.2": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 1.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 2.85e-06, + "output_cost_per_token": 1.425e-05, + "cache_read_input_token_cost": 2.85e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-4-7": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.6-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-26B-A4B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.1-pro": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-haiku-4-5": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/openai/gpt-oss-120b-Ultra": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 9.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-9B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.7e-06, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.7": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.75e-06, + "cache_read_input_token_cost": 8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 3.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 87b4b08ea62..e133f31cdac 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -16023,12 +16023,13 @@ "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 9e-08, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "max_tokens": 131072, @@ -16045,11 +16046,12 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 3e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 7e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/QwQ-32B": { "max_tokens": 131072, @@ -16066,12 +16068,13 @@ "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 1.2e-07, - "output_cost_per_token": 3.9e-07, + "input_cost_per_token": 3.6e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "max_tokens": 32768, @@ -16099,12 +16102,13 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 6e-08, + "input_cost_per_token": 1.2e-07, "output_cost_per_token": 2.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B": { "max_tokens": 40960, @@ -16122,11 +16126,12 @@ "max_input_tokens": 262144, "max_output_tokens": 262144, "input_cost_per_token": 9e-08, - "output_cost_per_token": 6e-07, + "output_cost_per_token": 5.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -16143,23 +16148,25 @@ "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 2.9e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-32B": { "max_tokens": 40960, "max_input_tokens": 40960, "max_output_tokens": 40960, - "input_cost_per_token": 1e-07, + "input_cost_per_token": 8e-08, "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "max_tokens": 262144, @@ -16176,23 +16183,27 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 2.9e-07, - "output_cost_per_token": 1.2e-06, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 1.4e-06, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.1e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_tokens": 262144, @@ -16219,11 +16230,12 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 6.5e-07, - "output_cost_per_token": 7.5e-07, + "input_cost_per_token": 8.5e-07, + "output_cost_per_token": 8.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": false + "supports_tool_choice": false, + "source": "https://deepinfra.com/pricing" }, "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { "max_tokens": 131072, @@ -16349,36 +16361,41 @@ "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 3.8e-07, + "input_cost_per_token": 3.2e-07, "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 2.5e-07, - "output_cost_per_token": 8.8e-07, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "cache_read_input_token_cost": 1.35e-07, + "supports_prompt_caching": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 163840, "max_input_tokens": 163840, "max_output_tokens": 163840, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 1e-06, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 9.5e-07, "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, "supports_reasoning": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { "max_tokens": 163840, @@ -16432,33 +16449,36 @@ "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 5e-08, - "output_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-27b-it": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 9e-08, + "input_cost_per_token": 8e-08, "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/google/gemma-3-4b-it": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 8e-08, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "max_tokens": 131072, @@ -16496,34 +16516,37 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 3.9e-07, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.2e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_function_calling": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { "max_tokens": 1048576, "max_input_tokens": 1048576, "max_output_tokens": 1048576, - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 327680, "max_input_tokens": 327680, "max_output_tokens": 327680, - "input_cost_per_token": 8e-08, + "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "max_tokens": 131072, @@ -16571,12 +16594,13 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.8e-07, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_tokens": 131072, @@ -16594,11 +16618,12 @@ "max_input_tokens": 131072, "max_output_tokens": 131072, "input_cost_per_token": 2e-08, - "output_cost_per_token": 3e-08, + "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/microsoft/WizardLM-2-8x22B": { "max_tokens": 65536, @@ -16625,12 +16650,13 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 2e-08, - "output_cost_per_token": 4e-08, + "input_cost_per_token": 1.9e-08, + "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "max_tokens": 32768, @@ -16712,14 +16738,16 @@ }, "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": { "max_input_tokens": 262144, - "input_cost_per_token": 5e-08, + "input_cost_per_token": 8e-08, "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat", - "source": "https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning", + "source": "https://deepinfra.com/pricing", "supports_tool_choice": true, "supports_function_calling": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "max_tokens": 131072, @@ -16736,23 +16764,25 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 5e-08, - "output_cost_per_token": 4.5e-07, + "input_cost_per_token": 3.7e-08, + "output_cost_per_token": 1.7e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/openai/gpt-oss-20b": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 4e-08, - "output_cost_per_token": 1.5e-07, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_function_calling": true + "supports_function_calling": true, + "source": "https://deepinfra.com/pricing" }, "deepinfra/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -20237,7 +20267,7 @@ "supports_image_size": false }, "gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-language-models", @@ -20247,7 +20277,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -20373,7 +20403,7 @@ }, "gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-language-models", @@ -20383,7 +20413,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -21953,7 +21983,7 @@ "supports_image_size": false }, "gemini/gemini-2.5-flash-preview-09-2025": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "deprecation_date": "2026-02-17", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, @@ -21965,7 +21995,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22001,7 +22031,7 @@ "supports_image_size": false }, "gemini/gemini-flash-latest": { - "cache_read_input_token_cost": 7.5e-08, + "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", @@ -22012,7 +22042,7 @@ "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22047,7 +22077,7 @@ } }, "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 3e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -22058,7 +22088,7 @@ "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -22094,7 +22124,7 @@ }, "gemini/gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", - "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost": 1e-08, "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -22105,7 +22135,7 @@ "output_cost_per_reasoning_token": 4e-07, "output_cost_per_token": 4e-07, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -42511,19 +42541,21 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.015, - "output_cost_per_token": 0.06, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.7e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/openai/gpt-oss-20b": { "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 0.005, - "output_cost_per_token": 0.02, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 1.3e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -42547,10 +42579,11 @@ "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, - "input_cost_per_token": 0.1, - "output_cost_per_token": 0.15, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 1.5e-06, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -42602,19 +42635,21 @@ "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.022, - "output_cost_per_token": 0.022, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 161000, "max_output_tokens": 128000, - "input_cost_per_token": 0.055, - "output_cost_per_token": 0.165, + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 1.65e-06, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-R1-0528": { "max_tokens": 161000, @@ -42638,10 +42673,11 @@ "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, - "input_cost_per_token": 0.071, - "output_cost_per_token": 0.071, + "input_cost_per_token": 7.1e-07, + "output_cost_per_token": 7.1e-07, "litellm_provider": "wandb", - "mode": "chat" + "mode": "chat", + "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 64000, @@ -46608,8 +46644,8 @@ "novita/xiaomimimo/mimo-v2-flash": { "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 1e-07, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 1.1e-07, + "output_cost_per_token": 3.3e-07, "max_input_tokens": 262144, "max_output_tokens": 32000, "max_tokens": 32000, @@ -46618,8 +46654,8 @@ "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, - "cache_read_input_token_cost": 2e-08, - "input_cost_per_token_cache_hit": 2e-08, + "cache_read_input_token_cost": 2.4e-08, + "input_cost_per_token_cache_hit": 2.4e-08, "supports_reasoning": true }, "novita/zai-org/autoglm-phone-9b-multilingual": { @@ -46639,14 +46675,16 @@ "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, "supports_response_schema": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true }, "novita/minimax/minimax-m2": { "litellm_provider": "novita", @@ -46662,7 +46700,8 @@ "supports_system_messages": true, "cache_read_input_token_cost": 3e-08, "input_cost_per_token_cache_hit": 3e-08, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/paddlepaddle/paddleocr-vl": { "litellm_provider": "novita", @@ -46700,7 +46739,9 @@ "max_tokens": 32768, "supports_vision": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/zai-org/glm-4.6v": { "litellm_provider": "novita", @@ -46765,7 +46806,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_response_schema": true + "supports_response_schema": true, + "supports_reasoning": true }, "novita/qwen/qwen3-next-80b-a3b-thinking": { "litellm_provider": "novita", @@ -46877,8 +46919,8 @@ "input_cost_per_token": 6e-07, "output_cost_per_token": 2.5e-06, "max_input_tokens": 262144, - "max_output_tokens": 262144, - "max_tokens": 262144, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -46888,8 +46930,8 @@ "novita/qwen/qwen3-coder-480b-a35b-instruct": { "litellm_provider": "novita", "mode": "chat", - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.3e-06, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.55e-06, "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, @@ -46935,8 +46977,8 @@ "input_cost_per_token": 5.7e-07, "output_cost_per_token": 2.3e-06, "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 100352, + "max_tokens": 100352, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -46949,8 +46991,8 @@ "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.12e-06, "max_input_tokens": 163840, - "max_output_tokens": 163840, - "max_tokens": 163840, + "max_output_tokens": 65536, + "max_tokens": 65536, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -46997,7 +47039,8 @@ "max_input_tokens": 16384, "max_output_tokens": 16384, "max_tokens": 16384, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/google/gemma-3-12b-it": { "litellm_provider": "novita", @@ -47076,13 +47119,14 @@ "mode": "chat", "input_cost_per_token": 1.35e-07, "output_cost_per_token": 4e-07, - "max_input_tokens": 131072, - "max_output_tokens": 120000, - "max_tokens": 120000, + "max_input_tokens": 12288, + "max_output_tokens": 12288, + "max_tokens": 12288, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/qwen/qwen-2.5-72b-instruct": { "litellm_provider": "novita", @@ -47122,7 +47166,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528": { "litellm_provider": "novita", @@ -47162,7 +47207,8 @@ "max_input_tokens": 8192, "max_output_tokens": 8192, "max_tokens": 8192, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/microsoft/wizardlm-2-8x22b": { "litellm_provider": "novita", @@ -47172,7 +47218,8 @@ "max_input_tokens": 65535, "max_output_tokens": 8000, "max_tokens": 8000, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/deepseek/deepseek-r1-0528-qwen3-8b": { "litellm_provider": "novita", @@ -47219,7 +47266,8 @@ "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8": { "litellm_provider": "novita", @@ -47230,7 +47278,8 @@ "max_output_tokens": 8192, "max_tokens": 8192, "supports_vision": true, - "supports_system_messages": true + "supports_system_messages": true, + "supports_response_schema": true }, "novita/meta-llama/llama-4-scout-17b-16e-instruct": { "litellm_provider": "novita", @@ -47366,7 +47415,9 @@ "max_output_tokens": 20000, "max_tokens": 20000, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/google/gemma-3-27b-it": { "litellm_provider": "novita", @@ -47404,7 +47455,8 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": true }, "novita/Sao10K/L3-8B-Stheno-v3.2": { "litellm_provider": "novita", @@ -47472,7 +47524,9 @@ "supports_parallel_function_calling": true, "supports_tool_choice": true, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "cache_read_input_token_cost": 2.5e-08, + "supports_prompt_caching": true }, "novita/qwen/qwen3-vl-30b-a3b-instruct": { "litellm_provider": "novita", @@ -47593,10 +47647,12 @@ "input_cost_per_token": 3e-08, "output_cost_per_token": 3e-08, "max_input_tokens": 128000, - "max_output_tokens": 20000, - "max_tokens": 20000, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_system_messages": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true, + "supports_tool_choice": true }, "novita/qwen/qwen2.5-7b-instruct": { "litellm_provider": "novita", @@ -47604,8 +47660,8 @@ "input_cost_per_token": 7e-08, "output_cost_per_token": 7e-08, "max_input_tokens": 32000, - "max_output_tokens": 32000, - "max_tokens": 32000, + "max_output_tokens": 8192, + "max_tokens": 8192, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, @@ -50838,14 +50894,14 @@ "supports_embedding_image_input": true }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": { - "cache_read_input_token_cost": 2.8e-08, - "input_cost_per_token": 1.4e-07, + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token": 2.2e-07, "litellm_provider": "fireworks_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.8e-07, + "output_cost_per_token": 6.6e-07, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -51152,5 +51208,2015 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "novita/zai-org/glm-5.3": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 1.3200000000000002e-07, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/moonshotai/kimi-k3": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/tencent/hy3": { + "cache_read_input_token_cost": 3.5e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 5.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5.2": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/moonshotai/kimi-k2.7-code": { + "cache_read_input_token_cost": 1.9e-07, + "input_cost_per_token": 9.499999999999999e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash-vision-exp": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash-0731": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/mindai/macaron-v1-venti": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.5e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.5e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m3": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek-v4-flash": { + "cache_read_input_token_cost": 2.8e-08, + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 2.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v4-pro": { + "cache_read_input_token_cost": 1.35e-07, + "input_cost_per_token": 1.6000000000000001e-06, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 393216, + "max_tokens": 393216, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/inclusionai/ling-3.0-flash-fast": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.8-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 6e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/inclusionai/ling-3.0-flash": { + "cache_read_input_token_cost": 1.2e-08, + "input_cost_per_token": 6e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/mindai/macaron-v1-tall": { + "cache_read_input_token_cost": 8e-08, + "input_cost_per_token": 4.5000000000000003e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.6e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/stepfun/step-3.7-flash": { + "cache_read_input_token_cost": 4e-08, + "input_cost_per_token": 2.0000000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 1.15e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/nvidia/nemotron-3-nano-30b-a3b": { + "input_cost_per_token": 5.0000000000000004e-08, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.0000000000000002e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/baidu/cobuddy": { + "cache_read_input_token_cost": 7e-08, + "input_cost_per_token": 2.8e-07, + "litellm_provider": "novita", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.13e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/xiaomimimo/mimo-v2.5": { + "cache_read_input_token_cost": 3.4e-09, + "input_cost_per_token": 1.6800000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.3600000000000004e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.7-max": { + "cache_read_input_token_cost": 2.5e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "novita", + "max_input_tokens": 1000000, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.75e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/xiaomimimo/mimo-v2.5-pro": { + "cache_read_input_token_cost": 4.3e-09, + "input_cost_per_token": 5.22e-07, + "litellm_provider": "novita", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.044e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.6-27b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.6000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/moonshotai/kimi-k2.6": { + "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 8.000000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5.1": { + "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 1.38e-06, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.7-highspeed": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5v-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 1.3e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/google/gemma-4-31b-it": { + "input_cost_per_token": 1.4e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-5-turbo": { + "cache_read_input_token_cost": 2.4e-07, + "input_cost_per_token": 1.2e-06, + "litellm_provider": "novita", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.7": { + "cache_read_input_token_cost": 6e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/minimax/minimax-m2.5-highspeed": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.5-27b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2.4e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-122b-a10b": { + "input_cost_per_token": 4.0000000000000003e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-35b-a3b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/qwen/qwen3.5-397b-a17b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.6000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/minimax/minimax-m2.5": { + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131100, + "max_tokens": 131100, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-5": { + "cache_read_input_token_cost": 2.0000000000000002e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "novita", + "max_input_tokens": 202800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.2000000000000003e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3-coder-next": { + "input_cost_per_token": 2.0000000000000002e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-ocr-2": { + "input_cost_per_token": 3e-08, + "litellm_provider": "novita", + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 3e-08, + "source": "https://novita.ai/pricing", + "supports_vision": true + }, + "novita/moonshotai/kimi-k2.5": { + "cache_read_input_token_cost": 1.0000000000000001e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/zai-org/glm-4.7-h": { + "cache_read_input_token_cost": 1.1e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "novita", + "max_input_tokens": 204800, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2.2e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/zai-org/glm-4.7-flash": { + "cache_read_input_token_cost": 1e-08, + "input_cost_per_token": 7e-08, + "litellm_provider": "novita", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4.0000000000000003e-07, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.48e-07, + "litellm_provider": "novita", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.4850000000000002e-06, + "source": "https://novita.ai/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "novita/deepseek/deepseek_v3": { + "input_cost_per_token": 8.900000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 8.900000000000001e-07, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-r1": { + "input_cost_per_token": 4e-06, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-v3/community": { + "input_cost_per_token": 8.900000000000001e-07, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 8.900000000000001e-07, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/deepseek/deepseek-r1/community": { + "input_cost_per_token": 4e-06, + "litellm_provider": "novita", + "max_input_tokens": 64000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/thudm/glm-4-32b-0414": { + "input_cost_per_token": 5.5e-07, + "litellm_provider": "novita", + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.66e-06, + "source": "https://api.novita.ai/v3/openai/models", + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "novita/meta-llama/llama-3.2-1b-instruct": { + "input_cost_per_token": 2e-08, + "litellm_provider": "novita", + "max_input_tokens": 131000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 2e-08, + "source": "https://api.novita.ai/v3/openai/models", + "supports_response_schema": true, + "supports_vision": false + }, + "wandb/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.15e-06, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/google/gemma-4-31B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/ibm-granite/granite-4.1-8b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/meta-llama/Llama-3.1-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/MiniMaxAI/MiniMax-M3": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 9.6e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.1e-07, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3.41e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2.5e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 2.75e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/OpenPipe/Qwen3-14B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2.2e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.8-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.6-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 1.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3.5-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.25e-06, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": true, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "wandb/zai-org/GLM-5.2": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.6e-07, + "output_cost_per_token": 2.42e-06, + "cache_read_input_token_cost": 1.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "wandb", + "mode": "chat", + "supports_vision": false, + "source": "https://wandb.ai/site/pricing/tokens/" + }, + "deepinfra/openai/gpt-oss-120b-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M2.7": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it-Ultra": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 7.6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.5": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 2.25e-06, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.7-Flash": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 1e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.6": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-4-8": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-sonnet-4-6": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.5-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 1.5e-06, + "output_cost_per_token": 9e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/XiaomiMiMo/MiMo-V2.5": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it-turbo": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3.4e-07, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/thinkingmachines/Inkling-Small": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/meta-models/Muse-Glimmer-30B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-Max-Thinking": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 8.8e-07, + "cache_read_input_token_cost": 1.1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 2.6e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.6-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 9.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/Nemotron-Content-Safety-3.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 2e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-5": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/thinkingmachines/Inkling": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 9.5e-07, + "output_cost_per_token": 4.05e-06, + "cache_read_input_token_cost": 1.6e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.6": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 1.5e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 2.6e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.7-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 2.5e-06, + "output_cost_per_token": 7.5e-06, + "cache_read_input_token_cost": 5e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-mini": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "cache_read_input_token_cost": 2e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-2.4T-A95B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 6e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M3": { + "max_tokens": 524288, + "max_input_tokens": 524288, + "input_cost_per_token": 2.8e-07, + "output_cost_per_token": 1.1e-06, + "cache_read_input_token_cost": 5.6e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.1-flash-lite": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.7-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 3.75e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/inclusionAI/Ling-3.0-flash": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.2e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/stepfun-ai/Step-3.7-Flash": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.15e-06, + "cache_read_input_token_cost": 4e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-35B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-1.8": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 2e-06, + "cache_read_input_token_cost": 5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/tencent/Hy3": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.8e-07, + "cache_read_input_token_cost": 3.5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-code": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/ByteDance/Seed-2.0-pro": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.08e-06, + "cache_read_input_token_cost": 1.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 2.5e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K2.7-Code": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 6.8e-07, + "output_cost_per_token": 3.4e-06, + "cache_read_input_token_cost": 1.36e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-sonnet-5": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-397B-A17B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2.2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.6e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-E4B-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V3.2": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "input_cost_per_token": 2.6e-07, + "output_cost_per_token": 3.8e-07, + "cache_read_input_token_cost": 1.3e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.8-Max": { + "max_tokens": 256000, + "max_input_tokens": 256000, + "input_cost_per_token": 1.65e-06, + "output_cost_per_token": 4.951e-06, + "cache_read_input_token_cost": 2.06e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-fable-5": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 1e-05, + "output_cost_per_token": 5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.2e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-122B-A10B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 2.9e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5.1": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 1.05e-06, + "output_cost_per_token": 3.5e-06, + "cache_read_input_token_cost": 2.05e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1.3e-06, + "output_cost_per_token": 2.6e-06, + "cache_read_input_token_cost": 1e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 8.5e-08, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-5.2": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 7.5e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 1.4e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/moonshotai/Kimi-K3": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 2.85e-06, + "output_cost_per_token": 1.425e-05, + "cache_read_input_token_cost": 2.85e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-opus-4-7": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 5e-06, + "output_cost_per_token": 2.5e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.6-27B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-26B-A4B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemini-3.1-pro": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1.2e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "cache_read_input_token_cost": 2e-07, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/anthropic/claude-haiku-4-5": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/deepseek-ai/DeepSeek-V4-Flash": { + "max_tokens": 1048576, + "max_input_tokens": 1048576, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.8e-07, + "cache_read_input_token_cost": 1.8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/openai/gpt-oss-120b-Ultra": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 9.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/Qwen/Qwen3.5-9B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/MiniMaxAI/MiniMax-M2.7-Turbo": { + "max_tokens": 196608, + "max_input_tokens": 196608, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.7e-06, + "cache_read_input_token_cost": 7e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/zai-org/GLM-4.7": { + "max_tokens": 202752, + "max_input_tokens": 202752, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.75e-06, + "cache_read_input_token_cost": 8e-08, + "supports_prompt_caching": true, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": false, + "source": "https://deepinfra.com/pricing" + }, + "deepinfra/google/gemma-4-31B-it": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 3.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_reasoning": true, + "supports_vision": true, + "source": "https://deepinfra.com/pricing" } } From d266326a42af668fa73c562b44d0322667265fc3 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 26 Aug 2026 16:56:53 +0000 Subject: [PATCH 4/7] fix(model_prices): azure gpt-4.1-nano retirement date, together deprecations, novita gpt-oss-120b vision flag, fireworks deepseek-v4-pro-0813 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 24 +++++- model_prices_and_context_window.json | 24 +++++- .../test_fireworks_serverless_model_costs.py | 86 +++++++++++++++++++ 3 files changed, 128 insertions(+), 6 deletions(-) create mode 100644 tests/test_litellm/test_fireworks_serverless_model_costs.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 267b43a2add..00c840c8df1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4681,7 +4681,7 @@ "supports_web_search": false }, "azure/gpt-4.1-nano": { - "deprecation_date": "2026-10-14", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -4714,7 +4714,7 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2026-10-14", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -18577,6 +18577,22 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/firefunction-v2": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", @@ -38475,6 +38491,7 @@ "supports_tool_choice": true }, "together_ai/google/gemma-3n-E4B-it": { + "deprecation_date": "2026-08-25", "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -38510,6 +38527,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/meta-llama/Llama-Guard-4-12B": { + "deprecation_date": "2026-08-25", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -47311,7 +47329,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 267b43a2add..00c840c8df1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4681,7 +4681,7 @@ "supports_web_search": false }, "azure/gpt-4.1-nano": { - "deprecation_date": "2026-10-14", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -4714,7 +4714,7 @@ "supports_vision": true }, "azure/gpt-4.1-nano-2025-04-14": { - "deprecation_date": "2026-10-14", + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 2.5e-08, "input_cost_per_token": 1e-07, "input_cost_per_token_batches": 5e-08, @@ -18577,6 +18577,22 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/firefunction-v2": { "input_cost_per_token": 9e-07, "litellm_provider": "fireworks_ai", @@ -38475,6 +38491,7 @@ "supports_tool_choice": true }, "together_ai/google/gemma-3n-E4B-it": { + "deprecation_date": "2026-08-25", "input_cost_per_token": 6e-08, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -38510,6 +38527,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/meta-llama/Llama-Guard-4-12B": { + "deprecation_date": "2026-08-25", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -47311,7 +47329,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": true, + "supports_vision": false, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true diff --git a/tests/test_litellm/test_fireworks_serverless_model_costs.py b/tests/test_litellm/test_fireworks_serverless_model_costs.py new file mode 100644 index 00000000000..0458af0da0e --- /dev/null +++ b/tests/test_litellm/test_fireworks_serverless_model_costs.py @@ -0,0 +1,86 @@ +""" +Validate the Fireworks AI Serverless entry added for #37274 exists in +`model_prices_and_context_window.json` and that the bare Fireworks model ID +resolves through `get_model_info`. + +Pricing as published at https://docs.fireworks.ai/serverless/pricing +(USD per 1M tokens, uncached input / cached input / output): + + accounts/fireworks/models/deepseek-v4-pro-0813 -> $1.32 / $0.044 / $3.96 +""" + +import json +import os + +import pytest + +import litellm +from litellm.utils import get_model_info + + +@pytest.fixture(scope="module", autouse=True) +def _local_model_cost_map(): + """ + Point litellm at the bundled cost map for the duration of this module + only. ``mp.undo()`` restores both the environment variable and + ``litellm.model_cost`` so nothing leaks into later tests. + """ + mp = pytest.MonkeyPatch() + mp.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + mp.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + get_model_info.cache_clear() + yield + mp.undo() + get_model_info.cache_clear() + + +NEW_ENTRIES = { + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { + "input_cost_per_token": 1.32e-06, + "cache_read_input_token_cost": 4.4e-08, + "output_cost_per_token": 3.96e-06, + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + }, +} + + +@pytest.fixture(scope="module") +def model_data(): + json_path = os.path.join( + os.path.dirname(__file__), "../../model_prices_and_context_window.json" + ) + with open(json_path) as f: + return json.load(f) + + +def test_fireworks_serverless_entries_exist(model_data): + """The new prefixed entry carries the pricing and metadata from #37274.""" + for key, expected in NEW_ENTRIES.items(): + assert key in model_data, f"{key} is missing from model_prices_and_context_window.json" + entry = model_data[key] + for field, value in expected.items(): + assert entry[field] == pytest.approx(value), f"{key}.{field}" + assert entry["litellm_provider"] == "fireworks_ai" + assert entry["mode"] == "chat" + assert entry["supports_function_calling"] is True + assert entry["supports_vision"] is False + + +def test_bare_fireworks_ids_resolve_through_prefixed_entries(): + """Bare IDs from #37274 resolve via the provider-prefix lookup path.""" + for bare_id, prefixed_key in [ + ( + "accounts/fireworks/models/deepseek-v4-pro-0813", + "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813", + ), + ]: + info = get_model_info(model=bare_id, custom_llm_provider="fireworks_ai") + expected = NEW_ENTRIES[prefixed_key] + assert info.get("key") == prefixed_key + assert info["litellm_provider"] == "fireworks_ai" + assert info["input_cost_per_token"] == pytest.approx(expected["input_cost_per_token"]) + assert info["cache_read_input_token_cost"] == pytest.approx(expected["cache_read_input_token_cost"]) + assert info["output_cost_per_token"] == pytest.approx(expected["output_cost_per_token"]) + assert info["max_input_tokens"] == expected["max_input_tokens"] + assert info["max_output_tokens"] == expected["max_output_tokens"] From d3ede97189e6c65157da5628a195e26972d0ec95 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 26 Aug 2026 16:57:26 +0000 Subject: [PATCH 5/7] fix(model_prices): keep novita gpt-oss-120b vision flag per provider catalog Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 2 +- model_prices_and_context_window.json | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 00c840c8df1..1ca0e748d38 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -47329,7 +47329,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": false, + "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 00c840c8df1..1ca0e748d38 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -47329,7 +47329,7 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_tool_choice": true, - "supports_vision": false, + "supports_vision": true, "supports_system_messages": true, "supports_response_schema": true, "supports_reasoning": true From 07c9812739b06d8d972f78fb141fedc834040b57 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 26 Aug 2026 17:18:51 +0000 Subject: [PATCH 6/7] fix(model_prices): carry anthropic behavior flags on deepinfra claude entries, move retired together models to deprecated list Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 84 +++++++++++-------- model_prices_and_context_window.json | 84 +++++++++++-------- .../test_together_ai_model_metadata.py | 4 +- 3 files changed, 102 insertions(+), 70 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 1ca0e748d38..5f565b84d38 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -52689,18 +52689,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-4-8": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { "max_tokens": 1000000, @@ -52890,18 +52893,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-5": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 512, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { "max_tokens": 524288, @@ -53199,18 +53205,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-sonnet-5": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 1e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { "max_tokens": 262144, @@ -53288,18 +53297,22 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-fable-5": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 5e-05, + "prompt_cache_min_tokens": 512, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "max_tokens": 262144, @@ -53408,18 +53421,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-4-7": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 2048, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { "max_tokens": 262144, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 1ca0e748d38..5f565b84d38 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -52689,18 +52689,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-4-8": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/anthropic/claude-sonnet-4-6": { "max_tokens": 1000000, @@ -52890,18 +52893,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-5": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 512, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/thinkingmachines/Inkling": { "max_tokens": 524288, @@ -53199,18 +53205,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-sonnet-5": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 1e-05, + "prompt_cache_min_tokens": 1024, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/Qwen/Qwen3.5-397B-A17B": { "max_tokens": 262144, @@ -53288,18 +53297,22 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-fable-5": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 1e-05, - "output_cost_per_token": 5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 5e-05, + "prompt_cache_min_tokens": 512, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "thinking_always_on": true }, "deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "max_tokens": 262144, @@ -53408,18 +53421,21 @@ "source": "https://deepinfra.com/pricing" }, "deepinfra/anthropic/claude-opus-4-7": { - "max_tokens": 1000000, - "max_input_tokens": 1000000, "input_cost_per_token": 5e-06, - "output_cost_per_token": 2.5e-05, "litellm_provider": "deepinfra", + "max_input_tokens": 1000000, + "max_tokens": 1000000, "mode": "chat", + "output_cost_per_token": 2.5e-05, + "prompt_cache_min_tokens": 2048, + "source": "https://deepinfra.com/pricing", + "supports_adaptive_thinking": true, "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, "supports_reasoning": true, - "supports_vision": true, - "source": "https://deepinfra.com/pricing" + "supports_response_schema": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true }, "deepinfra/Qwen/Qwen3.6-27B": { "max_tokens": 262144, diff --git a/tests/test_litellm/test_together_ai_model_metadata.py b/tests/test_litellm/test_together_ai_model_metadata.py index 5a0aadf4737..60e4b8ddb4d 100644 --- a/tests/test_litellm/test_together_ai_model_metadata.py +++ b/tests/test_litellm/test_together_ai_model_metadata.py @@ -31,16 +31,16 @@ SERVERLESS_CHAT_MODELS: Final = ( "together_ai/meta-models/Muse-Glimmer-30B", "together_ai/google/gemma-4-31B-it", "together_ai/pearl-ai/gemma-4-31b-it", - "together_ai/google/gemma-3n-E4B-it", "together_ai/arize-ai/qwen-2-1.5b-instruct", "together_ai/Prism-ML/Ternary-Bonsai-27B", - "together_ai/meta-llama/Llama-Guard-4-12B", "together_ai/openai/gpt-oss-120b", "together_ai/openai/gpt-oss-20b", "together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo", ) DEPRECATED_MODELS: Final = { + "together_ai/google/gemma-3n-E4B-it": "2026-08-25", + "together_ai/meta-llama/Llama-Guard-4-12B": "2026-08-25", "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": "2026-07-10", "together_ai/Qwen/Qwen3.5-397B-A17B": "2026-06-29", "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": "2026-06-04", From 4456a4407feb474439d344ee5116d7d82d8701ab Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 26 Aug 2026 19:20:14 +0000 Subject: [PATCH 7/7] fix(model_prices): azure gpt-5.6 cache writes, mistral missing models, together cache reads Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 272 ++++++++++++++++-- model_prices_and_context_window.json | 272 ++++++++++++++++-- tests/test_litellm/test_cost_calculator.py | 78 +++++ 3 files changed, 560 insertions(+), 62 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7515e7ad396..1526319ecf1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -6592,6 +6592,9 @@ "supports_web_search": true }, "azure/gpt-5.6": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -6642,6 +6645,9 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -6693,6 +6699,9 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_priority": 4e-07, @@ -6744,6 +6753,9 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_priority": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_priority": 4e-08, @@ -6795,12 +6807,15 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6808,7 +6823,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6842,13 +6857,16 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6856,7 +6874,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6890,13 +6908,16 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, - "cache_read_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, - "input_cost_per_token_priority": 5.5e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6904,7 +6925,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, - "output_cost_per_token_priority": 3.3e-05, + "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6938,13 +6959,16 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_priority": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, - "cache_read_input_token_cost_priority": 5.5e-08, + "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, - "input_cost_per_token_priority": 5.5e-07, + "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6952,7 +6976,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, - "output_cost_per_token_priority": 3.3e-06, + "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6986,12 +7010,15 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6999,7 +7026,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -7033,13 +7060,16 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7047,7 +7077,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -7081,13 +7111,16 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, - "cache_read_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, - "input_cost_per_token_priority": 5.5e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7095,7 +7128,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, - "output_cost_per_token_priority": 3.3e-05, + "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -7129,13 +7162,16 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_priority": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, - "cache_read_input_token_cost_priority": 5.5e-08, + "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, - "input_cost_per_token_priority": 5.5e-07, + "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7143,7 +7179,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, - "output_cost_per_token_priority": 3.3e-06, + "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -30721,6 +30757,152 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/ministral-14b-2512": { + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-14b-latest": { + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3b-2512": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3b-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-embed-2312": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "source": "https://docs.mistral.ai/models/mistral-embed-23-12" + }, + "mistral/mistral-medium-3": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/voxtral-mini-transcribe-realtime-latest": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-tts-latest": { + "litellm_provider": "mistral", + "mode": "audio_speech", + "output_cost_per_character": 1.6e-05, + "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true + }, + "mistral/voxtral-small-2507": { + "input_cost_per_second": 6.666666666666667e-05, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/voxtral-small-latest": { + "input_cost_per_second": 6.666666666666667e-05, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/zai-glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -31191,9 +31373,9 @@ "mistral/ministral-3-3b-2512": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://mistral.ai/pricing", @@ -38342,6 +38524,7 @@ "supports_tool_choice": true }, "together_ai/Qwen/Qwen3.5-397B-A17B": { + "cache_read_input_token_cost": 3.5e-07, "deprecation_date": "2026-06-29", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", @@ -38351,10 +38534,12 @@ "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, @@ -38365,6 +38550,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -38408,6 +38594,7 @@ "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, @@ -38415,7 +38602,8 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3.75e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { "input_cost_per_token": 3.2e-07, @@ -38428,6 +38616,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { + "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, @@ -38435,7 +38624,8 @@ "max_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6.25e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { "input_cost_per_token": 1e-07, @@ -38448,6 +38638,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -38458,10 +38649,12 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "together_ai", "max_input_tokens": 512000, @@ -38472,11 +38665,13 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -38487,6 +38682,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -38538,6 +38734,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/meta-models/Muse-Glimmer-30B": { + "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -38545,9 +38742,11 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -38558,11 +38757,13 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -38573,12 +38774,14 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, @@ -38589,6 +38792,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true @@ -38604,6 +38808,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/thinkingmachines/Inkling": { + "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, @@ -38614,10 +38819,12 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, @@ -38625,9 +38832,11 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048575, @@ -38638,6 +38847,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7515e7ad396..1526319ecf1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -6592,6 +6592,9 @@ "supports_web_search": true }, "azure/gpt-5.6": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -6642,6 +6645,9 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-sol": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, + "cache_creation_input_token_cost_priority": 1.25e-05, "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, "cache_read_input_token_cost_priority": 1e-06, @@ -6693,6 +6699,9 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_priority": 5e-06, "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_272k_tokens": 4e-07, "cache_read_input_token_cost_priority": 4e-07, @@ -6744,6 +6753,9 @@ "supports_minimal_reasoning_effort": false }, "azure/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_priority": 5e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, "cache_read_input_token_cost_priority": 4e-08, @@ -6795,12 +6807,15 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6808,7 +6823,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6842,13 +6857,16 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-sol": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6856,7 +6874,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6890,13 +6908,16 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, - "cache_read_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, - "input_cost_per_token_priority": 5.5e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6904,7 +6925,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, - "output_cost_per_token_priority": 3.3e-05, + "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6938,13 +6959,16 @@ "supports_minimal_reasoning_effort": false }, "azure/us/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_priority": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, - "cache_read_input_token_cost_priority": 5.5e-08, + "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, - "input_cost_per_token_priority": 5.5e-07, + "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6952,7 +6976,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, - "output_cost_per_token_priority": 3.3e-06, + "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -6986,12 +7010,15 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -6999,7 +7026,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -7033,13 +7060,16 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-sol": { + "cache_creation_input_token_cost": 6.875e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, + "cache_creation_input_token_cost_priority": 1.375e-05, "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.375e-06, + "cache_read_input_token_cost_priority": 1.1e-06, "deprecation_date": "2028-01-11", "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_priority": 1.375e-05, + "input_cost_per_token_priority": 1.1e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7047,7 +7077,7 @@ "mode": "chat", "output_cost_per_token": 3.3e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_priority": 8.25e-05, + "output_cost_per_token_priority": 6.6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -7081,13 +7111,16 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-terra": { + "cache_creation_input_token_cost": 2.75e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06, + "cache_creation_input_token_cost_priority": 5.5e-06, "cache_read_input_token_cost": 2.2e-07, "cache_read_input_token_cost_above_272k_tokens": 4.4e-07, - "cache_read_input_token_cost_priority": 5.5e-07, + "cache_read_input_token_cost_priority": 4.4e-07, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-06, "input_cost_per_token_above_272k_tokens": 4.4e-06, - "input_cost_per_token_priority": 5.5e-06, + "input_cost_per_token_priority": 4.4e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7095,7 +7128,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-05, "output_cost_per_token_above_272k_tokens": 1.98e-05, - "output_cost_per_token_priority": 3.3e-05, + "output_cost_per_token_priority": 2.64e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -7129,13 +7162,16 @@ "supports_minimal_reasoning_effort": false }, "azure/eu/gpt-5.6-luna": { + "cache_creation_input_token_cost": 2.75e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07, + "cache_creation_input_token_cost_priority": 5.5e-07, "cache_read_input_token_cost": 2.2e-08, "cache_read_input_token_cost_above_272k_tokens": 4.4e-08, - "cache_read_input_token_cost_priority": 5.5e-08, + "cache_read_input_token_cost_priority": 4.4e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2.2e-07, "input_cost_per_token_above_272k_tokens": 4.4e-07, - "input_cost_per_token_priority": 5.5e-07, + "input_cost_per_token_priority": 4.4e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7143,7 +7179,7 @@ "mode": "chat", "output_cost_per_token": 1.32e-06, "output_cost_per_token_above_272k_tokens": 1.98e-06, - "output_cost_per_token_priority": 3.3e-06, + "output_cost_per_token_priority": 2.64e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -30721,6 +30757,152 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/ministral-14b-2512": { + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-14b-latest": { + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://docs.mistral.ai/models/ministral-3-14b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3b-2512": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3b-latest": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://docs.mistral.ai/models/ministral-3-3b-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-embed-2312": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "source": "https://docs.mistral.ai/models/mistral-embed-23-12" + }, + "mistral/mistral-medium-3": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "source": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/voxtral-mini-transcribe-realtime-latest": { + "input_cost_per_second": 0.0001, + "litellm_provider": "mistral", + "mode": "audio_transcription", + "source": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", + "supported_endpoints": [ + "/v1/audio/transcriptions" + ], + "supported_modalities": [ + "audio" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true + }, + "mistral/voxtral-mini-tts-latest": { + "litellm_provider": "mistral", + "mode": "audio_speech", + "output_cost_per_character": 1.6e-05, + "source": "https://docs.mistral.ai/models/model-cards/voxtral-tts-26-03", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "audio" + ], + "supports_audio_output": true + }, + "mistral/voxtral-small-2507": { + "input_cost_per_second": 6.666666666666667e-05, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/voxtral-small-latest": { + "input_cost_per_second": 6.666666666666667e-05, + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-07, + "source": "https://docs.mistral.ai/models/voxtral-small-25-07", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/zai-glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -31191,9 +31373,9 @@ "mistral/ministral-3-3b-2512": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1e-07, "source": "https://mistral.ai/pricing", @@ -38342,6 +38524,7 @@ "supports_tool_choice": true }, "together_ai/Qwen/Qwen3.5-397B-A17B": { + "cache_read_input_token_cost": 3.5e-07, "deprecation_date": "2026-06-29", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", @@ -38351,10 +38534,12 @@ "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/MiniMaxAI/MiniMax-M3": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, @@ -38365,6 +38550,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -38408,6 +38594,7 @@ "supports_reasoning": true }, "together_ai/Qwen/Qwen3.7-Max": { + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.25e-06, "litellm_provider": "together_ai", "max_input_tokens": 1000000, @@ -38415,7 +38602,8 @@ "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 3.75e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/Qwen/Qwen3.7-Plus": { "input_cost_per_token": 3.2e-07, @@ -38428,6 +38616,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { + "cache_read_input_token_cost": 5e-07, "input_cost_per_token": 2.5e-06, "litellm_provider": "together_ai", "max_input_tokens": 1010000, @@ -38435,7 +38624,8 @@ "max_tokens": 1010000, "mode": "chat", "output_cost_per_token": 6.25e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/arize-ai/qwen-2-1.5b-instruct": { "input_cost_per_token": 1e-07, @@ -38448,6 +38638,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -38458,10 +38649,12 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 1.74e-06, "litellm_provider": "together_ai", "max_input_tokens": 512000, @@ -38472,11 +38665,13 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { + "cache_read_input_token_cost": 1.3e-07, "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -38487,6 +38682,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, @@ -38538,6 +38734,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/meta-models/Muse-Glimmer-30B": { + "cache_read_input_token_cost": 4e-08, "input_cost_per_token": 3.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -38545,9 +38742,11 @@ "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.5e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/moonshotai/Kimi-K2.7-Code": { + "cache_read_input_token_cost": 1.9e-07, "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -38558,11 +38757,13 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/moonshotai/Kimi-K3": { + "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -38573,12 +38774,14 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true }, "together_ai/nvidia/nemotron-3-ultra-550b-a55b": { + "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 512288, @@ -38589,6 +38792,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true @@ -38604,6 +38808,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/thinkingmachines/Inkling": { + "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 524288, @@ -38614,10 +38819,12 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { + "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 524288, @@ -38625,9 +38832,11 @@ "max_tokens": 524288, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models" + "source": "https://docs.together.ai/docs/serverless-models", + "supports_prompt_caching": true }, "together_ai/zai-org/GLM-5.2": { + "cache_read_input_token_cost": 2.6e-07, "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048575, @@ -38638,6 +38847,7 @@ "source": "https://docs.together.ai/docs/serverless-models", "supports_function_calling": true, "supports_parallel_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index 3d0921c6fd8..578282efee5 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -1727,6 +1727,84 @@ def test_azure_ai_cache_cost_calculation(_local_model_cost_map): ), f"Output cost mismatch: got {output_cost}, expected {expected_output_cost}" +AZURE_GPT_5_6_MAP_KEYS = ( + "azure/gpt-5.6", + "azure/gpt-5.6-sol", + "azure/gpt-5.6-terra", + "azure/gpt-5.6-luna", + "azure/us/gpt-5.6", + "azure/us/gpt-5.6-sol", + "azure/us/gpt-5.6-terra", + "azure/us/gpt-5.6-luna", + "azure/eu/gpt-5.6", + "azure/eu/gpt-5.6-sol", + "azure/eu/gpt-5.6-terra", + "azure/eu/gpt-5.6-luna", +) + + +def test_azure_gpt_5_6_cache_write_tokens_are_billed(_local_model_cost_map): + """ + Azure bills gpt-5.6 prompt cache writes at 1.25x the input rate, but the + azure entries carried no ``cache_creation_input_token_cost``, so + cache-write tokens were billed at the plain input rate instead. + """ + from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token + from litellm.types.utils import PromptTokensDetailsWrapper, Usage + + usage = Usage( + completion_tokens=100, + prompt_tokens=2000, + total_tokens=2100, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=0, text_tokens=687), + cache_creation_input_tokens=1313, + ) + + input_cost, output_cost = generic_cost_per_token( + model="azure/gpt-5.6-luna", usage=usage, custom_llm_provider="azure" + ) + + assert input_cost == pytest.approx(687 * 2e-07 + 1313 * 2.5e-07) + assert output_cost == pytest.approx(100 * 1.2e-06) + + +@pytest.mark.parametrize("model", AZURE_GPT_5_6_MAP_KEYS) +def test_azure_gpt_5_6_rates_match_azure_price_page(_local_model_cost_map, model): + """ + Per the Azure retail price API (2026-08-26): cache writes cost 1.25x input + on every published gpt-5.6 meter, and Data Zone standard and priority + rates cost 1.1x Global (us/eu priority rates previously sat at 1.25x). + Azure publishes no long-context priority meters, so the + ``*_above_272k_tokens_priority`` suffix is excluded. + """ + entry = litellm.model_cost[model] + input_keys = [ + key + for key in entry + if key.startswith("input_cost_per_token") + and not key.endswith("_above_272k_tokens_priority") + ] + assert input_keys + for key in input_keys: + suffix = key[len("input_cost_per_token") :] + assert entry["cache_creation_input_token_cost" + suffix] == pytest.approx( + entry[key] * 1.25 + ), key + + zone = model.split("/")[1] + if zone in ("us", "eu"): + global_entry = litellm.model_cost["azure/" + model.split("/", 2)[2]] + prefixes = ("input_cost_per_token", "output_cost_per_token", "cache_read", "cache_creation") + token_cost_keys = [ + key + for key in entry + if key.startswith(prefixes) and not key.endswith("_above_272k_tokens_priority") + ] + assert len(token_cost_keys) >= 9 + for key in token_cost_keys: + assert entry[key] == pytest.approx(global_entry[key] * 1.1), key + + def test_vertex_regional_deployment_costs_uplift_over_global(monkeypatch): """ Regression for https://github.com/BerriAI/litellm/issues/34393: two Vertex