diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json index f937e4d2f75..cc7bb8bab43 100644 --- a/litellm/llms/openai_like/providers.json +++ b/litellm/llms/openai_like/providers.json @@ -314,5 +314,14 @@ "supports_function_calling": true, "supports_reasoning": true } + }, + "popnow": { + "base_url": "https://api.popnow.ai/v1", + "api_key_env": "POPNOW_API_KEY", + "api_base_env": "POPNOW_API_BASE", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ] } } diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d9d996208d8..1eb6f26cdcf 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -86608,5 +86608,256 @@ "supports_tool_choice": true, "supports_vision": true, "token_count_framing": 100.0 + }, + "popnow/anthropic/claude-sonnet-5.5/chat": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "popnow/anthropic/claude-opus-5.5/chat": { + "cache_creation_input_token_cost": 4.5e-06, + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 3.6e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ] + }, + "popnow/openai/gpt-6.1-sol/chat": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "popnow", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "popnow/openai/gpt-6.1-terra/chat": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "popnow", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "popnow/google/gemini-3.7-flash/chat": { + "cache_read_input_token_cost": 6.75e-08, + "input_cost_per_token": 6.75e-07, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.375e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high" + ] + }, + "popnow/google/gemini-4-argon/chat": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ] + }, + "popnow/deepseek/v4-pro/chat": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "none", + "low", + "high" + ] + }, + "popnow/deepseek/v4-flash/chat": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "none", + "low", + "high" + ] + }, + "popnow/deepseek/v4.1-flash/chat": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "low", + "high" + ] + }, + "popnow/moonshot/kimi-k3.1-pro/chat": { + "cache_creation_input_token_cost": 2e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "popnow/moonshot/kimi-k3/chat": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 2.7e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1000000, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.35e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] } } diff --git a/litellm/provider_endpoints_support_backup.json b/litellm/provider_endpoints_support_backup.json index 00fee0a0d5a..9862b1fd975 100644 --- a/litellm/provider_endpoints_support_backup.json +++ b/litellm/provider_endpoints_support_backup.json @@ -33,6 +33,22 @@ } }, "providers": { + "popnow": { + "display_name": "PopNow (`popnow`)", + "url": "https://docs.litellm.ai/docs/providers/popnow", + "endpoints": { + "chat_completions": true, + "messages": false, + "responses": true, + "embeddings": false, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "refuseless": { "display_name": "Refuseless (`refuseless`)", "url": "https://docs.litellm.ai/docs/providers/refuseless", diff --git a/litellm/proxy/public_endpoints/provider_create_fields.json b/litellm/proxy/public_endpoints/provider_create_fields.json index 5afc3908820..3649eb111c4 100644 --- a/litellm/proxy/public_endpoints/provider_create_fields.json +++ b/litellm/proxy/public_endpoints/provider_create_fields.json @@ -3455,6 +3455,33 @@ ], "default_model_placeholder": "gpt-3.5-turbo" }, + { + "provider": "POPNOW", + "provider_display_name": "PopNow", + "credential_fields": [ + { + "key": "api_key", + "label": "API Key", + "placeholder": null, + "tooltip": null, + "required": true, + "field_type": "password", + "options": null, + "default_value": null + }, + { + "key": "api_base", + "label": "API Base", + "placeholder": "https://api.popnow.ai/v1", + "tooltip": "Optional. Leave blank to use the provider's default endpoint.", + "required": false, + "field_type": "text", + "options": null, + "default_value": null + } + ], + "default_model_placeholder": "popnow/google/gemini-3.7-flash/chat" + }, { "provider": "REFUSELESS", "provider_display_name": "Refuseless", diff --git a/litellm/types/utils.py b/litellm/types/utils.py index b082198d3f2..186658ec4a9 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -4606,6 +4606,7 @@ GenericBudgetConfigType = dict[str, BudgetConfig] class LlmProviders(str, Enum): + POPNOW = "popnow" REFUSELESS = "refuseless" OPENAI = "openai" CHATGPT = "chatgpt" diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d9d996208d8..1eb6f26cdcf 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -86608,5 +86608,256 @@ "supports_tool_choice": true, "supports_vision": true, "token_count_framing": 100.0 + }, + "popnow/anthropic/claude-sonnet-5.5/chat": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "popnow/anthropic/claude-opus-5.5/chat": { + "cache_creation_input_token_cost": 4.5e-06, + "cache_read_input_token_cost": 1.8e-07, + "input_cost_per_token": 3.6e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.8e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": false, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ] + }, + "popnow/openai/gpt-6.1-sol/chat": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "popnow", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "popnow/openai/gpt-6.1-terra/chat": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-06, + "litellm_provider": "popnow", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "output_cost_per_token_above_272k_tokens": 7.5e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "low", + "medium", + "high", + "xhigh", + "max" + ] + }, + "popnow/google/gemini-3.7-flash/chat": { + "cache_read_input_token_cost": 6.75e-08, + "input_cost_per_token": 6.75e-07, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3.375e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "minimal", + "low", + "medium", + "high" + ] + }, + "popnow/google/gemini-4-argon/chat": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 2e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "medium", + "high" + ] + }, + "popnow/deepseek/v4-pro/chat": { + "cache_read_input_token_cost": 4.4e-08, + "input_cost_per_token": 1.32e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "none", + "low", + "high" + ] + }, + "popnow/deepseek/v4-flash/chat": { + "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 4.4e-07, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.32e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "reasoning_effort_levels": [ + "none", + "low", + "high" + ] + }, + "popnow/deepseek/v4.1-flash/chat": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 384000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "none", + "low", + "high" + ] + }, + "popnow/moonshot/kimi-k3.1-pro/chat": { + "cache_creation_input_token_cost": 2e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 2e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] + }, + "popnow/moonshot/kimi-k3/chat": { + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 2.7e-06, + "litellm_provider": "popnow", + "max_input_tokens": 1000000, + "max_output_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.35e-05, + "source": "https://popnow.ai/docs/chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "reasoning_effort_levels": [ + "low", + "high", + "max" + ] } } diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json index 00fee0a0d5a..9862b1fd975 100644 --- a/provider_endpoints_support.json +++ b/provider_endpoints_support.json @@ -33,6 +33,22 @@ } }, "providers": { + "popnow": { + "display_name": "PopNow (`popnow`)", + "url": "https://docs.litellm.ai/docs/providers/popnow", + "endpoints": { + "chat_completions": true, + "messages": false, + "responses": true, + "embeddings": false, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "refuseless": { "display_name": "Refuseless (`refuseless`)", "url": "https://docs.litellm.ai/docs/providers/refuseless", diff --git a/tests/unit/llms/openai_like/test_popnow_provider.py b/tests/unit/llms/openai_like/test_popnow_provider.py new file mode 100644 index 00000000000..f4edce79ce0 --- /dev/null +++ b/tests/unit/llms/openai_like/test_popnow_provider.py @@ -0,0 +1,124 @@ +import json +from typing import Final + +import pytest +import respx + +import litellm +from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider +from litellm.utils import trim_messages + +MODEL: Final = "popnow/google/gemini-3.7-flash/chat" +UPSTREAM_MODEL: Final = "google/gemini-3.7-flash/chat" + + +def test_popnow_resolves_environment_and_explicit_credentials(monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.setenv("POPNOW_API_KEY", "fake-environment-key") + monkeypatch.delenv("POPNOW_API_BASE", raising=False) + assert get_llm_provider(model=MODEL) == ( + UPSTREAM_MODEL, + "popnow", + "fake-environment-key", + "https://api.popnow.ai/v1", + ) + assert get_llm_provider(model=MODEL, api_key="fake-explicit-key", api_base="https://gateway.example/v1") == ( + UPSTREAM_MODEL, + "popnow", + "fake-explicit-key", + "https://gateway.example/v1", + ) + + +def test_popnow_api_base_environment_override(monkeypatch: pytest.MonkeyPatch) -> None: + monkeypatch.setenv("POPNOW_API_KEY", "fake-environment-key") + monkeypatch.setenv("POPNOW_API_BASE", "https://proxy.example/v1") + assert get_llm_provider(model=MODEL)[3] == "https://proxy.example/v1" + + +def test_popnow_chat_keeps_nested_model_id_and_accounts_for_cache(local_model_cost_map: None) -> None: + with respx.mock() as upstream: + route: Final = upstream.post("https://api.popnow.ai/v1/chat/completions").respond( + 200, + json={ + "id": "chatcmpl-test", + "object": "chat.completion", + "created": 1, + "model": UPSTREAM_MODEL, + "choices": [ + {"index": 0, "message": {"role": "assistant", "content": "hello"}, "finish_reason": "stop"} + ], + "usage": { + "prompt_tokens": 100, + "completion_tokens": 5, + "total_tokens": 105, + "prompt_tokens_details": {"cached_tokens": 80}, + }, + }, + ) + response: Final = litellm.completion( + model=MODEL, + api_key="fake-test-key", + messages=[{"role": "user", "content": "Say hello"}], + reasoning_effort="low", + ) + request: Final = route.calls.last.request + body: Final = json.loads(request.content) + assert request.headers["authorization"] == "Bearer fake-test-key" + assert body["model"] == UPSTREAM_MODEL + assert body["reasoning_effort"] == "low" + assert response.choices[0].message.content == "hello" + rates: Final = litellm.model_cost[MODEL] + expected: Final = ( + 20 * rates["input_cost_per_token"] + + 80 * rates["cache_read_input_token_cost"] + + 5 * rates["output_cost_per_token"] + ) + assert litellm.completion_cost(completion_response=response) == pytest.approx(expected) + + +def test_popnow_uses_native_responses_endpoint() -> None: + with respx.mock() as upstream: + route: Final = upstream.post("https://api.popnow.ai/v1/responses").respond( + 200, + json={ + "id": "resp-test", + "object": "response", + "created_at": 1, + "model": UPSTREAM_MODEL, + "status": "completed", + "output": [ + { + "id": "msg-test", + "type": "message", + "role": "assistant", + "status": "completed", + "content": [{"type": "output_text", "text": "hello", "annotations": []}], + } + ], + "usage": {"input_tokens": 4, "output_tokens": 3, "total_tokens": 7}, + }, + ) + response: Final = litellm.responses( + model=MODEL, + api_key="fake-test-key", + input="Say hello", + store=False, + ) + assert route.calls.last.request.headers["authorization"] == "Bearer fake-test-key" + assert json.loads(route.calls.last.request.content)["model"] == UPSTREAM_MODEL + assert response.output[0].content[0].text == "hello" + + +def test_popnow_models_trim_to_their_input_budget(local_model_cost_map: None) -> None: + model_names: Final = tuple(model for model in litellm.model_cost if model.startswith("popnow/")) + assert model_names + messages: Final = [{"role": "user", "content": "hello " * 500}] + budget: Final = 100 + for model in model_names: + trimmed: Final = trim_messages( + messages, + model=model, + trim_ratio=budget / litellm.model_cost[model]["max_input_tokens"], + ) + assert litellm.token_counter(model=model, messages=messages) > budget + assert litellm.token_counter(model=model, messages=trimmed) <= budget