diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index f875936b0bf..ad4e8228742 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -68897,6 +68897,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68906,6 +68907,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/QwQ-32B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -68915,6 +68917,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68924,6 +68927,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68933,6 +68937,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "deprecation_date": "2026-02-06", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -68942,6 +68947,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, @@ -68951,6 +68957,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68960,6 +68967,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "deprecation_date": "2026-06-04", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68969,6 +68977,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { + "deprecation_date": "2026-05-14", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68978,6 +68987,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68987,6 +68997,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68996,6 +69007,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69005,6 +69017,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { + "deprecation_date": "2026-04-16", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69015,6 +69028,7 @@ }, "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", "max_input_tokens": 262144, @@ -69024,6 +69038,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69033,6 +69048,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69042,6 +69058,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69051,6 +69068,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-05-14", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69060,6 +69078,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, @@ -69069,6 +69088,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69088,6 +69108,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69097,6 +69118,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2026-02-06", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -69106,6 +69128,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69115,6 +69138,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69124,6 +69148,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69133,6 +69158,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "deprecation_date": "2026-03-06", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69142,6 +69168,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69151,6 +69178,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69160,6 +69188,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "deprecation_date": "2026-04-16", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69170,6 +69199,7 @@ }, "together_ai/moonshotai/Kimi-K2.6": { "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-19", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69180,6 +69210,7 @@ }, "together_ai/moonshotai/Kimi-K2.7-Code": { "cache_read_input_token_cost": 1.9e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69189,6 +69220,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69218,6 +69250,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-4.5-Air-FP8": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69227,6 +69260,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-4.7": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 4.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, @@ -69236,6 +69270,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5": { + "deprecation_date": "2026-06-22", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, @@ -69246,6 +69281,7 @@ }, "together_ai/zai-org/GLM-5.1": { "cache_read_input_token_cost": 2.6e-07, + "deprecation_date": "2026-07-10", "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f875936b0bf..ad4e8228742 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -68897,6 +68897,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68906,6 +68907,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/QwQ-32B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -68915,6 +68917,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68924,6 +68927,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68933,6 +68937,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo": { + "deprecation_date": "2026-02-06", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -68942,6 +68947,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, @@ -68951,6 +68957,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -68960,6 +68967,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "deprecation_date": "2026-06-04", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68969,6 +68977,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Coder-Next-FP8": { + "deprecation_date": "2026-05-14", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68978,6 +68987,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68987,6 +68997,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 1.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -68996,6 +69007,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-32B-Instruct": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69005,6 +69017,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3-VL-8B-Instruct": { + "deprecation_date": "2026-04-16", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69015,6 +69028,7 @@ }, "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", "max_input_tokens": 262144, @@ -69024,6 +69038,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69033,6 +69048,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69042,6 +69058,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69051,6 +69068,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-V3.1": { + "deprecation_date": "2026-05-14", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69060,6 +69078,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 16384, @@ -69069,6 +69088,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69088,6 +69108,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69097,6 +69118,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2026-02-06", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -69106,6 +69128,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69115,6 +69138,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 8192, @@ -69124,6 +69148,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "deprecation_date": "2026-02-25", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69133,6 +69158,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "deprecation_date": "2026-03-06", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69142,6 +69168,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-7B-Instruct-v0.1": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69151,6 +69178,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 1e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69160,6 +69188,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "deprecation_date": "2026-04-16", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69170,6 +69199,7 @@ }, "together_ai/moonshotai/Kimi-K2.6": { "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-08-19", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69180,6 +69210,7 @@ }, "together_ai/moonshotai/Kimi-K2.7-Code": { "cache_read_input_token_cost": 1.9e-07, + "deprecation_date": "2026-08-27", "input_cost_per_token": 9.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -69189,6 +69220,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "max_input_tokens": 32768, @@ -69218,6 +69250,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-4.5-Air-FP8": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -69227,6 +69260,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-4.7": { + "deprecation_date": "2026-04-02", "input_cost_per_token": 4.5e-07, "litellm_provider": "together_ai", "max_input_tokens": 202752, @@ -69236,6 +69270,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/zai-org/GLM-5": { + "deprecation_date": "2026-06-22", "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752, @@ -69246,6 +69281,7 @@ }, "together_ai/zai-org/GLM-5.1": { "cache_read_input_token_cost": 2.6e-07, + "deprecation_date": "2026-07-10", "input_cost_per_token": 1.4e-06, "litellm_provider": "together_ai", "max_input_tokens": 202752,