diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 8a03000539..a1de7faa69 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -15080,95 +15080,1037 @@ "litellm_provider": "ollama", "mode": "completion" }, - "deepinfra/lizpreciatior/lzlv_70b_fp16_hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 9e-07, + { + "deepinfra/deepseek-ai/DeepSeek-V3": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, + "deepinfra/Phind/Phind-CodeLlama-34B-v2": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.5e-08, + "output_cost_per_token": 2e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/gemma-2-9b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2-7B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/QVQ-72B-Preview": { + "max_tokens": 32000, + "max_input_tokens": 32000, + "max_output_tokens": 32000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/microsoft/Phi-4-multimodal-instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/mistralai/Devstral-Small-2507": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/microsoft/WizardLM-2-7B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-3.2-90B-Vision-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 3.5e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 2.8e-07, + "output_cost_per_token": 8.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/anthropic/claude-3-7-sonnet-latest": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 3.3e-06, + "output_cost_per_token": 1.65e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/cognitivecomputations/dolphin-2.9.1-llama-3-70b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3.5e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen3-235B-A22B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3-0324-Turbo": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/microsoft/WizardLM-2-8x22B": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 4.8e-07, + "output_cost_per_token": 4.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-Guard-4-12B": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 1.8e-07, + "output_cost_per_token": 1.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, "deepinfra/Gryphe/MythoMax-L2-13b": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 2.2e-07, + "input_cost_per_token": 7.2e-08, + "output_cost_per_token": 7.2e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, - "deepinfra/mistralai/Mistral-7B-Instruct-v0.1": { - "max_tokens": 8191, + "deepinfra/meta-llama/Llama-3.2-1B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-09, + "output_cost_per_token": 1e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/gemma-2-27b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 2.7e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mixtral-8x22B-Instruct-v0.1": { + "max_tokens": 65536, + "max_input_tokens": 65536, + "max_output_tokens": 65536, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 6.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-7B-Instruct": { + "max_tokens": 32768, "max_input_tokens": 32768, - "max_output_tokens": 8191, + "max_output_tokens": 32768, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/google/gemini-1.5-flash-8b": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 3.75e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-Guard-3-8B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 8e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/lizpreciatior/lzlv_70b_fp16_hf": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 3.5e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-2-13b-chat-hf": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 1.3e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, + "deepinfra/anthropic/claude-4-opus": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 1.65e-05, + "output_cost_per_token": 8.25e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/openchat/openchat-3.6-8b": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/google/gemma-3-27b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 1.7e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Austism/chronos-hermes-13b-v2": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Sao10K/L3.1-70B-Euryale-v2.2": { + "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, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/QwQ-32B-Preview": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 1.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/anthropic/claude-4-sonnet": { + "max_tokens": 200000, + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "input_cost_per_token": 3.3e-06, + "output_cost_per_token": 1.65e-05, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/microsoft/Phi-3-medium-4k-instruct": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/mattshumer/Reflection-Llama-3.1-70B": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3.5e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/openchat/openchat_3.5": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Sao10K/L3.3-70B-Euryale-v2.3": { + "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, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-V3.1": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 1.15e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen2.5-Coder-7B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2.5e-08, + "output_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2.4e-07, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-Prover-V2-671B": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.18e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/zai-org/GLM-4.5": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5.5e-07, + "output_cost_per_token": 2e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-3.2-3B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.2e-08, + "output_cost_per_token": 2.4e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3-70B-Instruct": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/gemini-1.5-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/KoboldAI/LLaMA2-13B-Tiefighter": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-pro": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 8.75e-07, + "output_cost_per_token": 7e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-30B-A3B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.9e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/QwQ-32B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/moonshotai/Kimi-K2-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Sao10K/L3-70B-Euryale-v2.1": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/microsoft/phi-4-reasoning-plus": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 3.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/google/gemma-3-12b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.5-flash": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 2.1e-07, + "output_cost_per_token": 1.75e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 2.15e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-7B-Instruct-v0.3": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 2.8e-08, + "output_cost_per_token": 5.4e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2.5-72B-Instruct": { + "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, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-14B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/allenai/olmOCR-7B-0725-FP8": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 2.7e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 4e-07, + "output_cost_per_token": 1.6e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/microsoft/phi-4": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 16384, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 1.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 7e-07, + "output_cost_per_token": 8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/zai-org/GLM-4.5-Air": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.1e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/openai/gpt-oss-120b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 4.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/codegemma-7b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 7e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 4e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/openbmb/MiniCPM-Llama3-V-2_5": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3.4e-07, + "output_cost_per_token": 3.4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/bigcode/starcoder2-15b-instruct-v0.1": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 1.5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "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, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "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, + "output_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/google/gemini-2.0-flash-001": { + "max_tokens": 1000000, + "max_input_tokens": 1000000, + "max_output_tokens": 1000000, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Gryphe/MythoMax-L2-13b-turbo": { + "max_tokens": 4096, + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 1.3e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/google/gemma-1.1-7b-it": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 7e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 2.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-32B": { + "max_tokens": 40960, + "max_input_tokens": 40960, + "max_output_tokens": 40960, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, "deepinfra/meta-llama/Llama-2-70b-chat-hf": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 9e-07, + "input_cost_per_token": 6.4e-07, + "output_cost_per_token": 8e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, - "deepinfra/cognitivecomputations/dolphin-2.6-mixtral-8x7b": { - "max_tokens": 8191, - "max_input_tokens": 32768, - "max_output_tokens": 8191, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 2.7e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/codellama/CodeLlama-34b-Instruct-hf": { + "deepinfra/nvidia/Nemotron-4-340B-Instruct": { "max_tokens": 4096, "max_input_tokens": 4096, "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 4.2e-06, + "output_cost_per_token": 4.2e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, - "deepinfra/deepinfra/mixtral": { - "max_tokens": 4096, - "max_input_tokens": 32000, - "max_output_tokens": 4096, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 2.7e-07, - "litellm_provider": "deepinfra", - "mode": "completion" - }, - "deepinfra/Phind/Phind-CodeLlama-34B-v2": { - "max_tokens": 4096, - "max_input_tokens": 16384, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, + "deepinfra/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.15e-06, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, - "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { - "max_tokens": 8191, + "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/NovaSky-AI/Sky-T1-32B-Preview": { + "max_tokens": 32768, "max_input_tokens": 32768, - "max_output_tokens": 8191, - "input_cost_per_token": 2.7e-07, - "output_cost_per_token": 2.7e-07, + "max_output_tokens": 32768, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 1.8e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, + "deepinfra/mistralai/Mistral-Small-3.1-24B-Instruct-2503": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-08, + "output_cost_per_token": 1e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/mistralai/Mistral-7B-Instruct-v0.1": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/Qwen/Qwen2-72B-Instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 3.5e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": true + }, + "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/Sao10K/L3-8B-Lunaris-v1": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, "deepinfra/deepinfra/airoboros-70b": { "max_tokens": 4096, "max_input_tokens": 4096, @@ -15179,112 +16121,72 @@ "mode": "chat", "supports_tool_choice": true }, - "deepinfra/01-ai/Yi-34B-Chat": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/01-ai/Yi-6B-200K": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, - "litellm_provider": "deepinfra", - "mode": "completion" - }, - "deepinfra/jondurbin/airoboros-l2-70b-gpt4-1.4.1": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 7e-07, - "output_cost_per_token": 9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-2-13b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 2.2e-07, - "output_cost_per_token": 2.2e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/amazon/MistralLite": { - "max_tokens": 8191, - "max_input_tokens": 32768, - "max_output_tokens": 8191, - "input_cost_per_token": 2e-07, - "output_cost_per_token": 2e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Llama-2-7b-chat-hf": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, + "deepinfra/google/gemma-3-4b-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, "deepinfra/meta-llama/Meta-Llama-3-8B-Instruct": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 4096, - "input_cost_per_token": 8e-08, - "output_cost_per_token": 8e-08, + "max_tokens": 8192, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "input_cost_per_token": 3e-08, + "output_cost_per_token": 6e-08, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true }, - "deepinfra/meta-llama/Meta-Llama-3-70B-Instruct": { - "max_tokens": 8191, - "max_input_tokens": 8191, - "max_output_tokens": 4096, - "input_cost_per_token": 5.9e-07, - "output_cost_per_token": 7.9e-07, - "litellm_provider": "deepinfra", - "mode": "chat", - "supports_tool_choice": true - }, - "deepinfra/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "deepinfra/mistralai/Mistral-7B-Instruct-v0.2": { "max_tokens": 32768, "max_input_tokens": 32768, "max_output_tokens": 32768, - "input_cost_per_token": 9e-07, - "output_cost_per_token": 9e-07, + "input_cost_per_token": 5.5e-08, + "output_cost_per_token": 5.5e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-08, + "output_cost_per_token": 1.2e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_function_calling": true, - "supports_parallel_function_calling": true, "supports_tool_choice": true }, - "deepinfra/01-ai/Yi-34B-200K": { - "max_tokens": 4096, - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "input_cost_per_token": 6e-07, - "output_cost_per_token": 6e-07, + "deepinfra/mistralai/Devstral-Small-2505": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, "litellm_provider": "deepinfra", - "mode": "completion" + "mode": "chat", + "supports_tool_choice": true }, - "deepinfra/openchat/openchat_3.5": { - "max_tokens": 4096, - "max_input_tokens": 4096, - "max_output_tokens": 4096, - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 1.3e-07, + "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 4.9e-08, + "output_cost_per_token": 4.9e-08, + "litellm_provider": "deepinfra", + "mode": "chat", + "supports_tool_choice": false + }, + "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": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true