1 line
85 KiB
JSON
1 line
85 KiB
JSON
{"repo": "agent-stronghold/stronghold", "files": {"deploy/helm/stronghold/files/litellm-proxy-config.yaml": {"184631b0ed32b47b761d4a575e5819c9322f1164": {"t": 1785596050.1355042, "n": 41827, "h": "cbb4a82c912dc0a0", "c": "model_list:\n- model_name: mistral-large\n litellm_params:\n model: mistral/mistral-large-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 400.0\n budget_duration: 30d\n rpm: 60\n tpm: 500000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-codestral\n litellm_params:\n model: mistral/codestral-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-devstral\n litellm_params:\n model: mistral/devstral-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 200.0\n budget_duration: 30d\n rpm: 60\n tpm: 500000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-small\n litellm_params:\n model: mistral/mistral-small-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 100.0\n budget_duration: 30d\n rpm: 60\n tpm: 500000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-llama8b\n litellm_params:\n model: cerebras/llama3.1-8b\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 1.0\n budget_duration: 1d\n rpm: 30\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemini-flash\n litellm_params:\n model: gemini/gemini-2.5-flash\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemini-3-flash\n litellm_params:\n model: gemini/gemini-3-flash-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemini-flash-lite\n litellm_params:\n model: gemini/gemini-2.5-flash-lite\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 10\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemma-27b\n litellm_params:\n model: gemini/gemma-3-27b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 28.8\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemma-12b\n litellm_params:\n model: gemini/gemma-3-12b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 28.8\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemma-4b\n litellm_params:\n model: gemini/gemma-3-4b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 28.8\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: imagen-4\n litellm_params:\n model: gemini/imagen-4-generate\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n model_info:\n input_cost_per_token: 0.01\n output_cost_per_token: 0.0\n- model_name: imagen-4-fast\n litellm_params:\n model: gemini/imagen-4-fast-generate\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n model_info:\n input_cost_per_token: 0.01\n output_cost_per_token: 0.0\n- model_name: imagen-4-ultra\n litellm_params:\n model: gemini/imagen-4-ultra-generate\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n model_info:\n input_cost_per_token: 0.01\n output_cost_per_token: 0.0\n- model_name: gemini-embedding\n litellm_params:\n model: gemini/gemini-embedding-1\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.1\n budget_duration: 1d\n rpm: 100\n tpm: 30000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-3.1-pro\n litellm_params:\n model: openrouter/google/gemini-3.1-pro-preview\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-anthropic/claude-opus-4.6\n litellm_params:\n model: openrouter/anthropic/claude-opus-4.6\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-upstage/solar-pro-3:free\n litellm_params:\n model: openrouter/upstage/solar-pro-3:free\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-openai/gpt-5.2-pro\n litellm_params:\n model: openrouter/openai/gpt-5.2-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-anthropic/claude-opus-4.5\n litellm_params:\n model: openrouter/anthropic/claude-opus-4.5\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-3-pro-image\n litellm_params:\n model: openrouter/google/gemini-3-pro-image-preview\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-3-pro\n litellm_params:\n model: openrouter/google/gemini-3-pro-preview\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-kwaipilot/kat-coder-pro\n litellm_params:\n model: openrouter/kwaipilot/kat-coder-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-perplexity/sonar-pro-search\n litellm_params:\n model: openrouter/perplexity/sonar-pro-search\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-openai/gpt-5-pro\n litellm_params:\n model: openrouter/openai/gpt-5-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-nousresearch/hermes-4-405b\n litellm_params:\n model: openrouter/nousresearch/hermes-4-405b\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-anthropic/claude-opus-4.1\n litellm_params:\n model: openrouter/anthropic/claude-opus-4.1\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-2.5-pro\n litellm_params:\n model: openrouter/google/gemini-2.5-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-openai/o3-pro\n litellm_params:\n model: openrouter/openai/o3-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-a-vision-07-2025\n litellm_params:\n model: cohere/command-a-vision-07-2025\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.1875\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-vision-8b\n litellm_params:\n model: cohere/c4ai-aya-vision-8b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-a-reasoning-08-2025\n litellm_params:\n model: cohere/command-a-reasoning-08-2025\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.1875\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-expanse-8b\n litellm_params:\n model: cohere/c4ai-aya-expanse-8b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-r-08-2024\n litellm_params:\n model: cohere/command-r-08-2024\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.125\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-r7b-arabic-02-2025\n litellm_params:\n model: cohere/command-r7b-arabic-02-2025\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-expanse-32b\n litellm_params:\n model: cohere/c4ai-aya-expanse-32b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.125\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-r7b-12-2024\n litellm_params:\n model: cohere/command-r7b-12-2024\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-vision-32b\n litellm_params:\n model: cohere/c4ai-aya-vision-32b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.125\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@hf/nousresearch/hermes-2-pro-mistral-7b\n litellm_params:\n model: cloudflare/@hf/nousresearch/hermes-2-pro-mistral-7b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 1.290322\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/meta/llama33-70b-fp8-fast\n litellm_params:\n model: cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.967741\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/deepseek-ai/deepseek-r1-distill-qwen-32b\n litellm_params:\n model: cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/qwen/qwen2.5-coder-32b\n litellm_params:\n model: cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/aisingapore/gemma-sea-lion-v4-27b\n litellm_params:\n model: cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/qwen/qwq-32b\n litellm_params:\n model: cloudflare/@cf/qwen/qwq-32b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/openai/gpt-oss-120b\n litellm_params:\n model: cloudflare/@cf/openai/gpt-oss-120b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/qwen/qwen1.5-0.5b\n litellm_params:\n model: cloudflare/@cf/qwen/qwen1.5-0.5b-chat\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/zai-org/glm-4.7-flash\n litellm_params:\n model: cloudflare/@cf/zai-org/glm-4.7-flash\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/ibm-granite/granite-4.0-h-micro\n litellm_params:\n model: cloudflare/@cf/ibm-granite/granite-4.0-h-micro\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/microsoft/phi-2\n litellm_params:\n model: cloudflare/@cf/microsoft/phi-2\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/openai/gpt-oss-20b\n litellm_params:\n model: cloudflare/@cf/openai/gpt-oss-20b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/openchat/openchat-3.5-0106\n litellm_params:\n model: cloudflare/@cf/openchat/openchat-3.5-0106\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/meta/llama-3-8b\n litellm_params:\n model: cloudflare/@cf/meta/llama-3-8b-instruct\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.32258\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/meta/llama31-8b-fp8\n litellm_params:\n model: cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.32258\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-gpt-oss-120b\n litellm_params:\n model: cerebras/gpt-oss-120b\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-zai-glm-4.7\n litellm_params:\n model: cerebras/zai-glm-4.7\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-qwen-3-235b-a22b-2507\n litellm_params:\n model: cerebras/qwen-3-235b-a22b-instruct-2507\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.166666\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-llama3.1-8b\n litellm_params:\n model: cerebras/llama3.1-8b\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.166666\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large-2411\n litellm_params:\n model: mistral/mistral-large-2411\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-pixtral-large-2411\n litellm_params:\n model: mistral/pixtral-large-2411\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-pixtral-large\n litellm_params:\n model: mistral/pixtral-large-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large-pixtral-2411\n litellm_params:\n model: mistral/mistral-large-pixtral-2411\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-codestral-2508\n litellm_params:\n model: mistral/codestral-2508\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large-2512\n litellm_params:\n model: mistral/mistral-large-2512\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large\n litellm_params:\n model: mistral/mistral-large-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-codestral-embed\n litellm_params:\n model: mistral/codestral-embed\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 0.09999999999999999\n budget_duration: 30d\n rpm: 100\n tpm: 30000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-medium-2505\n litellm_params:\n model: mistral/mistral-medium-2505\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-medium-2508\n litellm_params:\n model: mistral/mistral-medium-2508\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-medium\n litellm_params:\n model: mistral/mistral-medium-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-devstral-small-2507\n litellm_params:\n model: mistral/devstral-small-2507\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-devstral-medium-2507\n litellm_params:\n model: mistral/devstral-medium-2507\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-pro\n litellm_params:\n model: gemini/gemini-2.5-pro\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-pro\n litellm_params:\n model: gemini/gemini-pro-latest\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3-pro\n litellm_params:\n model: gemini/gemini-3-pro-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3.1-pro\n litellm_params:\n model: gemini/gemini-3.1-pro-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3.1-pro-customtools\n litellm_params:\n model: gemini/gemini-3.1-pro-preview-customtools\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3-pro-image\n litellm_params:\n model: gemini/gemini-3-pro-image-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-imagen-4.0-ultra-generate-001\n litellm_params:\n model: gemini/imagen-4.0-ultra-generate-001\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n rpm: 5\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash\n litellm_params:\n model: gemini/gemini-2.5-flash\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash-lite\n litellm_params:\n model: gemini/gemini-2.5-flash-lite\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 10\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash-image\n litellm_params:\n model: gemini/gemini-2.5-flash-image\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash-lite-09-2025\n litellm_params:\n model: gemini/gemini-2.5-flash-lite-preview-09-2025\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3-flash\n litellm_params:\n model: gemini/gemini-3-flash-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.0-flash-lite-001\n litellm_params:\n model: gemini/gemini-2.0-flash-lite-001\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.222222\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.0-flash-lite\n litellm_params:\n model: gemini/gemini-2.0-flash-lite\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.222222\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemma-3-27b\n litellm_params:\n model: gemini/gemma-3-27b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.222222\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-moonshotai/kimi-k2-0905\n litellm_params:\n model: groq/moonshotai/kimi-k2-instruct-0905\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-canopylabs/orpheus-v1-english\n litellm_params:\n model: groq/canopylabs/orpheus-v1-english\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-groq/compound\n litellm_params:\n model: groq/groq/compound\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-canopylabs/orpheus-arabic-saudi\n litellm_params:\n model: groq/canopylabs/orpheus-arabic-saudi\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-llama33-70b\n litellm_params:\n model: groq/llama-3.3-70b-versatile\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.065217\n budget_duration: 1d\n rpm: 30\n tpm: 131072\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-moonshotai/kimi-k2\n litellm_params:\n model: groq/moonshotai/kimi-k2-instruct\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-qwen/qwen3-32b\n litellm_params:\n model: groq/qwen/qwen3-32b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-groq/compound-mini\n litellm_params:\n model: groq/groq/compound-mini\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-llama31-8b-instant\n litellm_params:\n model: groq/llama-3.1-8b-instant\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 30\n tpm: 131072\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-openai/gpt-oss-20b\n litellm_params:\n model: groq/openai/gpt-oss-20b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-allam-2-7b\n litellm_params:\n model: groq/allam-2-7b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-openai/gpt-oss-120b\n litellm_params:\n model: groq/openai/gpt-oss-120b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-llama/llama-4-scout-17b-16e\n litellm_params:\n model: groq/meta-llama/llama-4-scout-17b-16e-instruct\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-r1-distill-llama-70b\n litellm_params:\n model: openai/DeepSeek-R1-Distill-Llama-70B\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 10.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-llama33-swallow-70b-v0.4\n litellm_params:\n model: openai/Llama-3.3-Swallow-70B-Instruct-v0.4\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 10.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-llama33-70b\n litellm_params:\n model: openai/Meta-Llama-3.3-70B-Instruct\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 10.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-qwen3-32b\n litellm_params:\n model: openai/Qwen3-32B\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-r1-0528\n litellm_params:\n model: openai/DeepSeek-R1-0528\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3-0324\n litellm_params:\n model: openai/DeepSeek-V3-0324\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.1\n litellm_params:\n model: openai/DeepSeek-V3.1\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.1-terminus\n litellm_params:\n model: openai/DeepSeek-V3.1-Terminus\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.1-cb\n litellm_params:\n model: openai/DeepSeek-V3.1-cb\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.2\n litellm_params:\n model: openai/DeepSeek-V3.2\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-qwen3-235b\n litellm_params:\n model: openai/Qwen3-235B\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-gpt-oss-120b\n litellm_params:\n model: openai/gpt-oss-120b\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-llama31-8b\n litellm_params:\n model: openai/Meta-Llama-3.1-8B-Instruct\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 3.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-minimax-m2.5\n litellm_params:\n model: openai/MiniMax-M2.5\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 3.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-e5-mistral-7b\n litellm_params:\n model: openai/E5-Mistral-7B-Instruct\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 3.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: deepseek-deepseek\n litellm_params:\n model: deepseek/deepseek-chat\n api_key: os.environ/DEEPSEEK_API_KEY\n max_budget: 25.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: deepseek-deepseek-reasoner\n litellm_params:\n model: deepseek/deepseek-reasoner\n api_key: os.environ/DEEPSEEK_API_KEY\n max_budget: 25.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-google/imagen-4.0-ultra\n litellm_params:\n model: together_ai/google/imagen-4.0-ultra\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 0.25\n budget_duration: 30d\n rpm: 5\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.1-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.1-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-qwen/qwen-image-2.0-pro\n litellm_params:\n model: together_ai/Qwen/Qwen-Image-2.0-Pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-bytedance/seedance-1.0-pro\n litellm_params:\n model: together_ai/ByteDance/Seedance-1.0-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-rundiffusion/juggernaut-pro-flux\n litellm_params:\n model: together_ai/RunDiffusion/Juggernaut-pro-flux\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.1.1-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.1.1-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.1-kontext-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.1-kontext-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-openai/sora-2-pro\n litellm_params:\n model: together_ai/openai/sora-2-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-kwaivgi/kling-1.6-pro\n litellm_params:\n model: together_ai/kwaivgI/kling-1.6-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-kwaivgi/kling-2.1-pro\n litellm_params:\n model: together_ai/kwaivgI/kling-2.1-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-google/gemini-3-pro-image\n litellm_params:\n model: together_ai/google/gemini-3-pro-image\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.2-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.2-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-llama/llama31-405b\n litellm_params:\n model: together_ai/meta-llama/Llama-3.1-405B-Instruct\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-llama/llama33-70b-turbo\n litellm_params:\n model: together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 2.727272\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n# ── Zhipu AI / Z.ai (GLM models) ──────────────────\n- model_name: zhipu-glm-4.7\n litellm_params:\n model: openai/glm-4.7\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-5\n litellm_params:\n model: openai/glm-5\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-5-turbo\n litellm_params:\n model: openai/glm-5-turbo\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-4.6\n litellm_params:\n model: openai/glm-4.6\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-4.5\n litellm_params:\n model: openai/glm-4.5\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-4.5-air\n litellm_params:\n model: openai/glm-4.5-air\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\nlitellm_settings:\n max_budget: 2000\n budget_duration: 30d\n drop_params: true\n routing_strategy: usage-based-routing-v2\n default_fallbacks:\n - mistral-small\n success_callback:\n - langfuse\n failure_callback:\n - langfuse\n request_timeout: 60\n num_retries: 2\n retry_after: 5\n cache: true\n cache_params:\n type: local\n ttl: 300\ngeneral_settings:\n master_key: os.environ/LITELLM_MASTER_KEY\n database_url: os.environ/LITELLM_DATABASE_URL\n enable_jwt_auth: false\n ui_access_mode: admin_only\nenvironment_variables:\n LANGFUSE_HOST: http://172.18.0.1:3100\n LANGFUSE_PUBLIC_KEY: pk-lf-conductor\n LANGFUSE_SECRET_KEY: sk-lf-conductor\n\n# MCP Servers — disabled until mcp-deployer sidecar is built.\n# Re-enable when mcpDeployerSidecar.enabled=true and the OpenAPI spec\n# is mounted into the container.\n# mcp_servers:\n# github:\n# url: \"https://api.github.com\"\n# spec_path: \"/app/github-openapi.json\"\n# auth_type: \"bearer_token\"\n# auth_value: \"placeholder\"\n# extra_headers:\n# - \"authorization\"\n# allowed_tools:\n# - \"create_issue\"\n# - \"get_file_contents\"\n# - \"create_or_update_file\"\n# - \"create_pull_request\"\n# - \"create_branch\"\n"}, "1a82c48e09618a1bdc992c711324db40d2eb941e": {"t": 1785767951.746249, "n": 41827, "h": "cbb4a82c912dc0a0", "c": "model_list:\n- model_name: mistral-large\n litellm_params:\n model: mistral/mistral-large-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 400.0\n budget_duration: 30d\n rpm: 60\n tpm: 500000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-codestral\n litellm_params:\n model: mistral/codestral-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-devstral\n litellm_params:\n model: mistral/devstral-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 200.0\n budget_duration: 30d\n rpm: 60\n tpm: 500000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-small\n litellm_params:\n model: mistral/mistral-small-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 100.0\n budget_duration: 30d\n rpm: 60\n tpm: 500000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-llama8b\n litellm_params:\n model: cerebras/llama3.1-8b\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 1.0\n budget_duration: 1d\n rpm: 30\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemini-flash\n litellm_params:\n model: gemini/gemini-2.5-flash\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemini-3-flash\n litellm_params:\n model: gemini/gemini-3-flash-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemini-flash-lite\n litellm_params:\n model: gemini/gemini-2.5-flash-lite\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 10\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemma-27b\n litellm_params:\n model: gemini/gemma-3-27b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 28.8\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemma-12b\n litellm_params:\n model: gemini/gemma-3-12b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 28.8\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: gemma-4b\n litellm_params:\n model: gemini/gemma-3-4b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 28.8\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: imagen-4\n litellm_params:\n model: gemini/imagen-4-generate\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n model_info:\n input_cost_per_token: 0.01\n output_cost_per_token: 0.0\n- model_name: imagen-4-fast\n litellm_params:\n model: gemini/imagen-4-fast-generate\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n model_info:\n input_cost_per_token: 0.01\n output_cost_per_token: 0.0\n- model_name: imagen-4-ultra\n litellm_params:\n model: gemini/imagen-4-ultra-generate\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n model_info:\n input_cost_per_token: 0.01\n output_cost_per_token: 0.0\n- model_name: gemini-embedding\n litellm_params:\n model: gemini/gemini-embedding-1\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.1\n budget_duration: 1d\n rpm: 100\n tpm: 30000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-3.1-pro\n litellm_params:\n model: openrouter/google/gemini-3.1-pro-preview\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-anthropic/claude-opus-4.6\n litellm_params:\n model: openrouter/anthropic/claude-opus-4.6\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-upstage/solar-pro-3:free\n litellm_params:\n model: openrouter/upstage/solar-pro-3:free\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-openai/gpt-5.2-pro\n litellm_params:\n model: openrouter/openai/gpt-5.2-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-anthropic/claude-opus-4.5\n litellm_params:\n model: openrouter/anthropic/claude-opus-4.5\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-3-pro-image\n litellm_params:\n model: openrouter/google/gemini-3-pro-image-preview\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-3-pro\n litellm_params:\n model: openrouter/google/gemini-3-pro-preview\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-kwaipilot/kat-coder-pro\n litellm_params:\n model: openrouter/kwaipilot/kat-coder-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-perplexity/sonar-pro-search\n litellm_params:\n model: openrouter/perplexity/sonar-pro-search\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-openai/gpt-5-pro\n litellm_params:\n model: openrouter/openai/gpt-5-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-nousresearch/hermes-4-405b\n litellm_params:\n model: openrouter/nousresearch/hermes-4-405b\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-anthropic/claude-opus-4.1\n litellm_params:\n model: openrouter/anthropic/claude-opus-4.1\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-google/gemini-2.5-pro\n litellm_params:\n model: openrouter/google/gemini-2.5-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: openrouter-openai/o3-pro\n litellm_params:\n model: openrouter/openai/o3-pro\n api_key: os.environ/OPENROUTER_API_KEY\n max_budget: 0.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-a-vision-07-2025\n litellm_params:\n model: cohere/command-a-vision-07-2025\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.1875\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-vision-8b\n litellm_params:\n model: cohere/c4ai-aya-vision-8b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-a-reasoning-08-2025\n litellm_params:\n model: cohere/command-a-reasoning-08-2025\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.1875\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-expanse-8b\n litellm_params:\n model: cohere/c4ai-aya-expanse-8b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-r-08-2024\n litellm_params:\n model: cohere/command-r-08-2024\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.125\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-r7b-arabic-02-2025\n litellm_params:\n model: cohere/command-r7b-arabic-02-2025\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-expanse-32b\n litellm_params:\n model: cohere/c4ai-aya-expanse-32b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.125\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-command-r7b-12-2024\n litellm_params:\n model: cohere/command-r7b-12-2024\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.0625\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cohere-c4ai-aya-vision-32b\n litellm_params:\n model: cohere/c4ai-aya-vision-32b\n api_key: os.environ/COHERE_API_KEY\n max_budget: 0.125\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@hf/nousresearch/hermes-2-pro-mistral-7b\n litellm_params:\n model: cloudflare/@hf/nousresearch/hermes-2-pro-mistral-7b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 1.290322\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/meta/llama33-70b-fp8-fast\n litellm_params:\n model: cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.967741\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/deepseek-ai/deepseek-r1-distill-qwen-32b\n litellm_params:\n model: cloudflare/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/qwen/qwen2.5-coder-32b\n litellm_params:\n model: cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/aisingapore/gemma-sea-lion-v4-27b\n litellm_params:\n model: cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/qwen/qwq-32b\n litellm_params:\n model: cloudflare/@cf/qwen/qwq-32b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/openai/gpt-oss-120b\n litellm_params:\n model: cloudflare/@cf/openai/gpt-oss-120b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/qwen/qwen1.5-0.5b\n litellm_params:\n model: cloudflare/@cf/qwen/qwen1.5-0.5b-chat\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/zai-org/glm-4.7-flash\n litellm_params:\n model: cloudflare/@cf/zai-org/glm-4.7-flash\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/ibm-granite/granite-4.0-h-micro\n litellm_params:\n model: cloudflare/@cf/ibm-granite/granite-4.0-h-micro\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/microsoft/phi-2\n litellm_params:\n model: cloudflare/@cf/microsoft/phi-2\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/openai/gpt-oss-20b\n litellm_params:\n model: cloudflare/@cf/openai/gpt-oss-20b\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/openchat/openchat-3.5-0106\n litellm_params:\n model: cloudflare/@cf/openchat/openchat-3.5-0106\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.645161\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/meta/llama-3-8b\n litellm_params:\n model: cloudflare/@cf/meta/llama-3-8b-instruct\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.32258\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cloudflare-@cf/meta/llama31-8b-fp8\n litellm_params:\n model: cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8\n api_key: os.environ/CLOUDFLARE_API_KEY\n max_budget: 0.32258\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-gpt-oss-120b\n litellm_params:\n model: cerebras/gpt-oss-120b\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-zai-glm-4.7\n litellm_params:\n model: cerebras/zai-glm-4.7\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-qwen-3-235b-a22b-2507\n litellm_params:\n model: cerebras/qwen-3-235b-a22b-instruct-2507\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.166666\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: cerebras-llama3.1-8b\n litellm_params:\n model: cerebras/llama3.1-8b\n api_key: os.environ/CEREBRAS_API_KEY\n max_budget: 0.166666\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large-2411\n litellm_params:\n model: mistral/mistral-large-2411\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-pixtral-large-2411\n litellm_params:\n model: mistral/pixtral-large-2411\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-pixtral-large\n litellm_params:\n model: mistral/pixtral-large-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large-pixtral-2411\n litellm_params:\n model: mistral/mistral-large-pixtral-2411\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-codestral-2508\n litellm_params:\n model: mistral/codestral-2508\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large-2512\n litellm_params:\n model: mistral/mistral-large-2512\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-large\n litellm_params:\n model: mistral/mistral-large-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 83.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-codestral-embed\n litellm_params:\n model: mistral/codestral-embed\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 0.09999999999999999\n budget_duration: 30d\n rpm: 100\n tpm: 30000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-medium-2505\n litellm_params:\n model: mistral/mistral-medium-2505\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-medium-2508\n litellm_params:\n model: mistral/mistral-medium-2508\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-mistral-medium\n litellm_params:\n model: mistral/mistral-medium-latest\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-devstral-small-2507\n litellm_params:\n model: mistral/devstral-small-2507\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: mistral-devstral-medium-2507\n litellm_params:\n model: mistral/devstral-medium-2507\n api_key: os.environ/MISTRAL_API_KEY\n max_budget: 55.555555\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-pro\n litellm_params:\n model: gemini/gemini-2.5-pro\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-pro\n litellm_params:\n model: gemini/gemini-pro-latest\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3-pro\n litellm_params:\n model: gemini/gemini-3-pro-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3.1-pro\n litellm_params:\n model: gemini/gemini-3.1-pro-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3.1-pro-customtools\n litellm_params:\n model: gemini/gemini-3.1-pro-preview-customtools\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3-pro-image\n litellm_params:\n model: gemini/gemini-3-pro-image-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.444444\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-imagen-4.0-ultra-generate-001\n litellm_params:\n model: gemini/imagen-4.0-ultra-generate-001\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.25\n budget_duration: 1d\n rpm: 5\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash\n litellm_params:\n model: gemini/gemini-2.5-flash\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash-lite\n litellm_params:\n model: gemini/gemini-2.5-flash-lite\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 10\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash-image\n litellm_params:\n model: gemini/gemini-2.5-flash-image\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.5-flash-lite-09-2025\n litellm_params:\n model: gemini/gemini-2.5-flash-lite-preview-09-2025\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.333333\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-3-flash\n litellm_params:\n model: gemini/gemini-3-flash-preview\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.04\n budget_duration: 1d\n rpm: 5\n tpm: 250000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.0-flash-lite-001\n litellm_params:\n model: gemini/gemini-2.0-flash-lite-001\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.222222\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemini-2.0-flash-lite\n litellm_params:\n model: gemini/gemini-2.0-flash-lite\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.222222\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: google-gemma-3-27b\n litellm_params:\n model: gemini/gemma-3-27b-it\n api_key: os.environ/GEMINI_API_KEY\n max_budget: 0.222222\n budget_duration: 1d\n rpm: 30\n tpm: 15000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-moonshotai/kimi-k2-0905\n litellm_params:\n model: groq/moonshotai/kimi-k2-instruct-0905\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-canopylabs/orpheus-v1-english\n litellm_params:\n model: groq/canopylabs/orpheus-v1-english\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-groq/compound\n litellm_params:\n model: groq/groq/compound\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-canopylabs/orpheus-arabic-saudi\n litellm_params:\n model: groq/canopylabs/orpheus-arabic-saudi\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-llama33-70b\n litellm_params:\n model: groq/llama-3.3-70b-versatile\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.065217\n budget_duration: 1d\n rpm: 30\n tpm: 131072\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-moonshotai/kimi-k2\n litellm_params:\n model: groq/moonshotai/kimi-k2-instruct\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-qwen/qwen3-32b\n litellm_params:\n model: groq/qwen/qwen3-32b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-groq/compound-mini\n litellm_params:\n model: groq/groq/compound-mini\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-llama31-8b-instant\n litellm_params:\n model: groq/llama-3.1-8b-instant\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 30\n tpm: 131072\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-openai/gpt-oss-20b\n litellm_params:\n model: groq/openai/gpt-oss-20b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-allam-2-7b\n litellm_params:\n model: groq/allam-2-7b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-openai/gpt-oss-120b\n litellm_params:\n model: groq/openai/gpt-oss-120b\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.043478\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: groq-llama/llama-4-scout-17b-16e\n litellm_params:\n model: groq/meta-llama/llama-4-scout-17b-16e-instruct\n api_key: os.environ/GROQ_API_KEY\n max_budget: 0.021739\n budget_duration: 1d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-r1-distill-llama-70b\n litellm_params:\n model: openai/DeepSeek-R1-Distill-Llama-70B\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 10.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-llama33-swallow-70b-v0.4\n litellm_params:\n model: openai/Llama-3.3-Swallow-70B-Instruct-v0.4\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 10.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-llama33-70b\n litellm_params:\n model: openai/Meta-Llama-3.3-70B-Instruct\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 10.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-qwen3-32b\n litellm_params:\n model: openai/Qwen3-32B\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-r1-0528\n litellm_params:\n model: openai/DeepSeek-R1-0528\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3-0324\n litellm_params:\n model: openai/DeepSeek-V3-0324\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.1\n litellm_params:\n model: openai/DeepSeek-V3.1\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.1-terminus\n litellm_params:\n model: openai/DeepSeek-V3.1-Terminus\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.1-cb\n litellm_params:\n model: openai/DeepSeek-V3.1-cb\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-deepseek-v3.2\n litellm_params:\n model: openai/DeepSeek-V3.2\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-qwen3-235b\n litellm_params:\n model: openai/Qwen3-235B\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-gpt-oss-120b\n litellm_params:\n model: openai/gpt-oss-120b\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 6.666666\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-llama31-8b\n litellm_params:\n model: openai/Meta-Llama-3.1-8B-Instruct\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 3.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-minimax-m2.5\n litellm_params:\n model: openai/MiniMax-M2.5\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 3.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: sambanova-e5-mistral-7b\n litellm_params:\n model: openai/E5-Mistral-7B-Instruct\n api_key: os.environ/SAMBANOVA_API_KEY\n api_base: https://api.sambanova.ai/v1\n max_budget: 3.333333\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: deepseek-deepseek\n litellm_params:\n model: deepseek/deepseek-chat\n api_key: os.environ/DEEPSEEK_API_KEY\n max_budget: 25.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: deepseek-deepseek-reasoner\n litellm_params:\n model: deepseek/deepseek-reasoner\n api_key: os.environ/DEEPSEEK_API_KEY\n max_budget: 25.0\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-google/imagen-4.0-ultra\n litellm_params:\n model: together_ai/google/imagen-4.0-ultra\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 0.25\n budget_duration: 30d\n rpm: 5\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.1-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.1-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-qwen/qwen-image-2.0-pro\n litellm_params:\n model: together_ai/Qwen/Qwen-Image-2.0-Pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-bytedance/seedance-1.0-pro\n litellm_params:\n model: together_ai/ByteDance/Seedance-1.0-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-rundiffusion/juggernaut-pro-flux\n litellm_params:\n model: together_ai/RunDiffusion/Juggernaut-pro-flux\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.1.1-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.1.1-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.1-kontext-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.1-kontext-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-openai/sora-2-pro\n litellm_params:\n model: together_ai/openai/sora-2-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-kwaivgi/kling-1.6-pro\n litellm_params:\n model: together_ai/kwaivgI/kling-1.6-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-kwaivgi/kling-2.1-pro\n litellm_params:\n model: together_ai/kwaivgI/kling-2.1-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-google/gemini-3-pro-image\n litellm_params:\n model: together_ai/google/gemini-3-pro-image\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-black-forest-labs/flux.2-pro\n litellm_params:\n model: together_ai/black-forest-labs/FLUX.2-pro\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-llama/llama31-405b\n litellm_params:\n model: together_ai/meta-llama/Llama-3.1-405B-Instruct\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 3.636363\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n- model_name: together-llama/llama33-70b-turbo\n litellm_params:\n model: together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo\n api_key: os.environ/TOGETHER_API_KEY\n max_budget: 2.727272\n budget_duration: 30d\n rpm: 60\n tpm: 100000\n model_info:\n input_cost_per_token: 1.0e-06\n output_cost_per_token: 1.0e-06\n# ── Zhipu AI / Z.ai (GLM models) ──────────────────\n- model_name: zhipu-glm-4.7\n litellm_params:\n model: openai/glm-4.7\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-5\n litellm_params:\n model: openai/glm-5\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-5-turbo\n litellm_params:\n model: openai/glm-5-turbo\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-4.6\n litellm_params:\n model: openai/glm-4.6\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-4.5\n litellm_params:\n model: openai/glm-4.5\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\n- model_name: zhipu-glm-4.5-air\n litellm_params:\n model: openai/glm-4.5-air\n api_key: os.environ/ZAI_API_KEY\n api_base: https://api.z.ai/api/coding/paas/v4\nlitellm_settings:\n max_budget: 2000\n budget_duration: 30d\n drop_params: true\n routing_strategy: usage-based-routing-v2\n default_fallbacks:\n - mistral-small\n success_callback:\n - langfuse\n failure_callback:\n - langfuse\n request_timeout: 60\n num_retries: 2\n retry_after: 5\n cache: true\n cache_params:\n type: local\n ttl: 300\ngeneral_settings:\n master_key: os.environ/LITELLM_MASTER_KEY\n database_url: os.environ/LITELLM_DATABASE_URL\n enable_jwt_auth: false\n ui_access_mode: admin_only\nenvironment_variables:\n LANGFUSE_HOST: http://172.18.0.1:3100\n LANGFUSE_PUBLIC_KEY: pk-lf-conductor\n LANGFUSE_SECRET_KEY: sk-lf-conductor\n\n# MCP Servers — disabled until mcp-deployer sidecar is built.\n# Re-enable when mcpDeployerSidecar.enabled=true and the OpenAPI spec\n# is mounted into the container.\n# mcp_servers:\n# github:\n# url: \"https://api.github.com\"\n# spec_path: \"/app/github-openapi.json\"\n# auth_type: \"bearer_token\"\n# auth_value: \"placeholder\"\n# extra_headers:\n# - \"authorization\"\n# allowed_tools:\n# - \"create_issue\"\n# - \"get_file_contents\"\n# - \"create_or_update_file\"\n# - \"create_pull_request\"\n# - \"create_branch\"\n"}}}} |