litellm-config-auto.yaml

general_settings:
  master_key: "os.environ/LITELLM_MASTER_KEY"

litellm_settings:
  drop_params: True
  modify_params: True
  additional_drop_params: ["messages[*].prefix"]
  callbacks: ["trim_messages_hook.proxy_handler_instance", "trim_messages_hook.error_handler_instance"]
  set_verbose: False
  request_timeout: 300

model_list:
  - model_name: gpt-4o-mini  # Cursor sees this and lets it pass
    litellm_params:
      model: openrouter/qwen/qwen3-coder:free # What you actually want to use
      api_key: "os.environ/OPENROUTER_API_KEY"
  - model_name: my-free-models
    litellm_params:
      model: openrouter/qwen/qwen3-coder:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-models
    litellm_params:
      model: openrouter/mistralai/mistral-small-3.1-24b-instruct:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-models
    litellm_params:
      model: openrouter/google/gemma-3-27b-it:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-models
    litellm_params:
      model: openrouter/stepfun/step-3.5-flash:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/qwen/qwen3-4b:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 32768
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/z-ai/glm-4.5-air:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/nvidia/nemotron-3-nano-30b-a3b:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/tngtech/tng-r1t-chimera:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/nvidia/nemotron-nano-12b-v2-vl:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/arcee-ai/trinity-mini:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/nvidia/nemotron-nano-9b-v2:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-models
    litellm_params:
      model: openrouter/upstage/solar-pro-3:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-coders-new
    litellm_params:
      model: gemini/gemini-3-flash-preview
      api_key: "os.environ/GOOGLE_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 1048576
      max_tokens: 65535
  - model_name: my-free-coders-new
    litellm_params:
      model: gemini/gemini-2.5-flash
      api_key: "os.environ/GOOGLE_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 1048576
      max_tokens: 65535
  - model_name: my-free-coders-new
    litellm_params:
      model: gemini/gemini-2.5-pro
      api_key: "os.environ/GOOGLE_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 1048576
      max_tokens: 65535
  - model_name: my-free-coders-new
    litellm_params:
      model: openrouter/openai/gpt-oss-20b:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-coders-new
    litellm_params:
      model: openrouter/meta-llama/llama-3.3-70b-instruct:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-coders-new
    litellm_params:
      model: openrouter/qwen/qwen3-next-80b-a3b-instruct:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 262144
      max_tokens: 8192
  - model_name: my-free-coders-new
    litellm_params:
      model: openrouter/nvidia/nemotron-3-nano-30b-a3b:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-free-coders
    litellm_params:
      model: openrouter/openai/gpt-oss-120b:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-free-coders
    litellm_params:
      model: openrouter/arcee-ai/trinity-large-preview:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-paid-coders
    litellm_params:
      model: openrouter/openai/gpt-oss-20b
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-paid-coders
    litellm_params:
      model: openrouter/nousresearch/deephermes-3-mistral-24b-preview
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 32000
      max_tokens: 8192
  - model_name: my-paid-coders
    litellm_params:
      model: openrouter/qwen/qwen-2.5-7b-instruct
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 32768
      max_tokens: 8192
  - model_name: my-paid-coders
    litellm_params:
      model: openrouter/mistralai/ministral-3b
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-paid-coders
    litellm_params:
      model: openrouter/meta-llama/llama-3.1-8b-instruct
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 4096
  - model_name: my-paid-coders
    litellm_params:
      model: openrouter/meta-llama/llama-3-8b-instruct
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 8192
      max_tokens: 4096
  - model_name: my-hf-models
    litellm_params:
      model: huggingface/meta-llama/Llama-3.3-70B-Instruct
      api_key: "os.environ/HF_TOKEN"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-hf-models
    litellm_params:
      model: huggingface/together/deepseek-ai/DeepSeek-R1
      api_key: "os.environ/HF_TOKEN"
      order: 2
    model_info:
      max_input_tokens: 128000
      max_tokens: 32768
  - model_name: my-large-context
    litellm_params:
      model: openrouter/meta-llama/llama-3.3-70b-instruct:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 1
    model_info:
      max_input_tokens: 128000
      max_tokens: 8192
  - model_name: my-large-context
    litellm_params:
      model: openrouter/qwen/qwen3-next-80b-a3b-instruct:free
      api_key: "os.environ/OPENROUTER_API_KEY"
      order: 2
    model_info:
      max_input_tokens: 262144
      max_tokens: 8192

router_settings:
  model_group_alias:
    "grok-code-fast-1": "my-free-coders-new"
  routing_strategy: latency-based-routing
  enable_pre_call_checks: true
  num_retries: 3
  allowed_fails: 3
  cooldown_time: 30
  retry_after: 10
  timeout: 600
  stream_timeout: 300
  max_fallbacks: 10
  default_fallbacks:
    - my-large-context
    - my-free-models
  retry_policy:
    AuthenticationErrorRetries: 3
    TimeoutErrorRetries: 3
    RateLimitErrorRetries: 3
    ContentPolicyViolationErrorRetries: 4
    InternalServerErrorRetries: 6
  allowed_fails_policy:
    BadRequestErrorAllowedFails: 1000
    NotFoundErrorAllowedFails: 1000
    AuthenticationErrorAllowedFails: 10
    TimeoutErrorAllowedFails: 12
    RateLimitErrorAllowedFails: 10000
    ContentPolicyViolationErrorAllowedFails: 15
    InternalServerErrorAllowedFails: 20
  fallbacks:
    - my-free-coders-new:
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-free-coders:
        - my-free-coders-new
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-paid-coders:
        - my-free-coders-new
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-free-models:
        - my-large-context
        - my-hf-models
    - my-hf-models:
        - my-large-context
        - my-free-models
    - my-large-context:
        - my-free-models
        - my-hf-models
  context_window_fallbacks:
    - my-free-coders-new:
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-free-coders:
        - my-free-coders-new
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-paid-coders:
        - my-free-coders-new
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-free-models:
        - my-large-context
        - my-hf-models
    - my-hf-models:
        - my-large-context
        - my-free-models
    - my-large-context:
        - my-free-models
        - my-hf-models
  content_policy_fallbacks:
    - my-free-coders-new:
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-free-coders:
        - my-free-coders-new
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-paid-coders:
        - my-free-coders-new
        - my-large-context
        - my-free-models
        - my-hf-models
    - my-free-models:
        - my-large-context
        - my-hf-models
    - my-hf-models:
        - my-large-context
        - my-free-models
    - my-large-context:
        - my-free-models
        - my-hf-models
  default_litellm_params:
    # Lower default to reduce output token usage; clients can override with max_tokens in the request
    max_tokens: 2048