{ "$schema": "https://json-schema.org/draft/2020-12/schema", "$id": "#/components/schemas/Model", "title": "Model", "properties": { "handle": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Handle", "description": "The handle for this config, in the format provider/model-name." }, "name": { "type": "string", "title": "Name", "description": "The actual model name used by the provider" }, "display_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Display Name", "description": "A human-friendly display name for the model." }, "provider_type": { "$ref": "#/components/schemas/ProviderType", "description": "The type of the provider" }, "provider_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Provider Name", "description": "The provider name for the model." }, "model_type": { "type": "string", "const": "llm", "title": "Model Type", "description": "Type of model (llm or embedding)", "default": "llm" }, "model": { "type": "string", "title": "Model", "description": "Deprecated: Use 'name' field instead. LLM model name.", "deprecated": true }, "model_endpoint_type": { "type": "string", "enum": [ "openai", "anthropic", "google_ai", "google_vertex", "azure", "groq", "ollama", "webui", "webui-legacy", "lmstudio", "lmstudio-legacy", "lmstudio-chatcompletions", "llamacpp", "koboldcpp", "vllm", "hugging-face", "baseten", "minimax", "mistral", "together", "bedrock", "deepseek", "xai", "zai", "zai_coding", "openrouter", "chatgpt_oauth" ], "title": "Model Endpoint Type", "description": "Deprecated: Use 'provider_type' field instead. The endpoint type for the model.", "deprecated": true }, "model_endpoint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Model Endpoint", "description": "Deprecated: The endpoint for the model.", "deprecated": true }, "provider_category": { "anyOf": [ { "$ref": "#/components/schemas/ProviderCategory" }, { "type": "null" } ], "description": "Deprecated: The provider category for the model.", "deprecated": true }, "model_wrapper": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Model Wrapper", "description": "Deprecated: The wrapper for the model.", "deprecated": true }, "context_window": { "type": "integer", "title": "Context Window", "description": "Deprecated: Use 'max_context_window' field instead. The context window size for the model.", "deprecated": true }, "put_inner_thoughts_in_kwargs": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Put Inner Thoughts In Kwargs", "description": "Deprecated: Puts 'inner_thoughts' as a kwarg in the function call.", "default": true, "deprecated": true }, "temperature": { "type": "number", "title": "Temperature", "description": "Deprecated: The temperature to use when generating text with the model.", "default": 0.7, "deprecated": true }, "max_tokens": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Max Tokens", "description": "Deprecated: The maximum number of tokens to generate.", "deprecated": true }, "enable_reasoner": { "type": "boolean", "title": "Enable Reasoner", "description": "Deprecated: Whether or not the model should use extended thinking if it is a 'reasoning' style model.", "default": true, "deprecated": true }, "reasoning_effort": { "anyOf": [ { "type": "string", "enum": [ "none", "minimal", "low", "medium", "high", "xhigh" ] }, { "type": "null" } ], "title": "Reasoning Effort", "description": "Deprecated: The reasoning effort to use when generating text reasoning models.", "deprecated": true }, "max_reasoning_tokens": { "type": "integer", "title": "Max Reasoning Tokens", "description": "Deprecated: Configurable thinking budget for extended thinking.", "default": 0, "deprecated": true }, "effort": { "anyOf": [ { "type": "string", "enum": [ "low", "medium", "high", "max" ] }, { "type": "null" } ], "title": "Effort", "description": "The effort level for Anthropic models that support it (Opus 4.5, Opus 4.6). Controls token spending and thinking behavior. Not setting this gives similar performance to 'high'." }, "frequency_penalty": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Frequency Penalty", "description": "Deprecated: Positive values penalize new tokens based on their existing frequency in the text so far.", "deprecated": true }, "compatibility_type": { "anyOf": [ { "type": "string", "enum": [ "gguf", "mlx" ] }, { "type": "null" } ], "title": "Compatibility Type", "description": "Deprecated: The framework compatibility type for the model.", "deprecated": true }, "verbosity": { "anyOf": [ { "type": "string", "enum": [ "low", "medium", "high" ] }, { "type": "null" } ], "title": "Verbosity", "description": "Deprecated: Soft control for how verbose model output should be.", "deprecated": true }, "tier": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Tier", "description": "Deprecated: The cost tier for the model (cloud only).", "deprecated": true }, "parallel_tool_calls": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Parallel Tool Calls", "description": "Deprecated: If set to True, enables parallel tool calling.", "default": false, "deprecated": true }, "response_format": { "anyOf": [ { "oneOf": [ { "$ref": "#/components/schemas/TextResponseFormat" }, { "$ref": "#/components/schemas/JsonSchemaResponseFormat" }, { "$ref": "#/components/schemas/JsonObjectResponseFormat" } ], "discriminator": { "propertyName": "type", "mapping": { "json_object": "#/components/schemas/JsonObjectResponseFormat", "json_schema": "#/components/schemas/JsonSchemaResponseFormat", "text": "#/components/schemas/TextResponseFormat" } } }, { "type": "null" } ], "title": "Response Format", "description": "The response format for the model's output. Supports text, json_object, and json_schema (structured outputs). Can be set via model_settings." }, "strict": { "type": "boolean", "title": "Strict", "description": "Enable strict mode for tool calling. When true, tool schemas include strict: true and additionalProperties: false, guaranteeing tool outputs match JSON schemas.", "default": false }, "return_logprobs": { "type": "boolean", "title": "Return Logprobs", "description": "Whether to return log probabilities of the output tokens. Useful for RL training.", "default": false }, "top_logprobs": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Top Logprobs", "description": "Number of most likely tokens to return at each position (0-20). Requires return_logprobs=True." }, "return_token_ids": { "type": "boolean", "title": "Return Token Ids", "description": "Whether to return token IDs for all LLM generations via SGLang native endpoint. Required for multi-turn RL training with loss masking. Only works with SGLang provider.", "default": false }, "tool_call_parser": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Tool Call Parser", "description": "SGLang tool call parser name (e.g. 'glm47', 'qwen25', 'hermes'). Used by the SGLang native adapter to parse tool calls from raw model output." }, "max_context_window": { "type": "integer", "title": "Max Context Window", "description": "The maximum context window for the model" } }, "type": "object", "required": [ "name", "provider_type", "model", "model_endpoint_type", "context_window", "max_context_window" ] }