routstr-core/models.example.json

{
    "models": [
        {
            "id": "google/gemini-2.5-flash",
            "canonical_slug": "google/gemini-2.5-flash",
            "hugging_face_id": "",
            "name": "Google: Gemini 2.5 Flash",
            "created": 1750172488,
            "description": "Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling. \n\nAdditionally, Gemini 2.5 Flash is configurable through the \"max tokens for reasoning\" parameter, as described in the documentation (https://openrouter.ai/docs/use-cases/reasoning-tokens#max-tokens-for-reasoning).",
            "context_length": 1048576,
            "architecture": {
                "modality": "text+image->text",
                "input_modalities": [
                    "file",
                    "image",
                    "text"
                ],
                "output_modalities": [
                    "text"
                ],
                "tokenizer": "Gemini",
                "instruct_type": null
            },
            "pricing": {
                "prompt": "0.0000003",
                "completion": "0.0000025",
                "request": "0",
                "image": "0.001238",
                "web_search": "0",
                "internal_reasoning": "0",
                "input_cache_read": "0.000000075",
                "input_cache_write": "0.0000003833"
            },
            "top_provider": {
                "context_length": 1048576,
                "max_completion_tokens": 65535,
                "is_moderated": false
            },
            "per_request_limits": null,
            "supported_parameters": [
                "max_tokens",
                "temperature",
                "top_p",
                "tools",
                "tool_choice",
                "stop",
                "response_format",
                "structured_outputs"
            ]
        },
        {
            "id": "openai/o3-pro",
            "canonical_slug": "openai/o3-pro-2025-06-10",
            "hugging_face_id": "",
            "name": "OpenAI: o3 Pro",
            "created": 1749598352,
            "description": "The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently better answers.\n\nNote that BYOK is required for this model. Set up here: https://openrouter.ai/settings/integrations",
            "context_length": 200000,
            "architecture": {
                "modality": "text+image->text",
                "input_modalities": [
                    "text",
                    "file",
                    "image"
                ],
                "output_modalities": [
                    "text"
                ],
                "tokenizer": "Other",
                "instruct_type": null
            },
            "pricing": {
                "prompt": "0.00002",
                "completion": "0.00008",
                "request": "0",
                "image": "0.0153",
                "web_search": "0",
                "internal_reasoning": "0"
            },
            "top_provider": {
                "context_length": 200000,
                "max_completion_tokens": 100000,
                "is_moderated": true
            },
            "per_request_limits": null,
            "supported_parameters": [
                "tools",
                "tool_choice",
                "seed",
                "max_tokens",
                "response_format",
                "structured_outputs"
            ]
        },
        {
            "id": "x-ai/grok-3-mini",
            "canonical_slug": "x-ai/grok-3-mini",
            "hugging_face_id": "",
            "name": "xAI: Grok 3 Mini",
            "created": 1749583245,
            "description": "A lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. The raw thinking traces are accessible.",
            "context_length": 131072,
            "architecture": {
                "modality": "text->text",
                "input_modalities": [
                    "text"
                ],
                "output_modalities": [
                    "text"
                ],
                "tokenizer": "Grok",
                "instruct_type": null
            },
            "pricing": {
                "prompt": "0.0000003",
                "completion": "0.0000005",
                "request": "0",
                "image": "0",
                "web_search": "0",
                "internal_reasoning": "0",
                "input_cache_read": "0.000000075"
            },
            "top_provider": {
                "context_length": 131072,
                "max_completion_tokens": null,
                "is_moderated": false
            },
            "per_request_limits": null,
            "supported_parameters": [
                "tools",
                "tool_choice",
                "max_tokens",
                "temperature",
                "top_p",
                "reasoning",
                "include_reasoning",
                "structured_outputs",
                "stop",
                "seed",
                "logprobs",
                "top_logprobs",
                "response_format"
            ]
        }
    ]
}