{
"id": "openrouter/pony-alpha",
"canonical_slug": "openrouter/pony-alpha",
"hugging_face_id": "",
"name": "Pony Alpha",
"created": 1770393855,
"description": "Pony is a cutting-edge foundation model with strong performance in coding, agentic workflows, reasoning, and roleplay, making it well suited for hands-on coding and real-world use.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.",
"context_length": 200000,
"architecture": {
"modality": "text-\u003Etext",
"input_modalities": [
"text"
],
"output_modalities": [
"text"
],
"tokenizer": "Other",
"instruct_type": null
},
"pricing": {
"prompt": "0",
"completion": "0",
"request": "0",
"image": "0",
"web_search": "0",
"internal_reasoning": "0"
},
"top_provider": {
"context_length": 200000,
"max_completion_tokens": 131000,
"is_moderated": false
},
"per_request_limits": null,
"supported_parameters": [
"include_reasoning",
"max_tokens",
"reasoning",
"response_format",
"structured_outputs",
"temperature",
"tools",
"top_p"
],
"default_parameters": {
"temperature": 1,
"top_p": 0.95,
"frequency_penalty": null
},
"expiration_date": null
},
OpenRouter proxies Perplexity models, e.g. Perplexity Sonar and variants; why aren't they listed in the models.dev list?
Reproduce:
Screenshot
Screenshot
I have a question for the maintainers. From a VERY brief look I took at the repo, there aren't any workflows to automatically update model lists for OpenAI compatible providers? Why not just run a workflow every 24 hrs to fetch and parse https://openrouter.ai/api/v1/models, which contains pretty much all the info you need, and update the list based on that?
Sample JSON from OpenRouter
{ "id": "openrouter/pony-alpha", "canonical_slug": "openrouter/pony-alpha", "hugging_face_id": "", "name": "Pony Alpha", "created": 1770393855, "description": "Pony is a cutting-edge foundation model with strong performance in coding, agentic workflows, reasoning, and roleplay, making it well suited for hands-on coding and real-world use.\n\n**Note:** All prompts and completions for this model are logged by the provider and may be used to improve the model.", "context_length": 200000, "architecture": { "modality": "text-\u003Etext", "input_modalities": [ "text" ], "output_modalities": [ "text" ], "tokenizer": "Other", "instruct_type": null }, "pricing": { "prompt": "0", "completion": "0", "request": "0", "image": "0", "web_search": "0", "internal_reasoning": "0" }, "top_provider": { "context_length": 200000, "max_completion_tokens": 131000, "is_moderated": false }, "per_request_limits": null, "supported_parameters": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "structured_outputs", "temperature", "tools", "top_p" ], "default_parameters": { "temperature": 1, "top_p": 0.95, "frequency_penalty": null }, "expiration_date": null },Thanks in advance!