List available models
https://api.poe.com/v1/modelsOverview
Returns a list of all models available via the Poe API.
Popular models include:
GPT-5-Pro- OpenAI's latest flagship model with extended reasoningGPT-5-Codex- Specialized for software engineering tasksClaude-Sonnet-4.5- Anthropic's most advanced modelClaude-Haiku-4.5- Fast and efficient with frontier intelligenceGemini-2.5-Pro- Google's advanced model with web searchGrok-4- xAI's most intelligent language modelDeepSeek-R1- Top open-source reasoning model
You can also access specialized bots for image generation (Nano-Banana, Amazon-Nova-Canvas), video generation (Amazon-Nova-Reel-1.1), and many other community-created models.
Note: This endpoint does not require authentication and returns all publicly available models.
Authentication
Send your Poe API key in the Authorization header:
Authorization: Bearer sk_test_51SAMPLEKEYAll requests must be made over HTTPS.
Parameters
This endpoint does not accept query or path parameters.
Responses
| Field | Type | Required | Description |
|---|---|---|---|
object | "list" | Optional | Object type identifier Allowed values: list |
data | object[] | Optional | |
data[].id | string | Required | Model identifier |
data[].object | "model" | Required | Object type, always "model" Allowed values: model |
data[].created | int64 | Required | Unix timestamp in milliseconds of when the model was created |
data[].description | string | Optional | Detailed description of the model's capabilities, features, and usage instructions |
data[].owned_by | string | Required | Organization that owns the model |
data[].permission | object[] | Optional | Permission information for the model (typically empty) |
data[].root | string | Optional | Root model identifier |
data[].parent | string | null | Optional | Parent model identifier if this is a derivative model |
data[].architecture | object | Optional | Model architecture and modality information |
data[].architecture.input_modalities | "text" | "image" | "video" | "audio"[] | Optional | Supported input modalities |
data[].architecture.output_modalities | "text" | "image" | "video"[] | Optional | Supported output modalities |
data[].architecture.modality | string | Optional | Simplified modality string representation |
data[].pricing | object | null | Optional | Pricing information for the model. Null for free models or models with request-based pricing |
❌ Error codes
| Http | Type | Description |
|---|---|---|
| 429 | rate_limit_error | Rate limit exceeded Rate limit exceeded (500 requests per minute) |
Best Practices
Cache the models list in your application. Model availability doesn't change frequently, so you can safely cache this response for 1-24 hours.
This endpoint returns all publicly available models. Consider:
- Caching: Models list changes infrequently, cache for 1-24 hours
- Filtering: Filter models by
architecture.input_modalitiesfor your use case - Pricing: Use the
pricingfield to estimate costs before making requests
🔁 Callbacks & webhooks
No callbacks or webhooks are associated with this endpoint.