Models

Retrieve the list of active LLM and image-generation models available in Fetch Hive

List active models

Returns all active (non-deprecated) LLM and image-generation models available in Fetch Hive as a flat JSON array. Excludes embedding-only models.

TogetherAI-hosted models — DeepSeek, Qwen, Kimi, Mistral, MiniMax, Meta Llama, and other Together-hosted models are sourced dynamically from https://api.together.ai/v1/models (filtered to type == "chat") and refreshed once per day. The list in this response reflects models that currently have active pricing on Together AI. Models that Together AI withdraws or de-prices are automatically removed on the next refresh.

GET /v1/models

Authentication

Requires a Bearer API key. See Authentication.

Response

Returns a JSON array. Each object includes:

Field	Type	Description
id	string	The model identifier used when configuring prompts, workflows, or agents via the API
name	string	Human-readable display name
slug	string	URL-friendly slug derived from the model name (e.g. gpt-4-1)
provider	string	Provider key. For TogetherAI-hosted models this resolves to the underlying model maker — e.g. deepseek, qwen, kimi, mistral, minimax, or llama — rather than togetherai
provider_name	string	Provider display name (e.g. MiniMax)
context_limit	integer	Maximum context window in tokens (0 if unknown)
model_type	string	Model category. Use llm for chat/text models and image_generation for models that generate images
is_image_generation	boolean	true when the model generates images
is_vision	boolean	Supports image inputs. This is separate from image generation; vision-capable LLMs can accept image input but do not generate images
is_reasoning	boolean	true for both OpenAI/xAI reasoning-effort models (o1, o3, GPT-5) and Anthropic extended-thinking models (Claude Sonnet/Opus)
is_tool_calling	boolean	Supports tool/function calling
is_json_schema	boolean	Supports structured JSON schema output

Filter on model_type when choosing models for a specific workflow. Use model_type: "llm" for LLM/chat selectors and model_type: "image_generation" for image-generation selectors. Do not use is_vision to identify image-generation models.

Example response

[
  {
    "id": "gpt-4.1",
    "name": "GPT 4.1",
    "slug": "gpt-4-1",
    "provider": "openai",
    "provider_name": "OpenAI",
    "context_limit": 1047576,
    "model_type": "llm",
    "is_image_generation": false,
    "is_vision": true,
    "is_reasoning": false,
    "is_tool_calling": true,
    "is_json_schema": true
  },
  {
    "id": "claude-sonnet-4-6",
    "name": "Claude Sonnet 4.6",
    "slug": "claude-sonnet-4-6",
    "provider": "anthropic",
    "provider_name": "Anthropic",
    "context_limit": 200000,
    "model_type": "llm",
    "is_image_generation": false,
    "is_vision": true,
    "is_reasoning": true,
    "is_tool_calling": true,
    "is_json_schema": false
  },
  {
    "id": "MiniMaxAI/MiniMax-M2.5",
    "name": "MiniMax M2.5",
    "slug": "minimax-m2-5",
    "provider": "minimax",
    "provider_name": "MiniMax",
    "context_limit": 256000,
    "model_type": "llm",
    "is_image_generation": false,
    "is_vision": false,
    "is_reasoning": true,
    "is_tool_calling": true,
    "is_json_schema": true
  },
  {
    "id": "moonshotai/Kimi-K2.5",
    "name": "Kimi K2.5",
    "slug": "kimi-k2-5",
    "provider": "kimi",
    "provider_name": "Kimi",
    "context_limit": 256000,
    "model_type": "llm",
    "is_image_generation": false,
    "is_vision": true,
    "is_reasoning": true,
    "is_tool_calling": true,
    "is_json_schema": true
  },
  {
    "id": "gpt-image-2",
    "name": "GPT Image 2",
    "slug": "gpt-image-2",
    "provider": "openai",
    "provider_name": "OpenAI",
    "context_limit": 0,
    "model_type": "image_generation",
    "is_image_generation": true,
    "is_vision": false,
    "is_reasoning": false,
    "is_tool_calling": false,
    "is_json_schema": false
  },
  {
    "id": "gemini-2.5-flash-image",
    "name": "Gemini 2.5 Flash Image",
    "slug": "gemini-2-5-flash-image",
    "provider": "google",
    "provider_name": "Google",
    "context_limit": 0,
    "model_type": "image_generation",
    "is_image_generation": true,
    "is_vision": false,
    "is_reasoning": false,
    "is_tool_calling": false,
    "is_json_schema": false
  }
]

See Model Library for a full overview of supported models by provider.