Documentation Index
Fetch the complete documentation index at: https://docs.hunch.tools/docs/llms.txt
Use this file to discover all available pages before exploring further.
Dynamic Model Selection
Hunch offers two special model options: “Advanced Text” and “Fast Text”. These are dynamic selections that automatically use the most capable or efficient text models available:
- Advanced Text: Currently uses Anthropic’s Claude 3.5 Sonnet model. This option prioritizes advanced capabilities and high-quality outputs.
- Fast Text: Currently uses OpenAI’s GPT-4o Mini model. This option prioritizes speed and efficiency for quicker responses.
By choosing these dynamic options instead of specific models, your tools, templates, and canvases will automatically benefit from improvements as newer, better models are released. This removes the need to manually upgrade blocks in your workflows. However, you can still specify a particular model if you need to ensure consistency or have specific requirements.
Active models
| Provider | Model Name | Input Types | Output Type |
|---|
| OpenAI | GPT-4 Turbo | Text, Image | Text |
| OpenAI | GPT-4o | Text, Image, PDF | Text |
| OpenAI | GPT-4o Mini | Text, Image, PDF | Text |
| OpenAI | GPT-4.1 | Text, Image, PDF | Text |
| OpenAI | GPT-4.1 mini | Text, Image, PDF | Text |
| OpenAI | GPT-4.1 nano | Text, Image, PDF | Text |
| OpenAI | o1 | Text, Image, PDF | Text |
| OpenAI | o1-mini | Text | Text |
| OpenAI | o3-mini | Text, Image | Text |
| OpenAI | o3 | Text, Image, PDF | Text |
| OpenAI | o4-mini | Text, Image | Text |
| OpenAI | Whisper | Audio, Video, Text | Text |
| OpenAI | DALL·E 3 | Text | Image |
| OpenAI | GPT-Image-1 | Text, Image | Image |
| OpenAI | TTS | Text | Audio |
| OpenAI | TTS HD | Text | Audio |
| Stability | Stable Diffusion 3 Medium | Text | Image |
| Stability | Stable Diffusion 3 Large | Text | Image |
| Stability | Stable Diffusion 3 Turbo | Text | Image |
| Stability | Stable Image Core | Text | Image |
| Stability | Stable Image Ultra | Text | Image |
| Stability | Stable Diffusion 3.5 Large | Text | Image |
| Stability | Stable Diffusion 3.5 Large Turbo | Text | Image |
| Stability | Stable Diffusion 3.5 Medium | Text | Image |
| Fal | FLUX 1 Schnell | Text | Image |
| Fal | FLUX 1 Dev | Text | Image |
| Fal | FLUX 1.1 Pro | Text | Image |
| Fal | FLUX 1.1 Pro Ultra | Text | Image |
| Fal | Bria RMBG 2.0 | Image | Image |
| Ideogram | Ideogram 1 | Text | Image |
| Ideogram | Ideogram 1 Turbo | Text | Image |
| Ideogram | Ideogram 2 | Text | Image |
| Ideogram | Ideogram 2 Turbo | Text | Image |
| Ideogram | Ideogram 2A | Text | Image |
| Ideogram | Ideogram 2A Turbo | Text | Image |
| Ideogram | Ideogram 3 | Text | Image |
| Ideogram | Ideogram 3 Turbo | Text | Image |
| Ideogram | Ideogram 3 Quality | Text | Image |
| Eleven | ElevenLabs Turbo v2 | Text | Audio |
| Eleven | ElevenLabs Multilingual v2 | Text | Audio |
| Eleven | ElevenLabs Scribe v1 | Audio, Video | Text |
| Anthropic | Claude 3 Opus | Text, Image | Text |
| Anthropic | Claude 3.5 Sonnet | Text, Image | Text |
| Anthropic | Claude 3.5 Haiku | Text, Image | Text |
| Anthropic | Claude 3.7 Sonnet | Text, Image | Text |
| Anthropic | Claude 3.7 Sonnet (thinking) | Text, Image | Text |
| Anthropic | Claude 4 Opus | Text, Image | Text |
| Anthropic | Claude 4 Sonnet | Text, Image | Text |
| Google | Gemini 1.5 Pro | Text, Image, Audio, Video, PDF | Text |
| Google | Gemini 1.5 Flash | Text, Image, Audio, Video, PDF | Text |
| Google | Gemini 2.0 Flash | Text, Image, Audio, Video, PDF | Text |
| Google | Gemini 2.0 Flash Lite | Text, Image, Audio, Video, PDF | Text |
| Google | Gemini 2.5 Pro | Text, Image, Audio, Video, PDF | Text |
| Google | Gemini 2.5 Flash | Text, Image, Audio, Video, PDF | Text |
| Google | Gemini 2.5 Flash Lite | Text, Image, Audio, Video, PDF | Text |
| Google | Imagen 3 | Text | Image |
| Google | Imagen 3 Fast | Text | Image |
| Google | Imagen 4 | Text | Image |
| Google | Imagen 4 Ultra | Text | Image |
| Google | Veo 2 | Text | Video |
| Google | Veo 3 | Text | Video |
| Mistral | 7B | Text | Text |
| Mistral | Mixtral 8x7B | Text | Text |
| Mistral | Small | Text | Text |
| Mistral | Medium | Text | Text |
| Mistral | Large 2 | Text | Text |
| Mistral | OCR | PDF | Text |
| Perplexity | Sonar | Text | Text |
| Perplexity | Sonar Pro | Text | Text |
| Perplexity | Sonar Deep Research | Text | Text |
| Groq | Llama 3 70B | Text | Text |
| Groq | Llama 3 8B | Text | Text |
| Groq | Llama 3.1 8B Instant | Text | Text |
| Groq | Llama 4 Scout 17B | Text, Image | Text |
| Deepgram | Nova 3 English | Audio, Video, URL | Text |
| Deepgram | Nova 3 Multilingual | Audio, Video, URL | Text |
| Jina | Reader | URL | Text |
| Luma | Dream Machine | Text, Image | Video |
| Qwen | 2.5 72B Instruct | Text | Text |
| Groq | Gemma2 9B IT | Text | Text |
| Groq | Llama 3.2 1B Preview | Text | Text |
| Groq | Llama 3.2 3B Preview | Text | Text |
| Groq | Llama 3.2 11B Vision Preview | Text, Image | Text |
| Groq | Llama 3.2 90B Vision Preview | Text, Image | Text |
| Groq | Llama Guard 3 8B | Text | Text |
| Groq | Distil Whisper Large V3 EN | Audio | Text |
| Groq | Whisper Large V3 | Audio | Text |
| Groq | Whisper Large V3 Turbo | Audio | Text |
| Play | Play.ai Dialog | Text | Audio |
| Deepseek | R1 | Text | Text |
Legacy models
| Provider | Model Name | Input Types | Output Type |
|---|
| OpenAI | GPT-3.5 Turbo | Text | Text |
| OpenAI | GPT-4 | Text | Text |
| OpenAI | GPT-4.5 | Text, Image, PDF | Text |
| Stability | Stable Diffusion XL 1.0 | Text | Image |
| Eleven | ElevenLabs English v1 | Text | Audio |
| Anthropic | Claude 3 Sonnet | Text, Image | Text |
| Anthropic | Claude 3 Haiku | Text, Image | Text |
| Reducto | PDF Reader | PDF | Text |
| Groq | Mixtral 8x7B | Text | Text |
| Deepgram | Nova 2 | Audio, Video, URL | Text |
Deprecated models
| Provider | Model Name | Input Types | Output Type |
|---|
| OpenAI | GPT-4 Vision | Image, Text | Text |
| Anthropic | Claude 2.1 | Text | Text |
| Anthropic | Claude Instant 1 | Text | Text |
| Google | Gemini 1.0 Pro | Text | Text |
| Google | Gemini 1.0 Pro Vision | Image, Text | Text |
| Google | Gemini 2.0 Flash Thinking | Text | Text |
| Perplexity | Sonar Small Online | Text | Text |
| Perplexity | Sonar Large Online | Text | Text |
| Perplexity | Sonar Huge Online | Text | Text |
| Perplexity | Sonar Small Chat | Text | Text |
| Perplexity | Sonar Large Chat | Text | Text |
| Perplexity | Llama 3.1 70B Instruct | Text | Text |
| Groq | Llama 2 70B | Text | Text |
| Groq | Gemma 7B IT | Text | Text |
| Groq | Llama 3.1 70B Versatile | Text | Text |
