Reference
Hunch AI Model List
Reference
Hunch AI Model List
Powerful artificial intelligence engines driving your workflows
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 | Tokens In | Tokens Out |
|---|---|---|---|---|---|
| OpenAI | GPT-4 Turbo | Text, Image | Text | 128,000 | 4,096 |
| OpenAI | GPT-4o | Text, Image | Text | 128,000 | 4,096 |
| OpenAI | GPT-4o mini | Text, Image | Text | 128,000 | 16,384 |
| OpenAI | o1-preview | Text | Text | 128,000 | 32,768 |
| OpenAI | o1-mini | Text | Text | 128,000 | 65,536 |
| OpenAI | Whisper | Audio, Video, Text | Text | ||
| OpenAI | DALL-E 3 | Text | Image | ||
| OpenAI | TTS-1 | Text | Audio | ||
| OpenAI | TTS-1 HD | Text | Audio | ||
| Stability | SD3 Medium | Text | Image | ||
| Stability | SD3 Large | Text | Image | ||
| Stability | SD3 Turbo | Text | Image | ||
| Stability | Image Core | Text | Image | ||
| Stability | Image Ultra | Text | Image | ||
| ElevenLabs | Turbo V2 | Text | Audio | ||
| ElevenLabs | Multilingual V2 | Text | Audio | ||
| Anthropic | Claude 3 Opus | Text, Image | Text | 200,000 | 4,096 |
| Anthropic | Claude 3 Haiku | Text, Image | Text | 200,000 | 4,096 |
| Anthropic | Claude 3.5 Sonnet | Text, Image | Text | 200,000 | 8,192 |
| Gemini 1.5 Pro | Text, Image, Audio, Video | Text | |||
| Gemini 1.5 Flash | Text, Image, Audio, Video | Text | |||
| Mistral | 7B | Text | Text | ||
| Mistral | 8x7B | Text | Text | ||
| Mistral | Small | Text | Text | ||
| Mistral | Medium | Text | Text | ||
| Mistral | Large 2 | Text | Text | ||
| Reducto | Text | ||||
| Wolfram | Alpha | 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 Online | Text | Text | ||
| Perplexity | Llama 3.1 70B Instruct | Text | Text | ||
| Groq | Mixtral 8x7B | Text | Text | ||
| Groq | Gemma 7B IT | Text | Text | ||
| Groq | LLaMA3 70B | Text | Text | ||
| Groq | LLaMA3 8B | Text | Text | ||
| Groq | LLaMA3-1 70B | Text | Text | ||
| Groq | LLaMA3-1 8B | Text | Text | ||
| Groq | Distil-Whisper English | Audio, Video, URL | Text | ||
| Groq | Whisper Large V3 | Audio, Video, URL | Text | ||
| Groq | Whisper Large V3 Turbo | Audio, Video, URL | Text | ||
| Deepgram | Nova 2 | Audio, Video, URL | Text | ||
| Jina | Reader | URL | Text | ||
| Google Search | URL | Text | |||
| Qwen | 2.5 72B Instruct | Text | Text | ||
| Luma | Dream Machine | Text | Video | ||
| fal | FLUX.1 [schnell] | Text | Image | ||
| fal | FLUX.1 [dev] | Text | Image | ||
| fal | FLUX1.1 [pro] | Text | Image | ||
| Ideogram | Ideogram 1.0 | Text | Image | ||
| Ideogram | Ideogram 1.0 Turbo | Text | Image | ||
| Ideogram | Ideogram 2.0 | Text | Image | ||
| Ideogram | Ideogram 2.0 Turbo | Text | Image |
Legacy models
| Provider | Model Name | Input Types | Output Type |
|---|---|---|---|
| OpenAI | GPT-4 | Text | Text |
| OpenAI | GPT-4 Vision | Image, Text | Text |
| OpenAI | GPT-3.5 | Text | Text |
| Stability | XL 1 | Text | Image |
| Eleven | Mono | Text | Audio |
| Anthropic | Claude 2 | Text | Text |
| Anthropic | Claude Instant 1 | Text | Text |
| Anthropic | Claude 3 Sonnet | Text, Image | Text |
| Gemini Pro | Text | Text | |
| Gemini Pro Vision | Image, Text | Text |
Deprecated models
| Provider | Model Name | Input Types | Output Type |
|---|---|---|---|
| Perplexity | Sonar Small Chat | Text | Text |
| Perplexity | Sonar Medium Chat | Text | Text |
| Perplexity | Code LLaMA 70B Instruct | Text | Text |
| Groq | LLaMA2 70B | Text | Text |