AI models supported by Polymeti
Use any of these with your own API key. Your messages go from your browser straight to the model's provider — Polymeti is not in between.
Private by design.
Your key stays in your browser and your conversations are stored on your device, not on our servers.
OpenAI
- GPT-5.6 Sol Frontier model for complex professional work
- GPT-5.6 Terra GPT-5.6 model that balances intelligence and cost
- GPT-5.6 Luna GPT-5.6 model optimized for cost-sensitive workloads
- GPT-5.5 Pro Version of GPT-5.5 that produces smarter and more precise responses.
- GPT-5.5 A new class of intelligence for coding and professional work.
- GPT-5.4 Pro Version of GPT-5.4 that produces smarter and more precise responses.
- GPT-5.4 A more affordable model for coding and professional work.
- GPT-5.4 Mini Our strongest mini model yet for coding, computer use, and subagents
- GPT-5.4 Nano Our cheapest GPT-5.4-class model for simple high-volume tasks
- GPT-5.2 Previous frontier model for professional work with configurable reasoning effort
- GPT-5 Mini Near-frontier intelligence for cost sensitive, low latency, high volume workloads
- GPT-5 Nano Fastest, most cost-efficient version of GPT-5
- GPT-4o Mini Fast, affordable small model for focused tasks
- GPT-3.5 Turbo Legacy GPT model for cheaper chat and non-chat tasks
- GPT-4.1 Smartest non-reasoning model
- GPT-4.1 Mini Smaller, faster version of GPT-4.1
- GPT-4.1 Nano Fastest, most cost-efficient version of GPT-4.1
- GPT-4o Fast, intelligent, flexible GPT model
- GPT-5 Previous intelligent reasoning model for coding and agentic tasks with configurable reasoning effort
- GPT-5 Pro Version of GPT-5 that produces smarter and more precise responses
- GPT-5.1 The best model for coding and agentic tasks with configurable reasoning effort
- GPT-5.2 Chat GPT-5.2 model used in ChatGPT
- GPT-5.2 Pro Previous pro model for professional work that produces smarter and more precise responses
- GPT-5.3 Chat GPT-5.3 Instant model used in ChatGPT
- GPT-5.3 Codex The most capable agentic coding model to date
- o1 Previous full o-series reasoning model
- o3 Reasoning model for complex tasks, succeeded by GPT-5
- o3 Mini A small model alternative to o3
- o4 Mini Fast, cost-efficient reasoning model, succeeded by GPT-5 mini
- GPT Image 2 State-of-the-art image generation model
- GPT Image 1 Our previous image generation model
- GPT Image 1 Mini A cost-efficient version of GPT Image 1
- GPT Image 1.5 Our previous image generation model
Anthropic
- Claude Fable 5 The most capable Claude. Best for hard problems and long, multi-step work.
- Claude Opus 4.8 Strong at code and detailed technical work.
- Claude Opus 4.7 Careful, thorough reasoning over long documents.
- Claude Opus 4.6 Older version. Prefer Opus 4.7 or 4.8.
- Claude Opus 4.5 Older version. Prefer Opus 4.7 or 4.8.
- Claude Opus 4.1 The oldest Opus still available. Retires 5 August 2026.
- Claude Sonnet 5 Fast and capable. A good default for everyday work.
- Claude Sonnet 4.6 Balanced speed and quality for writing and code.
- Claude Sonnet 4.5 Older version. Prefer Sonnet 4.6 or 5.
- Claude Haiku 4.5 The fastest and cheapest Claude. Good for short questions.
- Claude Opus 5 The newest Opus. Strong at complex code and long, multi-step work.
Google
- Gemini 3.6 Flash Fast, capable and cheap. The best Gemini for everyday work.
- Gemini 3.5 Flash Older fast Gemini. Still quick and cheap; 3.6 Flash is better.
- Gemini 3.5 Flash Lite A fast, low-cost Gemini 3.5 for high-volume, simple tasks.
- Gemini 3.1 Flash Lite Older version. Prefer Gemini 3.5 Flash Lite. Retires 7 May 2027.
- Gemini 2.5 Flash Lite Older version. Prefer Gemini 3.5 Flash Lite. Retires 16 October 2026.
- Gemini 2.5 Pro Older version. Retires 16 October 2026.
- Gemini 2.5 Flash Older version. Prefer Gemini 3.6 Flash. Retires 16 October 2026.
- Gemini 3.1 Flash Image Creates and edits images from a description. Fast, good quality.
- Gemini 3.1 Flash Lite Image Creates and edits images the fastest and cheapest. Less detail.
- Gemini 3 Pro Image The highest-quality images, good with text in the picture. Slower.
- Gemini 2.5 Flash Image Older image model. Shuts down 2 October 2026 — use Gemini 3.1 Flash Image.
xAI
- Grok 4.5 Strong at code and technical work.
- Grok 4.3 xAI's best all-round model. Fast and capable.
- Grok 4.20 Reasoning Older Grok. Thinks before answering, so it is slower.
- Grok 4.20 Non-Reasoning Older Grok. Answers immediately, with less care.
DeepSeek