Switch between models mid-conversation — your CLAIV memory follows you everywhere. All models powered by OpenRouter for maximum reliability and access to the latest releases.
Fastest responses for everyday questions and high-volume tasks.
A large step up in quality at only twice the token cost of Nano.
OpenAI's flagship reasoning model — strong across coding, math, and logic.
Highly capable OpenAI model. State-of-the-art on reasoning benchmarks.
Latest OpenAI model with computer use and a 1M context window.
Anthropic's fastest Claude — nuanced tone and excellent instruction following.
Exceptional writing quality and nuanced reasoning at a balanced cost.
Anthropic's most powerful model. Best for expert-level analysis and writing.
Ultra-fast with a longer context window than GPT-5 Nano — great for document tasks.
A 128k context window at a low token cost — ideal for long document analysis.
Google's flagship with a massive 200k context. Best for large corpora.
Next-generation Google model. Benchmark leader across coding and reasoning.
Meta's open-source flagship — strong reasoning and coding at a very low token cost.
Optimised for chain-of-thought reasoning, math, and science at frontier quality.
Fast, highly capable open model rivaling frontier models at a fraction of the cost.
Sorted by Echo Token rate — lowest to highest
| Model | Provider | ET Rate | Min Plan | Context |
|---|---|---|---|---|
| GPT-5 Nano | OpenAI | 4 ET / 1k | Free | 32k |
| Gemini 2.5 Flash-Lite | 4 ET / 1k | Free | 64k | |
| DeepSeek V3 | Open Source | 4 ET / 1k | Builder | 256k |
| GPT-5 Mini | OpenAI | 5 ET / 1k | Pro+ | 64k |
| Gemini 2.5 Flash | 5 ET / 1k | Pro+ | 128k | |
| Llama 3.3 70B | Open Source | 5 ET / 1k | Builder | 128k |
| DeepSeek R1 | Open Source | 5 ET / 1k | Builder | 64k |
| Claude Haiku 4.5 | Anthropic | 6 ET / 1k | Pro+ | 100k |
| GPT-5 | OpenAI | 9 ET / 1k | Power+ | 128k |
| Gemini 2.5 Pro | 9 ET / 1k | Power+ | 200k | |
| Gemini 3.1 Pro | 10 ET / 1k | Builder | 1M | |
| GPT-5.2 | OpenAI | 11 ET / 1k | Power+ | 128k |
| Claude Sonnet 4.6 | Anthropic | 12 ET / 1k | Power+ | 200k |
| GPT-5.4 | OpenAI | 13 ET / 1k | Builder | 1M |
| Claude Opus 4.6 | Anthropic | 18 ET / 1k | Builder | 200k |
ET rates per 1,000 combined input + output tokens. Online search adds a flat +5 ET per message. Persistent memory is included at no extra cost on all plans.
Start with GPT-5 Nano and Gemini Flash-Lite on the free plan. Upgrade to unlock Claude Opus, GPT-5.4, and more.