Sakana AI / sakana/fugu-max
Fugu Max - access through LLMTR
Fugu Max is Sakana AI's OpenAI-compatible multi-agent model. It uses the same agent approach as Fugu Ultra but draws mainly on open-weights models such as the NVIDIA Nemotron family, assembling an agent team suited to each task's price point. Input and output prices are flat and independent of context length, so a long prompt never moves the row into a more expensive band. For coding, research, and analysis work it is markedly cheaper than Fugu Ultra.
Technical specifications
| Canonical ID | sakana/fugu-max |
|---|---|
| Provider | Sakana AI |
| Context window | 1,000,000 tokens |
| Operations | CHAT_COMPLETIONS, RESPONSES |
| Modalities | text, image |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| CHAT_COMPLETIONS | INPUT_TEXT | PER_1M_TOKENS | $2.00 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.250000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $6.00 |
| RESPONSES | INPUT_TEXT | PER_1M_TOKENS | $2.00 |
| RESPONSES | CACHE_READ | PER_1M_TOKENS | $0.250000 |
| RESPONSES | OUTPUT_TEXT | PER_1M_TOKENS | $6.00 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"sakana/fugu-max","messages":[{"role":"user","content":"Hello"}]}'Related models
- Fugu Ultra sakana/fugu-ultra
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- Trendyol Asure 12B llmtr/trendyol-asure-12b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Muse Glimmer 30B (Turkey) llmtr/muse-glimmer-30b-tr
- EmbeddingGemma 300M llmtr/embeddinggemma-300m
- Qwen 3.5 4B llmtr/qwen3-5-4b