Sakana AI / sakana/fugu-ultra
Fugu Ultra - access through LLMTR
Fugu Ultra is Sakana AI's OpenAI-compatible multi-agent reasoning model. It uses a deeper expert-agent pool for hard coding, security analysis, scientific research, and long-context synthesis tasks.
Technical specifications
| Canonical ID | sakana/fugu-ultra |
|---|---|
| Provider | Sakana AI |
| Context window | 1,000,000 tokens |
| Operations | CHAT_COMPLETIONS, RESPONSES |
| Modalities | text, image |
Pricing
A 6% 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 | $5.00 |
| CHAT_COMPLETIONS | CACHE_READ | PER_1M_TOKENS | $0.500000 |
| CHAT_COMPLETIONS | OUTPUT_TEXT | PER_1M_TOKENS | $30.00 |
| RESPONSES | INPUT_TEXT | PER_1M_TOKENS | $5.00 |
| RESPONSES | CACHE_READ | PER_1M_TOKENS | $0.500000 |
| RESPONSES | OUTPUT_TEXT | PER_1M_TOKENS | $30.00 |
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-ultra","messages":[{"role":"user","content":"Hello"}]}'Related models
- Gemma 4 llmtr/gemma-4
- Qwen 3.6 35B-A3B llmtr/qwen3-6-35b
- MedGemma 4B llmtr/medgemma-4b
- Trendyol 7B llmtr/trendyol-7b
- Magibu 11B v8 llmtr/magibu-11b-v8
- Sincap llmtr/sincap
- EmbeddingGemma 300M llmtr/embeddinggemma-300m
- GPT-5.5 openai/gpt-5.5