GPT-5.6 Sol vs Fugu Ultra
Side-by-side API pricing and Artificial Analysis performance for GPT-5.6 Sol (OpenAI) and Fugu Ultra (Sakana). Green cells mark the better value in each row.
Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly
| GPT-5.6 Sol OpenAI | Fugu Ultra Sakana | |
|---|---|---|
| Pricing | ||
| Input $/1M | $4.00 | $5.00 |
| Output $/1M | $20.00 | $30.00 |
| Blended $/1M (3:1) | $8.00 | $11.25 |
| RAG example (30K in / 2K out) | $0.16 | $0.21 |
| Quality & speed | ||
| Intelligence Index | — | — |
| Coding Index | 78.3 | — |
| Agentic Index | 47.4 | — |
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Specs | ||
| Context window | 1.05M | 1M |
| Input modalities | file, image, text | text, image |
FAQ
Which is cheaper, GPT-5.6 Sol or Fugu Ultra?
GPT-5.6 Sol has the lower blended API price at $8.00 per 1M tokens (3:1 input:output mix), versus $11.25 for the other model. Prices are live from OpenRouter and refresh nightly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), GPT-5.6 Sol costs about $0.16 per request versus $0.21. Also compare context windows: GPT-5.6 Sol offers 1.05M and Fugu Ultra offers 1M.
Which scores higher on Artificial Analysis benchmarks?
Intelligence Index scores are unavailable or tied for these two models. Compare coding index, speed, and price on this page to decide.