Sakana model
Fugu Ultra v2 API cost calculator
Fugu Ultra v2 costs $5 per 1M input tokens and $30 per 1M output tokens on the Sakana API, with a 1M-token context window. A typical request (2K input, 500 output tokens) costs $0.03 — about $750/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on Fugu Ultra v2
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | $0.01 | $11.50 |
| RAG query with context | 4,000 / 500 | $0.04 | $35.00 |
| Document summarization | 20,000 / 1,000 | $0.13 | $130 |
| Agent coding session | 100,000 / 5,000 | $0.65 | $650 |
Fugu Ultra v2 vs other Sakana models
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Fugu Ultra v2 | $5 | $30 | 1M |
| Fugu Max | $2 | $6 | 1M |
| Sakana Namazu | $0.95 | $4 | 262K |
| Fugu Ultra | $5 | $30 | 1M |
Frequently asked questions
How much does Fugu Ultra v2 cost per 1M tokens?
According to current pricing data, Fugu Ultra v2 costs $5 per 1M input tokens and $30 per 1M output tokens. Processing 1M tokens each way costs $35.00.
What does a typical API request to Fugu Ultra v2 cost?
A typical request with 2,000 input tokens and 500 output tokens costs $0.03. At 1,000 requests per day that is $25.00 daily, or about $750 per month.
What is Fugu Ultra v2's context window?
Fugu Ultra v2 supports a 1M-token context window (1,000,000 tokens).
Does Fugu Ultra v2 support prompt caching?
Yes. Cached input tokens cost $0.50 per 1M — a 90% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to Fugu Ultra v2?
Granite 4.0 Micro from Ibm-granite is currently the cheapest comparable option at $0.02 per 1M input tokens versus $5 for Fugu Ultra v2 — roughly 294x cheaper on input.
Compare all current prices on the live model pricing dashboard, see Fugu Ultra v2 vs Granite 4.0 Micro pricing, or run Fugu Ultra v2 head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.