Fugu Max with Jev
Fugu Max is a model from Sakana, released 2026-09-11. It costs $2.00 per million input tokens and $6.00 per million output tokens, reads up to 1M tokens of context, and writes up to 128,000 tokens in one reply. Through llm11, set model to sakana/fugu-max.
- Input price
- $2.00 / 1M
- Output price
- $6.00 / 1M
- Context window
- 1M tokens
- Max output
- 128K tokens
- Cached input
- $0.250 / 1M
- Released
- 2026-09-11
- Accepts
- text, image, file
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 22% of the 332 priced models we can call cost more.
Using Fugu Max with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Fugu Max does the answering when Jev sends it work, or when you name it yourself. At list price Fugu Max falls in the llm11-balanced band, but no pack routes to it because Sakana is not one of the labs the packs draw from. You can still pin it: pass sakana/fugu-max as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Fugu Max with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00220 | $2.20 |
| Question over retrieved documents | 4,000 / 500 | $0.011 | $11.00 |
| Long document summary | 30,000 / 1,000 | $0.066 | $66.00 |
Cheaper models to try
The catalogue has no benchmark score for Fugu Max, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3.6 Max PreviewRetires 2026-10-09 | $1.03 | $6.16 | 262K | |
| Qwen Qwen3.7 Max | $1.48 | $4.42 | 1M | |
| Anthropic Claude Haiku 4.5 | $1.00 | $5.00 | 200K | |
| OpenAI o4 Mini | $1.10 | $4.40 | 200K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="sakana/fugu-max",
messages=[{"role": "user", "content": "Hello"}],
)More from Sakana
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Fugu Ultra v2 | $5.00 | $30 | 1M | |
| Sakana Namazu | $0.950 | $4.00 | 262K | |
| Fugu Ultra | $5.00 | $30 | 1M |
Questions
- What is Fugu Max with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Fugu Max does the answering when Jev sends it work, or when you name it yourself. At list price Fugu Max falls in the llm11-balanced band, but no pack routes to it because Sakana is not one of the labs the packs draw from. You can still pin it: pass sakana/fugu-max as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Fugu Max a System One model?
- No. Fugu Max answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Fugu Max cost?
- $2.00 per million input tokens and $6.00 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.011, so a thousand of them is about $11.00. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Fugu Max context window?
- 1,000,000 tokens, with up to 128,000 tokens in a single reply.
- Does Fugu Max support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Fugu Max through llm11?
- Yes. Set model to sakana/fugu-max on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Fugu Max?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Fugu Max falls in the llm11-balanced band, but no pack routes to it because Sakana is not one of the labs the packs draw from. You can still pin it: pass sakana/fugu-max as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Fugu Max?
- Nearest in price and below it: Qwen Qwen3.6 Max Preview at $1.03 in and $6.16 out, Qwen Qwen3.7 Max at $1.48 in and $4.42 out and Anthropic Claude Haiku 4.5 at $1.00 in and $5.00 out. The catalogue has no benchmark score for Fugu Max, so this is a price ordering. It does not claim these answer as well.