Sakana Namazu API: toman pricing and code

What is Sakana Namazu good for?

Sakana Namazu is one of Sakana's models. Put "sakana/sakana-namazu" in the model field and the rest of your code stays as it is. Sakana Namazu keeps 262,144 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 65,536 tokens. On price it sits in the "mid-range" band — cheaper than 265 and dearer than 141 of the other paid models in the catalogue.

What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; it takes files such as PDFs as input; it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

Input runs at 275,619 toman per 1M tokens and output at 1,160,500 — output costs 4.2× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 43,519 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is Kimi K2.6: Sakana Namazu works out roughly 1× more expensive, and its context window is the same size. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 54 thousand-word requests on Sakana Namazu, and every 1,000 toman is about 536 words of round trip. A job with one million input tokens and one million output tokens comes to 1,436,119 toman in total. Filling this model's 262,144-token window costs 72,252 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "sakana/fugu-ultra", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 7.1× cheaper (1,867 against 13,201 toman). The context windows differ too: 262,144 against 1,000,000 tokens. Maximum answer length differs as well: 65,536 against 128,000 tokens.

Sakana has 2 models in our catalogue; the cheapest is Sakana Namazu at 1,867 toman per thousand words and the dearest Fugu Ultra at 13,201. Among the less common parameters it accepts reasoning_effort, web_search_options — all through the standard request body. It does not support max_tokens, response_format, temperature, top_p, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Trinity Large Thinking at 262,144 tokens.

Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, pulling text and fields out of images, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.