多智能体指挥，能够协调前沿专家模型，用于硬推理、编码和研究，支持100万上下文、图像输入和网页搜索。
Sakana AI文本生成1M 上下文发布日期 Jun 21, 2026专有端点新多智能体指挥，能够协调前沿专家模型，用于硬推理、编码和研究，支持100万上下文、图像输入和网页搜索。
支持文本和图像输入、1M令牌上下文、函数调用、JSON模式结构化输出以及内置网页搜索。推理始终开启，努力等级分别为高、xhigh 和 max（xhigh 和 max）最为努力。网络搜索无需额外收费;其成本反映在指挥报告的配器代币使用情况中。编排令牌的输入输出速率与提示和最终答案相同，因此即使是短请求也包含编排费用。
也称为 Sakana AI Fugu Ultra, Fugu-Ultra
fugu-ultraPOST /v1/chat/completionsPOST /v1/responsesPOST /v1/messagesLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Fugu Ultra serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id fugu-ultra. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fugu-ultra",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="fugu-ultra",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Fugu Ultra API on EmpirioLabs. Defaults apply when a field is omitted.
| 参数 | 类型 | 默认 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| max_tokens | integer | 32768 | 1 to 131072 | Maximum number of output tokens for the final answer. The conductor needs room to work, so very small values can return empty output. |
| reasoning_effort | enum | high | high, xhigh, max | How hard Fugu Ultra reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort (more thorough and slower than high). |
| tool_web_search | boolean | false | - | Enable built-in web search. There is no separate fee; the search cost is reflected in the orchestration tokens billed for the request. |
| tools | array | [] | - | OpenAI-compatible function calling tool definitions. |
| tool_choice | object | - | - | OpenAI-compatible tool choice control. |
| response_format | object | - | - | OpenAI-compatible JSON mode for structured output. |
Fugu Ultra 是一个多智能体指挥者：每个请求协调一组专家模型，并将他们的工作整合成一个单一答案。延迟和流式传输 - 复杂提示的响应时间从几秒到几分钟不等。- 模型完成时一次性返回完整答案，而非按标记返回。流式传输是被接受的，但它是在最终交付完整的响应，而不是流式代币生成。- 留出宽裕的余量max_tokens，因为极小的限制可能会截断或清空答案。功能 - 文本和图像输入，带1M令牌上下文。- 永远在场的推理。高为默认;Xhigh和Max是相同的最大努力量。- 函数调用、JSON 模式，以及内置的网页搜索，在有需要时提供来源（无需额外费用）。计费 - 按完整令牌使用计费，包括模型内部使用的编排令牌，因此即使是短提示也会有一定成本。- 上下文分层：总输入令牌数超过272K请求，使用显示的更高速率。
On EmpirioLabs, Fugu Ultra is billed pay as you go: 投入 <=272K $7.50; >272K $15.00 每1M 提示符; 产出 <=272K $45.00; >272K $67.50 每1M个生成的令牌; 隐形缓存已读 <=272K $1.50; >272K $3.00 每1M缓存输入符. The live rate card on this page always matches what the API charges.
Fugu Ultra supports a 1M-token context window with up to 131,072 output tokens per response.
Yes. Fugu Ultra serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to fugu-ultra.
Yes. The EmpirioLabs playground runs Fugu Ultra in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
