Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.
Sakana AI文本生成1M 上下文发布日期 2026年6月21日专有端点Original multi-agent conductor for hard reasoning, coding, and research, with 1M context, image input, function calling, and web search.
Supports text and image input, a 1M token context, function calling, JSON mode structured output, and built-in web search. Reasoning is always on with effort levels high, xhigh, and max; xhigh and max are aliases on v1.0. Web search has no separate fee. Full orchestration token usage is billed at the displayed input, output, and cache rates.
也称为 Fugu Ultra, Sakana AI Fugu Ultra v1.0, Fugu-Ultra-v1.0, fugu-ultra-v1-0
fugu-ultra-v1-0/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/fugu-ultra-v1-0:generateContentfugu-ultrafugu-ultra-20260615fugu-ultra-v1.0sakana/fugu-ultrasakana/fugu-ultra-20260615sakana/fugu-ultra-v1-0sakana/fugu-ultra-v1.0来自 EmpirioLabs 目录的实时按量计费价格。只为实际用量付费，没有月度最低消费。
Fugu Ultra v1.0 提供 OpenAI 兼容的 Chat Completions API。用你的 EmpirioLabs API 密钥把任意 OpenAI SDK 指向 https://api.empiriolabs.ai/v1，并使用模型 ID fugu-ultra-v1-0。 在EmpirioLabs 控制台获取 API 密钥。
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fugu-ultra-v1-0",
"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-v1-0",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)EmpirioLabs 上 Fugu Ultra v1.0 API 支持的请求参数。省略字段时使用默认值。
| 参数 | 类型 | 默认值 | 范围 / 值 | 描述 |
|---|---|---|---|---|
| max_tokens | integer | 32768 | 16 到 131072 | Maximum number of output tokens for the final answer. Must be at least 16. The conductor needs room to work, so very small values can truncate or empty the answer. |
| reasoning_effort | enum | high | high, xhigh, max | How hard Fugu Ultra v1.0 reasons. Reasoning is always on. The default is high; xhigh and max are aliases of the same maximum effort. |
| 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 | enum | - | - | Return the output as a valid JSON object (JSON mode). Describe the fields you want in your prompt. |
Fugu Ultra v1.0 is the original multi-agent conductor: each request coordinates a pool of expert models and composes their work into a single answer.
在 EmpirioLabs，Fugu Ultra v1.0 按量计费。本页的实时价格表始终与 API 的实际计费一致。
Fugu Ultra v1.0 支持 1M token 的上下文窗口，每次响应最多 131,072 个输出 token。
兼容。Fugu Ultra v1.0 提供 OpenAI 兼容的 Chat Completions API，现有 OpenAI SDK 只需把 base_url 指向 https://api.empiriolabs.ai/v1 并把模型 ID 设为 fugu-ultra-v1-0 即可使用。
可以。EmpirioLabs Playground在浏览器中以与 API 相同的参数运行 Fugu Ultra v1.0，你可以在写代码之前先测试提示词。
创建 EmpirioLabs 账户，然后在控制台的 API Keys生成密钥。计费使用按量付费的额度，只为实际发出的请求付费。
