--- title: Sakana: Fugu Ultra API | Text Generation | ModelsLab description: Build with Sakana: Fugu Ultra API by Sakana. Text generation, chat, code, and reasoning. Pay-per-use. Free tier. url: https://modelslab.com/models/sakana/sakana-fugu-ultra.md canonical: https://modelslab.com/models/sakana/sakana-fugu-ultra.md type: product component: Playground/LLM/Index generated_at: 2026-06-24T14:14:13.703892Z --- Sakana: Fugu Ultra --- [LLMs.txt](https://modelslab.com/models/open_router/sakana-fugu-ultra/llms.txt) [.md](https://modelslab.com/models/sakana/sakana-fugu-ultra.md) Sakana: Fugu Ultra --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### Sakana: Fugu Ultra sakana sakana-fugu-ultra Copy model ID PricingInput $5.00 / 1M tokens Output $30.00 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [#### open\_router/Qwen: Qwen3 Max qwen-qwen3-max From $2.34/M tokens](https://modelslab.com/models/open_router/qwen-qwen3-max) [#### open\_router/Mistral: Mistral Large 3 2512 mistralai-mistral-large-2512 From $1.00/M tokens](https://modelslab.com/models/open_router/mistralai-mistral-large-2512) [#### open\_router/Amazon: Nova 2 Lite amazon-nova-2-lite-v1 From $1.40/M tokens](https://modelslab.com/models/open_router/amazon-nova-2-lite-v1) [#### perplexity\_ai/R1 1776 perplexity-ai-r1-1776 From $8.40/M tokens](https://modelslab.com/models/perplexity_ai/perplexity-ai-r1-1776) [#### open\_router/IBM: Granite 4.0 Micro ibm-granite-granite-4.0-h-micro From $0.06/M tokens](https://modelslab.com/models/open_router/ibm-granite-granite-4.0-h-micro) [#### openai/GPT OSS 120b gpt-oss-120b From $0.11/M tokens](https://modelslab.com/models/openai/gpt-oss-120b) [#### open\_router/Qwen: Qwen3.7 Max qwen-qwen3.7-max From $2.50/M tokens](https://modelslab.com/models/open_router/qwen-qwen3.7-max) [#### qwen/Qwen2.5-VL (72B) Instruct Qwen-Qwen2.5-VL-72B-Instruct From $4.97/M tokens](https://modelslab.com/models/qwen/Qwen-Qwen2.5-VL-72B-Instruct) [#### together\_ai/OpenAI GPT-OSS 120B openai-gpt-oss-120b From $0.11/M tokens](https://modelslab.com/models/together_ai/openai-gpt-oss-120b) [#### open\_router/Nous: Hermes 3 405B Instruct nousresearch-hermes-3-llama-3.1-405b From $1.00/M tokens](https://modelslab.com/models/open_router/nousresearch-hermes-3-llama-3.1-405b) [#### meta/Llama 4 Maverick Instruct (17Bx128E) meta-llama-Llama-4-Maverick-17B-128E-Instruct-FP8 From $0.56/M tokens](https://modelslab.com/models/meta/meta-llama-Llama-4-Maverick-17B-128E-Instruct-FP8) [#### open\_router/Mistral: Codestral 2508 mistralai-codestral-2508 From $0.60/M tokens](https://modelslab.com/models/open_router/mistralai-codestral-2508) [#### arcee\_ai/Arcee AI Spotlight arcee\_ai-arcee-spotlight From $0.22/M tokens](https://modelslab.com/models/arcee_ai/arcee_ai-arcee-spotlight) [#### open\_router/Reka Edge rekaai-reka-edge From $0.10/M tokens](https://modelslab.com/models/open_router/rekaai-reka-edge) [#### open\_router/Anthropic: Claude Opus 4.8 (Fast) anthropic-claude-opus-4.8-fast From $30.00/M tokens](https://modelslab.com/models/open_router/anthropic-claude-opus-4.8-fast) [#### open\_router/Qwen: Qwen3 Coder Plus qwen-qwen3-coder-plus From $1.95/M tokens](https://modelslab.com/models/open_router/qwen-qwen3-coder-plus) [#### open\_router/Meta: Llama 4 Maverick meta-llama-llama-4-maverick From $0.38/M tokens](https://modelslab.com/models/open_router/meta-llama-llama-4-maverick) [#### open\_router/Relace: Relace Search relace-relace-search From $2.00/M tokens](https://modelslab.com/models/open_router/relace-relace-search) Open Source Alternatives --- Explore open-source models that offer similar capabilities with full transparency and flexibility [View all open source models](https://modelslab.com/models?feature=llm&provider=open-source-models) [MU Popular](https://modelslab.com/models/modelslab/uncensored-chat)[ModelsLab](https://modelslab.com/models/modelslab) [Modelslab: Uncensored Chat Open Source Model](https://modelslab.com/models/modelslab/uncensored-chat) About Sakana: Fugu Ultra --- Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route... ### Technical Specifications Model IDsakana-fugu-ultra CategoryLLM Models TaskText Generation Price$17.5 per million tokens AddedJune 24, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate Sakana: Fugu Ultra into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "sakana-fugu-ultra", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` ### Pricing Sakana: Fugu Ultra API costs $17.500000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Sakana](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Sakana: Fugu Ultra FAQ --- ### What is Sakana: Fugu Ultra? Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route... ### How do I use the Sakana: Fugu Ultra API? You can integrate Sakana: Fugu Ultra into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "sakana-fugu-ultra" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Sakana: Fugu Ultra cost? Sakana: Fugu Ultra costs $17.500000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Sakana: Fugu Ultra model ID? The model ID for Sakana: Fugu Ultra is "sakana-fugu-ultra". Use this ID in your API requests to specify this model. ### Does Sakana: Fugu Ultra have a free tier? Yes, ModelsLab offers a free tier that lets you try Sakana: Fugu Ultra and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-06-24*