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...
11 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
31 providers
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
29 providers
Coding-optimized GPT model for repository edits, reviews, and agentic software work
13 providers
Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token....
14 providers
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...
30 providers
StepFun flash model for efficient multimodal reasoning, coding, and tool use
6 providers
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
20 providers
The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...
8 providers
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4o ("o" for "omni") is...
7 providers
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
10 providers
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
15 providers
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
23 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Sakana: Fugu Ultrasakana/fugu-ultra | Sakana |
58.7 | 1M | $5 | $30 | 2026-06-15 | ||
| Qwen3.7 Maxalibaba/qwen3.7-max | Alibaba Qwen |
53.5 | 1M | $2.5 | $7.5 | 2026-05-21 | ||
| Google: Gemini 2.5 Progoogle/gemini-2.5-pro | Google |
42.8 | 1.04858M | $1.25 | $10 | 2025-06-17 | ||
| GPT-5-Codexopenai/gpt-5-codex | OpenAI |
40.9 | 400K | $1.1 | $9 | 2025-09-15 | ||
| StepFun: Step 3.5 Flashstepfun/step-3.5-flash | StepFun |
40.4 | 262.144K | $0.1 | $0.3 | 2026-01-29 | ||
| Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
39.4 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | ||
| Step 3.5 Flash 2603stepfun/step-3.5-flash-2603 | StepFun |
38.5 | 256K | $0.1 | $0.3 | 2026-04-02 | ||
| Qwen3 Maxalibaba/qwen3-max | Alibaba Qwen |
38.3 | 262.144K | $1.2 | $6 | 2025-09-23 | ||
| OpenAI: GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI |
33.3 | 128K | $2.5 | $10 | 2024-11-20 | ||
| OpenAI: GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | OpenAI |
33.1 | 128K | $2.5 | $10 | 2024-08-06 | ||
| Mistral Medium 3mistral/mistral-medium-2505 | Mistral AI |
33.1 | 131.072K | $0.4 | $2 | 2025-05-07 | ||
| OpenAI: GPT-4 Turboopenai/gpt-4-turbo | OpenAI |
31.9 | 128K | $10 | $30 | 2023-11-06 | ||
| OpenAI: GPT-4o-miniopenai/gpt-4o-mini | OpenAI |
22.9 | 128K | $0.15 | $0.6 | 2024-07-18 |