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...
14 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
14 providers
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
34 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...
31 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...
32 providers
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
21 providers
Flagship Qwen3 model for coding agents, complex reasoning, and tool use
23 providers
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
16 providers
Classic open reasoning model for transparent math, coding, and deliberate problem solving
16 providers
Hybrid-reasoning GLM release that made the 4.5 line broadly useful
15 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...
9 providers
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
13 providers
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
12 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...
8 providers
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
13 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.
16 providers
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...
6 providers
Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
13 providers
Flagship Mistral model for advanced reasoning, coding, and multilingual work
2 providers
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
29 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...
26 providers
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
19 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Sakana: Fugu Ultrasakana/fugu-ultra | Sakana |
58.7 | 1M | $5 | $30 | 2026-06-15 | ||
| Meta: Muse Spark Openmeta/muse-spark-open | Meta |
58.5 | 1.04858M | $1.25 | $4.25 | 2026-10-15 | ||
| 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 | ||
| Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash | Google |
39.4 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | ||
| GLM-4.6zhipuai/glm-4.6 | Zhipu AI |
38.4 | 204.8K | $0.6 | $2.2 | 2025-09-30 | ||
| Qwen3 Maxalibaba/qwen3-max | Alibaba Qwen |
38.3 | 262.144K | $1.2 | $6 | 2025-09-23 | ||
| Mistral Large 3mistral/mistral-large-2512 | Mistral AI |
36.2 | 262.144K | $0.5 | $1.5 | 2025-12-02 | ||
| DeepSeek-R1deepseek/deepseek-r1 | DeepSeek |
35.7 | 128K | $0.58 | $2.319 | 2025-01-20 | ||
| GLM-4.5zhipuai/glm-4.5 | Zhipu AI |
34.8 | 131.072K | $0.6 | $2.2 | 2025-07-28 | ||
| OpenAI: GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | OpenAI |
33.3 | 128K | $2.5 | $10 | 2024-11-20 | ||
| Devstral 2mistral/devstral-2512 | Mistral AI |
33.1 | 262.144K | $0.4 | $2 | 2025-12-09 | ||
| Mistral Medium 3mistral/mistral-medium-2505 | Mistral AI |
33.1 | 131.072K | $0.4 | $2 | 2025-05-07 | ||
| OpenAI: GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | OpenAI |
33.1 | 128K | $2.5 | $10 | 2024-08-06 | ||
| NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning | NVIDIA |
32.6 | 262.144K | $0.07 | $0.2 | 2026-08-11 | ||
| OpenAI: GPT-4 Turboopenai/gpt-4-turbo | OpenAI |
31.9 | 128K | $10 | $30 | 2023-11-06 | ||
| OpenAI: GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13 | OpenAI |
30.9 | 128K | $5 | $15 | 2024-05-13 | ||
| GLM-4.5-Airzhipuai/glm-4.5-air | Zhipu AI |
30.6 | 131.072K | $0.12 | $0.896 | 2025-07-28 | ||
| Mistral Large 2.1mistral/mistral-large-2411 | Mistral AI |
29.2 | 131.072K | — | — | 2024-11-18 | ||
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | Meta |
26.0 | 128K | $0.1 | $0.32 | 2024-12-06 | ||
| OpenAI: GPT-4o-miniopenai/gpt-4o-mini | OpenAI |
22.9 | 128K | $0.15 | $0.6 | 2024-07-18 | ||
| Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | Google |
19.3 | 1.04858M | $0.1 | $0.4 | 2025-06-17 |