Quality-first multi-agent model for hard research, analysis, and competitions
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.
Google's proven reasoning model for coding, math, and multimodal analysis
Coding-optimized GPT model for repository edits, reviews, and agentic software work
Fast Gemini workhorse for multimodal apps where latency and price matter
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Mistral model for multilingual chat, reasoning, and tool-assisted workflows
GPT model for general reasoning, writing, coding, and tool-assisted tasks
Compact GPT model for low-latency assistance and high-volume workloads
Small omni GPT for cheap multimodal assistance and production-scale traffic
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Fugu Ultrasakana/fugu-ultra | 58.7 | 1M | $5 | $30 | 2026-06-15 | |||
| Muse Spark Openmeta/muse-spark-open | 58.5 | 1.04858M | $1.25 | $4.25 | 2026-10-15 | |||
| Gemini 2.5 Progoogle/gemini-2.5-pro | 42.8 | 1.04858M | $1.25 | $10 | 2025-06-17 | |||
| GPT-5-Codexopenai/gpt-5-codex | 40.9 | 400K | $1.1 | $9 | 2025-09-15 | |||
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | 39.4 | 1.04858M | $0.3 | $2.5 | 2025-06-17 | |||
| GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20 | 33.3 | 128K | $2.5 | $10 | 2024-11-20 | |||
| Mistral Medium 3mistral/mistral-medium-2505 | 33.1 | 131.072K | $0.4 | $2 | 2025-05-07 | |||
| GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06 | 33.1 | 128K | $2.5 | $10 | 2024-08-06 | |||
| GPT-4 Turboopenai/gpt-4-turbo | 31.9 | 128K | $10 | $30 | 2023-11-06 | |||
| GPT-4o miniopenai/gpt-4o-mini | 22.9 | 128K | $0.15 | $0.6 | 2024-07-18 |