Quality-first multi-agent model for hard research, analysis, and competitions
14 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
33 providers
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
34 providers
DeepSeek V4.1 Flash model for reasoning and agentic coding
70 providers
Open MoE flagship with million-token context for coding and long agent runs
71 providers
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
46 providers
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
68 providers
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.
12 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Fugu Ultrasakana/fugu-ultra | Sakana |
95.5 | 1M | $5 | $30 | 2026-06-15 | ||
| Qwen3.8 Maxalibaba/qwen3.8-max | Alibaba Qwen |
92.6 | 1M | $2 | $6 | 2026-08-03 | ||
| Qwen3.7 Maxalibaba/qwen3.7-max | Alibaba Qwen |
92.4 | 1M | $2.5 | $7.5 | 2026-05-21 | ||
| DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek |
90.9 | 1M | $0.02 | $1 | 2026-09-10 | ||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
90.1 | 1M | $0.66 | $1.98 | 2026-04-24 | ||
| Qwen3.8 27Balibaba/qwen3.8-27b | Alibaba Qwen |
89.2 | 262.144K | $0.04 | $1.35 | 2026-08-14 | ||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | DeepSeek |
88.1 | 1M | $0.15 | $0.6 | 2026-04-24 | ||
| Muse Glimmer 30Bmeta/muse-glimmer-30b | Meta |
83.5 | 131.072K | $0.2 | $0.8 | 2026-08-10 |