Default frontier GPT for coding, computer use, research, and knowledge work
50 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Strong GLM coding model for agentic engineering, terminals, and repository generation
47 providers
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
69 providers
Reasoning-first Gemini preview for agentic coding and complex problem solving
37 providers
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
47 providers
Prior MiniMax coding model for agent workflows, office edits, and automation
37 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5.5openai/gpt-5.5 | OpenAI |
79.1 | 1.05M | $5 | $30 | 2026-04-23 | ||
| GLM-5.1zhipuai/glm-5.1 | Zhipu AI |
73.2 | 200K | $0.896 | $3.585 | 2026-04-07 | ||
| Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI |
59.8 | 262.144K | $0.95 | $4 | 2026-04-20 | ||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | Google |
45.6 | 1.04858M | $2 | $12 | 2026-02-19 | ||
| Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI |
13.1 | 262.144K | $0.375 | $2 | 2026-01-27 | ||
| MiniMax-M2.5minimax/MiniMax-M2.5 | MiniMax |
10.3 | 204.8K | $0.3 | $1.2 | 2026-02-12 |