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.
Agent-ready GPT for coding and computer-use workflows at a lower cost
46 providers
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
34 providers
Open MoE flagship with million-token context for coding and long agent runs
71 providers
Open MiMo model for multimodal coding agents and long-context automation
27 providers
Strong small GPT for coding subagents, quick tool use, and high-volume work
35 providers
Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work
68 providers
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation
30 providers
Agentic coding model from Poolside in the XS size class for local deployment
6 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5.5openai/gpt-5.5 | OpenAI |
82.7 | 1.05M | $5 | $30 | 2026-04-23 | ||
| GPT-5.4openai/gpt-5.4 | OpenAI |
75.1 | 1.05M | $2.5 | $15 | 2026-03-05 | ||
| Qwen3.7 Maxalibaba/qwen3.7-max | Alibaba Qwen |
69.7 | 1M | $2.5 | $7.5 | 2026-05-21 | ||
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek |
67.9 | 1M | $0.66 | $1.98 | 2026-04-24 | ||
| MiMo-V2.5xiaomi/mimo-v2.5 | Xiaomi |
65.8 | 1.04858M | $0.14 | $0.28 | 2026-04-22 | ||
| GPT-5.4 miniopenai/gpt-5.4-mini | OpenAI |
60.0 | 400K | $0.75 | $4.5 | 2026-03-17 | ||
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | DeepSeek |
56.9 | 1M | $0.15 | $0.6 | 2026-04-24 | ||
| GPT-5.4 nanoopenai/gpt-5.4-nano | OpenAI |
46.3 | 400K | $0.2 | $1.25 | 2026-03-17 | ||
| Laguna XS 2.1poolside/laguna-xs-2.1 | Poolside |
37.5 | 262.144K | $0.06 | $0.12 | 2026-07-02 |