Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
30 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Deliberate o-series reasoner for hard math, coding, and multi-step analysis
20 providers
Flagship Claude model for deep reasoning, coding, and long-horizon agents
8 providers
O-series reasoning model for hard analysis, math, coding, and planning
16 providers
Smaller o-series reasoner for economical coding, math, and planning tasks
19 providers
Long-lived GPT workhorse for coding, instruction following, and production apps
28 providers
Dense open Qwen model for self-hosted chat, reasoning, and coding
15 providers
Omni-era GPT for multimodal chat, practical coding, and general assistants
23 providers
Small omni GPT for cheap multimodal assistance and production-scale traffic
23 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| GPT-5openai/gpt-5 | OpenAI |
88.0 | 400K | $1.25 | $10 | 2025-08-07 | ||
| o3openai/o3 | OpenAI |
81.3 | 200K | $2 | $8 | 2025-04-16 | ||
| Claude Opus 4anthropic/claude-opus-4-20250514 | Anthropic |
72.0 | 200K | $15 | $75 | 2025-05-22 | ||
| o1openai/o1 | OpenAI |
61.7 | 200K | $15 | $60 | 2024-12-05 | ||
| o3-miniopenai/o3-mini | OpenAI |
60.4 | 200K | $1.1 | $4.4 | 2024-12-20 | ||
| GPT-4.1openai/gpt-4.1 | OpenAI |
52.4 | 1.04758M | $2 | $8 | 2025-04-14 | ||
| Qwen3 32Balibaba/qwen3-32b | Alibaba Qwen |
40.0 | 131.072K | $0.7 | $2.8 | 2025-04 | ||
| GPT-4oopenai/gpt-4o | OpenAI |
23.1 | 128K | $2.5 | $10 | 2024-05-13 | ||
| GPT-4o miniopenai/gpt-4o-mini | OpenAI |
3.6 | 128K | $0.15 | $0.6 | 2024-07-18 |