Claude model for creative writing, analysis, and controlled agent workflows
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
More exact GPT-5.4 tier for demanding professional reasoning and agent tasks
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding
Default frontier GPT for coding, computer use, research, and knowledge work
Agent-ready GPT for coding and computer-use workflows at a lower cost
Reasoning-first Gemini preview for agentic coding and complex problem solving
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Strong small GPT for coding subagents, quick tool use, and high-volume work
Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Claude Fable 5anthropic/claude-fable-5 | 64.5 | 1M | $10 | $50 | 2026-06-09 | |||
| GPT-5.4 Proopenai/gpt-5.4-pro | 58.7 | 1.05M | $30 | $180 | 2026-03-05 | |||
| Claude Opus 4.8anthropic/claude-opus-4-8 | 57.9 | 1M | $5 | $25 | 2026-05-28 | |||
| GPT-5.5 Proopenai/gpt-5.5-pro | 57.2 | 1.05M | $30 | $180 | 2026-04-23 | |||
| GPT-5.5openai/gpt-5.5 | 52.2 | 1.05M | $5 | $30 | 2026-04-23 | |||
| GPT-5.4openai/gpt-5.4 | 52.1 | 1.05M | $2.5 | $15 | 2026-03-05 | |||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 44.4 | 1.04858M | $2 | $12 | 2026-02-19 | |||
| Qwen3.7 Maxalibaba/qwen3.7-max | 41.4 | 1M | $2.5 | $7.5 | 2026-05-21 | |||
| Gemini 3.5 Flashgoogle/gemini-3.5-flash | 40.2 | 1.04858M | $1.5 | $9 | 2026-05-19 | |||
| GPT-5.4 miniopenai/gpt-5.4-mini | 28.2 | 400K | $0.75 | $4.5 | 2026-03-17 | |||
| GPT-5.4 nanoopenai/gpt-5.4-nano | 24.3 | 400K | $0.2 | $1.25 | 2026-03-17 |