Fast Gemini model balancing multimodal reasoning, tool use, and cost
31 providers
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Reasoning-first Gemini preview for agentic coding and complex problem solving
Open flagship GLM for long-horizon coding agents and million-token context work
Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks
Default frontier GPT for coding, computer use, research, and knowledge work
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Gemini 3.5 Flashgoogle/gemini-3.5-flash | 83.6 | 1.04858M | $1.5 | $9 | 2026-05-19 | |||
| Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview | 78.2 | 1.04858M | $2 | $12 | 2026-02-19 | |||
| GLM-5.2zhipuai/glm-5.2 | 76.8 | 1M | $1.4 | $4.4 | 2026-06-13 | |||
| Qwen3.7 Maxalibaba/qwen3.7-max | 76.4 | 1M | $2.5 | $7.5 | 2026-05-21 | |||
| GPT-5.5openai/gpt-5.5 | 75.3 | 1.05M | $5 | $30 | 2026-04-23 |