Frontier multimodal coding model with 1M context window and tunable thinking depth
15 providers
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality
6 providers
2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
33 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| MiniMax-M3.1-Flashminimax/MiniMax-M3.1-Flash | MiniMax |
1M | $0.15 | $0.6 | 2026-10-19 | ||
| Ember-1fireworks/ember-1 | Fireworks |
1.04858M | $3 | $15 | 2026-09-22 | ||
| Qwen3.8 Maxalibaba/qwen3.8-max | Alibaba Qwen |
1M | $2 | $6 | 2026-08-03 |