First MoE MiniCPM-V model for single-image, multi-image and video understanding
1 provider
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Compact MiniCPM-V model for single-image, multi-image and video understanding
1 provider
MiMo Flash model for multimodal coding agents and long-context automation
24 providers
Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding
6 providers
Native multimodal GLM model for efficient coding and long-horizon agent tasks
65 providers
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
46 providers
| Model | Creator | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|
| MiniCPM-V 4.7 35B-A3Bopenbmb/minicpm-v-4.7-35b-a3b | 262.144K | — | — | 2026-10-07 | |||
| MiniCPM-V 4.7 1Bopenbmb/minicpm-v-4.7-1b | 262.144K | — | — | 2026-10-06 | |||
| MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | Xiaomi |
1.04858M | $0.14 | $0.28 | 2026-09-22 | ||
| Qwen3.8 Flash Nextalibaba/qwen3.8-flash-next | Alibaba Qwen |
262.144K | $0.1 | $0.2 | 2026-08-27 | ||
| GLM-5.3-Flashzhipuai/glm-5.3-flash | Zhipu AI |
1M | $0.12 | $0.418 | 2026-08-26 | ||
| Qwen3.8 27Balibaba/qwen3.8-27b | Alibaba Qwen |
262.144K | $0.04 | $1.35 | 2026-08-14 |