Umans Flash
Open multimodal Qwen MoE for local agents that need vision, audio, and code
Model facts
- Context window
- 262K tokens
- Maximum output
- 262K tokens
- Cheapest paid input
- $0.15 per 1M tokens
- Cheapest paid output
- $1 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
reasoning, tool calling, structured output, attachments, open weights, text, image.
Observed price history
- 2026-08-24: $0.15 input / $1 output per 1M tokens
API providers
- Umans AI Coding Plan — model id umans-flash; free input / free output per 1M tokens; provider documentation
- Umans AI — model id umans-flash; $0.15 input / $1 output per 1M tokens; provider documentation