# Maxwell V1.0 Flash

> Maxwell V1.0 Flash is the Maxwell team's open-weight 35B/3B-active sparse MoE with a 256K-token context. It returns text for agentic work, grounded research and software engineering. Listed as upcoming.

**ID**: `maxwell-model/maxwell-v1-flash`  
**Creator**: maxwell-model  
**Category**: text  
**Context**: 262K tokens  
**Status**: Coming soon — announced, not yet routable on AnyRouter; requests return 404 `model_not_yet_available`.  
**Note**: Coming soon. The Maxwell team published Apache-2.0 weights on 2026-11-13; no inference API with published token prices serves them yet. We will list prices and route requests once a host does.  
**Pricing**: Not published yet  
**Released**: 2026-11-13  
**Links**: [Weights on Hugging Face](https://huggingface.co/maxwell-model/Maxwell-V1-Flash) · [Announcement](https://x.com/TeksEdge/status/2122481090250313747)  
**Web page**: https://anyrouter.dev/model/maxwell-model/maxwell-v1-flash

**Input modalities**: text  
**Output modalities**: text  

**Capabilities**: chat, function-calling, reasoning

**Aliases**: `maxwell/maxwell-v1-flash`, `maxwell-model/Maxwell-V1-Flash`
