Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for arcee-ai

Arcee AI: Arcee Blitz

arcee-ai/arcee-blitz

Model weights

Arcee Blitz is a 24 B‑parameter dense model distilled from DeepSeek and built on Mistral architecture for "everyday" chat. The distillation‑plus‑refinement pipeline trims compute while keeping DeepSeek‑style reasoning, so Blitz punches above its weight on MMLU, GSM‑8K and BBH compared with other mid‑size open models. With a default 128 k context window and competitive throughput, it serves as a cost‑efficient workhorse for summarization, brainstorming and light code help. Internally, Arcee uses Blitz as the default writer in Conductor pipelines when the heavier Virtuoso line is not required. Users therefore get near‑70 B quality at ~⅓ the latency and price.

Modalities

Context

33K

Released

May 5, 2025

Knowledge Cutoff

Mar 2025

ActivityFAQ

Activity

Token volume and request traffic to this model over time.

About Arcee AI: Arcee Blitz

OpenRouter makes Arcee AI: Arcee Blitz available through a unified, OpenAI-compatible API using the model ID arcee-ai/arcee-blitz.

Arcee AI: Arcee Blitz accepts text and returns text. It has a 32,768-token context window.

It was released on May 5, 2025; its knowledge cutoff is March 31, 2025.

More models from Arcee AI

  • Trinity Large Thinking
  • Virtuoso Large

Frequently asked questions

Arcee Blitz is a 24 B‑parameter dense model distilled from DeepSeek and built on Mistral architecture for "everyday" chat. The distillation‑plus‑refinement pipeline trims compute while keeping DeepSeek‑style reasoning, so Blitz punches above its weight on MMLU, GSM‑8K and BBH compared with other mid‑size open models.

Arcee Blitz has a 32,768 token context window.

Trinity Large Thinking and Virtuoso Large are other text models from Arcee AI.

Arcee Blitz was released on May 5, 2025. Its knowledge cutoff is March 31, 2025.