Arcee AI: Arcee Blitz

Text input Text output Unavailable
Author's Description

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.

Key Specifications
Cost
$$$
Context
32K
Parameters
24B (Rumoured)
Released
May 05, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Logit Bias Response Format Stop Min P Top P Max Tokens Frequency Penalty Temperature Presence Penalty
Features

This model supports the following features:

Response Format
Performance Summary

Arcee Blitz, a 24B-parameter model distilled from DeepSeek and built on Mistral architecture, demonstrates strong performance as a cost-efficient workhorse for everyday chat. It performs among the fastest models, ranking in the top tier for speed (78th percentile across 5 benchmarks), and offers competitive pricing (51st percentile). Notably, Arcee Blitz exhibits exceptional reliability with a 100% success rate across all benchmarks, indicating consistent and usable responses. In terms of specific benchmarks, Arcee Blitz shows solid reasoning capabilities, achieving 97.5% accuracy in General Knowledge and 99.0% in Ethics, both ranking above the 50th percentile. Its performance in Coding is also respectable at 83.0% accuracy. A key strength is its Email Classification, where it achieves 95.0% accuracy and is highlighted as "Most accurate among models this fast," despite a 34th percentile accuracy ranking overall. This suggests a strong balance of speed and accuracy in this specific task. A notable area for improvement is Instruction Following, where it scored 59.2% accuracy, placing it in the 62nd percentile but indicating room for refinement in handling complex, multi-layered instructions. Its competitive throughput and 128k context window make it suitable for summarization and brainstorming.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.45
Completion $0.75

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Together
Together | arcee-ai/arcee-blitz 32K $0.45 / 1M tokens $0.75 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by arcee-ai