Codestral 25.08 vs Qwen3 VL 235B A22B Instruct

Price and specs side by side · USD per 1M tokens · verified 2026-11-22

// side by side

metricCodestral 25.08Qwen3 VL 235B A22B Instruct
input / 1M$0.30$0.20
output / 1M$0.90$0.88
blended (3:1)$0.45$0.37
cache read / 1M$0.03$0.11
context256K262.1K
max output8.2K32.8K
input typestext · pdftext · image
reasoningnono
tool callingyesyes
structured outputyesyes
open weightsnoyes
released2025-07-302025-09-23
knowledge cutoffn/a2025-03-31
labMistralAlibaba (Qwen)

// monthly cost scenarios

workloadtokens in / outCodestral 25.08Qwen3 VL 235B A22B Instruct
Chatbot10M / 2M$4.80$3.76
RAG app50M / 5M$19.50$14.40
Coding agent20M / 10M$15.00$12.80

// verdict

// Codestral 25.08 or Qwen3 VL 235B A22B Instruct: which one to choose

// related comparisons

Codestral 25.08 vs GPT-5.6 LunaCodestral 25.08 vs GPT-5.4 nanoCodestral 25.08 vs Qwen3 Omni 30B A3B ThinkingCodestral 25.08 vs DeepSeek-V3.1DeepSeek-V3.1 vs Qwen3 VL 235B A22B InstructGPT-5.6 Luna vs Qwen3 VL 235B A22B InstructGPT-5.4 nano vs Qwen3 VL 235B A22B InstructDeepSeek-V3.2 vs Qwen3 VL 235B A22B Instruct