token.app › Compare › Codestral 2508 (batch) vs Xing4.0 29B A4B (free)

Codestral 2508 (batch) vs Xing4.0 29B A4B (free)

Xing4.0 29B A4B (free) is free to use, against $0.225 per million tokens. Xing4.0 29B A4B (free) accepts the larger context window (262K).

Head to head
Blended price uses a 3:1 input:output mix
Codestral 2508 (batch)Xing4.0 29B A4B (free)
ProviderMistral AIXingchen agi
Input $/1M$0.150Free
Output $/1M$0.450Free
Blended $/1M$0.225Free
Context window256K262K
Max output205K236K
ReleasedAug 2025Oct 2026
LicenceProprietaryOpen weights
Choose Codestral 2508 (batch) if…
  • No clear advantage on the data we hold.
Choose Xing4.0 29B A4B (free) if…
  • Costs less per token — Free vs $0.225 blended
  • Larger context window (262K)
  • Open weights — self-hostable
  • Newer model (released Oct 2026)
FAQ
Which is better, Codestral 2508 (batch) or Xing4.0 29B A4B (free)?
We do not hold independently-run benchmark scores covering both Codestral 2508 (batch) and Xing4.0 29B A4B (free), so we make no quality claim. Their pricing and specifications are compared on this page.
Is Codestral 2508 (batch) cheaper than Xing4.0 29B A4B (free)?
Xing4.0 29B A4B (free) is cheaper: Free versus $0.225 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs Free. Output alone: $0.450 vs Free.
What context windows do Codestral 2508 (batch) and Xing4.0 29B A4B (free) have?
Codestral 2508 (batch): 256,000 tokens. Xing4.0 29B A4B (free): 262,144 tokens.
Who makes Codestral 2508 (batch) and Xing4.0 29B A4B (free)?
Codestral 2508 (batch) is made by Mistral AI. Xing4.0 29B A4B (free) is made by Xingchen agi.
Related comparisons