token.app › Compare › Codestral 2508 (batch) vs Beam 1.0 501B A23B

Codestral 2508 (batch) vs Beam 1.0 501B A23B

Codestral 2508 (batch) is 1.9× cheaper per token on a blended 3:1 basis. Beam 1.0 501B A23B accepts the larger context window (1.0M).

Head to head
Blended price uses a 3:1 input:output mix
Codestral 2508 (batch)Beam 1.0 501B A23B
ProviderMistral AIReflection
Input $/1M$0.150$0.250
Output $/1M$0.450$1.00
Blended $/1M$0.225$0.438
Context window256K1.0M
Max output205K131K
ReleasedAug 2025Oct 2026
LicenceProprietaryOpen weights
Choose Codestral 2508 (batch) if…
  • Costs less per token — $0.225 vs $0.438 blended
Choose Beam 1.0 501B A23B if…
  • Larger context window (1.0M)
  • Open weights — self-hostable
  • Newer model (released Oct 2026)
FAQ
Which is better, Codestral 2508 (batch) or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both Codestral 2508 (batch) and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Codestral 2508 (batch) cheaper than Beam 1.0 501B A23B?
Codestral 2508 (batch) is cheaper: $0.225 versus $0.438 per million tokens blended at 3:1 input:output. Input alone: $0.150 vs $0.250. Output alone: $0.450 vs $1.00.
What context windows do Codestral 2508 (batch) and Beam 1.0 501B A23B have?
Codestral 2508 (batch): 256,000 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes Codestral 2508 (batch) and Beam 1.0 501B A23B?
Codestral 2508 (batch) is made by Mistral AI. Beam 1.0 501B A23B is made by Reflection.
Related comparisons
Codestral 2508 (batch) full details Beam 1.0 501B A23B full details Codestral 2508 (batch) vs Flint (free) Codestral 2508 (batch) vs MiniMax M3.1 Flash (free) Codestral 2508 (batch) vs DeepSeek V4.1 Flash 1017 Codestral 2508 (batch) vs Glimpse Codestral 2508 (batch) vs Xing4.0 29B A4B (free) Codestral 2508 (batch) vs Mercury 3