token.app › Compare › Mistral Small 3.2 24B vs Beam 1.0 501B A23B

Mistral Small 3.2 24B vs Beam 1.0 501B A23B

Mistral Small 3.2 24B is 3.3× 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
Mistral Small 3.2 24BBeam 1.0 501B A23B
ProviderMistral AIReflection
Input $/1M$0.094$0.250
Output $/1M$0.250$1.00
Blended $/1M$0.133$0.438
Context window256K1.0M
Max output16K131K
ReleasedJun 2025Oct 2026
LicenceOpen weightsOpen weights
Choose Mistral Small 3.2 24B if…
  • Costs less per token — $0.133 vs $0.438 blended
Choose Beam 1.0 501B A23B if…
  • Larger context window (1.0M)
  • Newer model (released Oct 2026)
FAQ
Which is better, Mistral Small 3.2 24B or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both Mistral Small 3.2 24B and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Mistral Small 3.2 24B cheaper than Beam 1.0 501B A23B?
Mistral Small 3.2 24B is cheaper: $0.133 versus $0.438 per million tokens blended at 3:1 input:output. Input alone: $0.094 vs $0.250. Output alone: $0.250 vs $1.00.
What context windows do Mistral Small 3.2 24B and Beam 1.0 501B A23B have?
Mistral Small 3.2 24B: 256,000 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes Mistral Small 3.2 24B and Beam 1.0 501B A23B?
Mistral Small 3.2 24B is made by Mistral AI. Beam 1.0 501B A23B is made by Reflection.
Related comparisons
Mistral Small 3.2 24B full details Beam 1.0 501B A23B full details Mistral Small 3.2 24B vs Flint (free) Mistral Small 3.2 24B vs MiniMax M3.1 Flash (free) Mistral Small 3.2 24B vs DeepSeek V4.1 Flash 1017 Mistral Small 3.2 24B vs Glimpse Mistral Small 3.2 24B vs Xing4.0 29B A4B (free) Mistral Small 3.2 24B vs Mercury 3