token.app › Compare › Mistral Large vs Beam 1.0 501B A23B
Mistral Large vs Beam 1.0 501B A23B
Beam 1.0 501B A23B is 6.9× 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
| Mistral Large | Beam 1.0 501B A23B | |
|---|---|---|
| Provider | Mistral AI | Reflection |
| Input $/1M | $2.00 | $0.250 |
| Output $/1M | $6.00 | $1.00 |
| Blended $/1M | $3.00 | $0.438 |
| Context window | 128K | 1.0M |
| Max output | 102K | 131K |
| Released | Feb 2024 | Oct 2026 |
| Licence | Proprietary | Open weights |
Choose Mistral Large if…
- No clear advantage on the data we hold.
Choose Beam 1.0 501B A23B if…
- Costs less per token — $0.438 vs $3.00 blended
- Larger context window (1.0M)
- Open weights — self-hostable
- Newer model (released Oct 2026)
FAQ
Which is better, Mistral Large or Beam 1.0 501B A23B?
We do not hold independently-run benchmark scores covering both Mistral Large and Beam 1.0 501B A23B, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Mistral Large cheaper than Beam 1.0 501B A23B?
Beam 1.0 501B A23B is cheaper: $0.438 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.250. Output alone: $6.00 vs $1.00.
What context windows do Mistral Large and Beam 1.0 501B A23B have?
Mistral Large: 128,000 tokens. Beam 1.0 501B A23B: 1,048,576 tokens.
Who makes Mistral Large and Beam 1.0 501B A23B?
Mistral Large is made by Mistral AI. Beam 1.0 501B A23B is made by Reflection.