Mistral AI models on Amazon Bedrock
14 Mistral AI models available through Bedrock, with price per 1M tokens, context window and region coverage.
| Model | Context | Input | Output | Regions |
|---|---|---|---|---|
| Devstral 2 123B mistral.devstral-2-123b | — | — | — | On-demand 11 Inference profile only 0 |
| Magistral Small 2509 mistral.magistral-small-2509 | — | $0.500 | $1.50 | On-demand 9 Inference profile only 0 |
| Ministral 14B 3.0 mistral.ministral-3-14b-instruct | — | $0.200 | $0.200 | On-demand 9 Inference profile only 0 |
| Ministral 3 8B mistral.ministral-3-8b-instruct | — | $0.150 | $0.150 | On-demand 9 Inference profile only 0 |
| Ministral 3B mistral.ministral-3-3b-instruct | — | $0.100 | $0.100 | On-demand 9 Inference profile only 0 |
| Mistral 7B Instruct mistral.mistral-7b-instruct-v0:2 | 32K | $0.150 | $0.200 | On-demand 9 Inference profile only 0 |
| Mistral Large (24.02) mistral.mistral-large-2402-v1:0 | 32K | $4.00 | $12.00 | On-demand 9 Inference profile only 0 |
| Mistral Large (24.07) mistral.mistral-large-2407-v1:0 | 128K | $2.00 | $6.00 | On-demand 1 Inference profile only 0 |
| Mistral Large 3 mistral.mistral-large-3-675b-instruct | — | $0.500 | $1.50 | On-demand 7 Inference profile only 0 |
| Mistral Small (24.02) mistral.mistral-small-2402-v1:0 | 32K | $1.00 | $3.00 | On-demand 1 Inference profile only 0 |
| Mixtral 8x7B Instruct mistral.mixtral-8x7b-instruct-v0:1 | 32K | $0.450 | $0.700 | On-demand 9 Inference profile only 0 |
| Pixtral Large (25.02) mistral.pixtral-large-2502-v1:0 | — | $2.00 | $6.00 | On-demand 0 Inference profile only 7 |
| Voxtral Mini 3B 2507 mistral.voxtral-mini-3b-2507 | — | $0.040 | $0.040 | On-demand 9 Inference profile only 0 |
| Voxtral Small 24B 2507 mistral.voxtral-small-24b-2507 | — | — | — | On-demand 9 Inference profile only 0 |
Common questions
- Which Mistral AI model is cheapest on Amazon Bedrock?
- Voxtral Mini 3B 2507 at $0.040 per 1M input tokens in us-east-1, against $0.040 per 1M output tokens.
- Which Mistral AI model is available in the most AWS regions?
- Devstral 2 123B, callable in 11 of the 16 regions tracked here — 11 on-demand and 0 through a cross-region inference profile.
- Which Mistral AI model has the largest context window on Bedrock?
- Mistral Large (24.07), with a 128K-token context window.