Mistral: Models Intelligence, Performance & Price
Analysis of Mistral's models across key metrics including quality, price, output speed, latency, context window & more. This analysis is intended to support you in choosing the best model provided by Mistral for your use-case. For more details including relating to our methodology, see our FAQs. Models analyzed: Pixtral Large, Mistral Large 2 (Nov '24), Mistral Large 2 (Jul '24), Mistral Small 3, Mistral Small (Sep '24), Mixtral 8x22B, Pixtral 12B, Ministral 8B, Mistral NeMo, Ministral 3B, Mixtral 8x7B, Codestral-Mamba, Codestral (Jan '25), Mistral Saba, Mistral Small (Feb '24), Mistral Large (Feb '24), Mistral 7B, Mistral Medium, and Codestral (May '24).
Link:
Mistral Model Comparison Summary
Intelligence: Mistral Large 2 (Nov '24)Ā andĀ Pixtral LargeĀ are the highest quality models offered by Mistral, followed by Mistral Large 2 (Jul '24), Mistral Small 3 & Mistral Saba.Output Speed (tokens/s): Codestral (Jan '25) (209 t/s)Ā andĀ Ministral 8B (141 t/s)Ā are the fastest models offered by Mistral, followed by Ministral 3B, Mistral 7B & Mistral Small (Feb '24).Latency (seconds): Mistral 7B (0.27s)Ā and Ā Codestral (May '24) (0.27s)Ā are the lowest latency models offered by Mistral, followed by Mistral NeMo, Codestral (Jan '25) & Mistral Small (Feb '24).Blended Price ($/M tokens): Ministral 3B ($0.04)Ā andĀ Ministral 8B ($0.10)Ā are the cheapest models offered by Mistral, followed by Mistral Small 3, Pixtral 12B & Mistral NeMo.Context Window Size: Codestral (Jan '25) (256k)Ā andĀ Codestral-Mamba (256k)Ā are the largest context window models offered by Mistral, followed by Mistral Large 2 (Nov '24), Pixtral Large & Mistral Large 2 (Jul '24).
Mistral Large 2 (Nov '24)Ā andĀ Pixtral LargeĀ are the highest quality models offered by Mistral, followed by Mistral Large 2 (Jul '24), Mistral Small 3 & Mistral Saba.Output Speed (tokens/s): Codestral (Jan '25) (209 t/s)Ā andĀ Ministral 8B (141 t/s)Ā are the fastest models offered by Mistral, followed by Ministral 3B, Mistral 7B & Mistral Small (Feb '24).Latency (seconds): Mistral 7B (0.27s)Ā and Ā Codestral (May '24) (0.27s)Ā are the lowest latency models offered by Mistral, followed by Mistral NeMo, Codestral (Jan '25) & Mistral Small (Feb '24).Blended Price ($/M tokens): Ministral 3B ($0.04)Ā andĀ Ministral 8B ($0.10)Ā are the cheapest models offered by Mistral, followed by Mistral Small 3, Pixtral 12B & Mistral NeMo.Context Window Size: Codestral (Jan '25) (256k)Ā andĀ Codestral-Mamba (256k)Ā are the largest context window models offered by Mistral, followed by Mistral Large 2 (Nov '24), Pixtral Large & Mistral Large 2 (Jul '24).Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Features | Model Intelligence | Price | Output tokens/s | Latency | |||
|---|---|---|---|---|---|---|---|
Further Analysis | |||||||
 | Mistral Large 2 (Nov '24) | 128k | 38 | $3.00 | 46.1 | 0.34 | |
| Pixtral Large | 128k | 37 | $3.00 | 35.9 | 0.40 | |
| Mistral Large 2 (Jul '24) | 128k | 37 | $3.00 | 30.7 | 0.38 | |
| Mistral Small 3 | 32k | 35 | $0.15 | 122.4 | 0.30 | |
| Mistral Saba | 32k | 32 | $0.30 | 96.1 | 0.30 | |
| Codestral (Jan '25) | 256k | 28 | $0.45 | 209.1 | 0.28 | |
| Mistral Small (Sep '24) | 33k | 27 | $0.30 | 96.3 | 0.32 | |
| Mistral Large (Feb '24) | 33k | 26 | $6.00 | 36.2 | 0.39 | |
| Mixtral 8x22B | 65k | 26 | $3.00 | 74.2 | 0.28 | |
| Mistral Medium | 33k | 24 | $4.09 | 43.3 | 0.37 | |
| Pixtral 12B | 128k | 23 | $0.15 | 101.5 | 0.30 | |
| Mistral Small (Feb '24) | 33k | 23 | $1.50 | 123.2 | 0.28 | |
| Ministral 8B | 128k | 22 | $0.10 | 141.5 | 0.31 | |
| Codestral (May '24) | 33k | 20 | $0.30 | 83.4 | 0.27 | |
| Ministral 3B | 128k | 20 | $0.04 | 130.5 | 0.29 | |
| Mistral NeMo | 128k | 20 | $0.15 | 116.7 | 0.27 | |
| Codestral-Mamba | 256k | 14 | $0.25 | 95.0 | 0.45 | |
| Mixtral 8x7B | 33k | $0.70 | 99.5 | 0.29 | ||
| Mistral 7B | 8k | $0.25 | 128.4 | 0.27 |
Key definitions
Context window: Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
Output Speed: Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Latency: Time to first token of tokens received, in seconds, after API request sent. For models which do not support streaming, this represents time to receive the completion.
Price: Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Output Price: Price per token generated by the model (received from the API), represented as USD per million Tokens.
Input Price: Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Time period: Metrics are 'live' and are based on the past 72 hours of measurements, measurements are taken 8 times a day for single requests and 2 times per day for parallel requests.