Skip to content

Model Library

MistralReleased February 26, 2024

Mistral Small (Feb)

Mistral · Released February 26, 2024

View public research Browse the library

Intelligence score

4

At a glance

Intelligence
4
Speed
167.4tokens/sec
Latency
750mstime to first token
Input price
$1.00per 1M tokens
Output price
$3.00per 1M tokens
Context window
33Ktokens
Parameters
—

Summary

Comparison summary

Mistral Small (Feb '24) scores 4 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other non-reasoning models in a similar price tier (median: 17). Mistral Small (Feb '24) generates output at 167.4 tokens per second (based on Mistral's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 61.7 t/s). Mistral Small (Feb '24) costs $1.00 per 1M input tokens (very competitive, median: $1.88) and $3.00 per 1M output tokens (very competitive, median: $7.75), based on Mistral's API.

Specifications

Technical specifications

Model nameMistral Small (Feb)
ProviderMistral
Release dateFebruary 26, 2024
Intelligence score4
Speed167.4 tokens/sec
Latency (TTFT)0.75s
Input price$1.00 / 1M tokens
Output price$3.00 / 1M tokens
Context window33,000 tokens
Parameters—
ReasoningNo
Input modalitiestext
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: mistral-small-2402

Pricing

Token prices

Price per 1M tokens

Mistral Small (Feb), as listed in the catalog record

Input $1.00 and output $3.00 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$1.00
  2. Output$3.00

Model Intelligence legacy profile: mistral-small-2402

FAQ · 18

Frequently asked questions

Mistral Small (Feb '24) was released on February 26, 2024.

Mistral Small (Feb '24) was created by Mistral.

Mistral Small (Feb '24) scores 4 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other non-reasoning models in a similar price tier (median: 17).

Mistral Small (Feb '24) generates output at 167.4 tokens per second (based on Mistral's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 61.7 t/s).

Mistral Small (Feb '24) has a time to first token (TTFT) of 0.75s (based on Mistral's API), which is very competitive compared to other non-reasoning models in a similar price tier (median: 1.57s).

Mistral Small (Feb '24) costs $1.00 per 1M input tokens (very competitive, median: $1.88) and $3.00 per 1M output tokens (very competitive, median: $7.75), based on Mistral's API.

Mistral Small (Feb '24) costs $1.00 per 1M input tokens and $3.00 per 1M output tokens (based on Mistral's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.20 per 1M tokens. Pricing may vary by provider.

No, Mistral Small (Feb '24) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Mistral Small (Feb '24) supports text only input.

Mistral Small (Feb '24) supports text only output.

No, Mistral Small (Feb '24) does not support image input. It can only process text.

No, Mistral Small (Feb '24) is not multimodal. It only supports text only input.

Mistral Small (Feb '24) has a context window of 33k tokens. This determines how much text and conversation history the model can process in a single request.

No, Mistral Small (Feb '24) is proprietary. The model weights are not publicly available.

Mistral Small (Feb '24) is a proprietary model and Mistral has not disclosed the model size or parameter count.

Mistral Small (Feb '24) achieves a score of 4 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Mistral Small (Feb '24) is available via API through 1 provider.

Mistral Small (Feb '24) is available through 1 API provider.