Skip to content

Model Library

MistralReleased September 27, 2023

Mistral 7B

Mistral · Released September 27, 2023

View public research Browse the library

Intelligence score

2

At a glance

Intelligence
2
Speed
97.5tokens/sec
Latency
830mstime to first token
Input price
$0.25per 1M tokens
Output price
$0.25per 1M tokens
Context window
7tokens
Parameters
7billions

Summary

Comparison summary

Mistral 7B Instruct scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6). Mistral 7B Instruct generates output at 97.5 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Mistral 7B Instruct costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.25 per 1M output tokens (better than average, median: $0.32), based on Mistral's API.

Specifications

Technical specifications

Model nameMistral 7B
ProviderMistral
Release dateSeptember 27, 2023
Intelligence score2
Speed97.5 tokens/sec
Latency (TTFT)0.83s
Input price$0.25 / 1M tokens
Output price$0.25 / 1M tokens
Context window7 tokens
Parameters7B
ReasoningNo
Input modalitiestext
Output modalities—
Open weightsYes
LicenseApache 2
API availability—
SourceModel Intelligence legacy profile: mistral-7b-instruct

Pricing

Token prices

Price per 1M tokens

Mistral 7B, as listed in the catalog record

Input $0.25 and output $0.25 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.25
  2. Output$0.25

Model Intelligence legacy profile: mistral-7b-instruct

FAQ · 19

Frequently asked questions

Mistral 7B Instruct was released on September 27, 2023.

Mistral 7B Instruct was created by Mistral.

Mistral 7B Instruct scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 6).

Mistral 7B Instruct generates output at 97.5 tokens per second (based on Mistral's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).

Mistral 7B Instruct has a time to first token (TTFT) of 0.83s (based on Mistral's API), which is very competitive compared to other open weight non-reasoning models of similar size (median: 1.54s).

Mistral 7B Instruct costs $0.25 per 1M input tokens (somewhat higher than average, median: $0.15) and $0.25 per 1M output tokens (better than average, median: $0.32), based on Mistral's API.

Mistral 7B Instruct costs $0.25 per 1M input tokens and $0.25 per 1M output tokens (based on Mistral's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.25 per 1M tokens. Pricing may vary by provider.

No, Mistral 7B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Mistral 7B Instruct supports text only input.

Mistral 7B Instruct supports text only output.

No, Mistral 7B Instruct does not support image input. It can only process text.

No, Mistral 7B Instruct is not multimodal. It only supports text only input.

Mistral 7B Instruct has a context window of 8.2k tokens. This determines how much text and conversation history the model can process in a single request.

Yes, Mistral 7B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.

Mistral 7B Instruct has 7 billion parameters.

Mistral 7B Instruct is released under the Apache 2.0 license. This license allows commercial use.

Mistral 7B Instruct achieves a score of 2 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Mistral 7B Instruct is available via API through 2 providers.

Mistral 7B Instruct is available through 2 API providers.