Mistral: Mistral 7B Instruct v0.2

mistralai/mistral-7b-instruct-v0.2

Created Dec 28, 202332,768 context
$0.20/M input tokens$0.20/M output tokens

A high-performing, industry-standard 7.3B parameter model, with optimizations for speed and context length.

An improved version of Mistral 7B Instruct, with the following changes:

  • 32k context window (vs 8k context in v0.1)
  • Rope-theta = 1e6
  • No Sliding-Window Attention

Providers for Mistral 7B Instruct v0.2

OpenRouter routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

Context
33K
Max Output
33K
Input
$0.20
Output
$0.20

Apps using Mistral 7B Instruct v0.2

Top public apps this week using this model

1.
Open WebUI
Extensible, self-hosted AI interface
382Ktokens
2.
Cline
Autonomous coding agent right in your IDE
244Ktokens
3.
85Ktokens
4.
OpenRouter: Chatroom
Chat with multiple LLMs at once
74Ktokens
6.
37Ktokens
7.
Chub AI
GenAI for everyone
31Ktokens
8.
RisuAI
Browse characters, choose models, and chat
28Ktokens
9.
25Ktokens
10.
13Ktokens
11.
Mantella
Skyrim & Fallout 4 mod, naturally speak to NPCs
8Ktokens
15.
BotHub
Multi-model ChatGPT
1Ktokens
16.
1Ktokens
18.
985tokens
19.
964tokens

Recent activity on Mistral 7B Instruct v0.2

Tokens processed per day

Apr 25May 2May 9May 16May 23May 30Jun 6Jun 13Jun 20Jun 27Jul 4Jul 11Jul 1825M50M75M100M

Versions by Token Share

Jul 17Jul 18Jul 19Jul 20Jul 21Jul 22Jul 23Jul 2430%60%100%
Mistral: Mistral 7B Instruct v0.3
Created May 27, 202432,768 context
58.8M tokens
Mistral: Mistral 7B Instruct
Created May 27, 202432,768 context
733M tokens
Currently Viewing
Mistral: Mistral 7B Instruct v0.2
Created December 28, 202332,768 context
26.7M tokens
Mistral: Mistral 7B Instruct v0.1
Created September 28, 20234,096 context
2.48M tokens

Uptime stats for Mistral 7B Instruct v0.2

Uptime stats for Mistral 7B Instruct v0.2 on the only provider

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it.

Learn more about our load balancing and customization options.

Sample code and API for Mistral 7B Instruct v0.2

OpenRouter normalizes requests and responses across providers for you.

OpenRouter provides an OpenAI-compatible completion API to 400+ models & providers that you can call directly, or using the OpenAI SDK. Additionally, some third-party SDKs are available.

In the examples below, the OpenRouter-specific headers are optional. Setting them allows your app to appear on the OpenRouter leaderboards.

from openai import OpenAI

client = OpenAI(
  base_url="https://openrouter.ai/api/v1",
  api_key="<OPENROUTER_API_KEY>",
)

completion = client.chat.completions.create(
  extra_headers={
    "HTTP-Referer": "<YOUR_SITE_URL>", # Optional. Site URL for rankings on openrouter.ai.
    "X-Title": "<YOUR_SITE_NAME>", # Optional. Site title for rankings on openrouter.ai.
  },
  extra_body={},
  model="mistralai/mistral-7b-instruct-v0.2",
  messages=[
    {
      "role": "user",
      "content": "What is the meaning of life?"
    }
  ]
)
print(completion.choices[0].message.content)

Using third-party SDKs

For information about using third-party SDKs and frameworks with OpenRouter, please see our frameworks documentation.

See the Request docs for all possible fields, and Parameters for explanations of specific sampling parameters.

More models from Mistral AI

    Mistral 7B Instruct v0.2 - API, Providers, Stats | OpenRouter