Mistral 7B Instruct v0.1

Provider: Mistral AI EU

No longer listed on OpenRouter since 2026-05-30. The figures below are the last recorded values.
Input price
$0.11
/ 1M tokens
Output price
$0.19
/ 1M tokens
Context
4K tokens
Max output 3K tokens

Overview

Mistral 7B Instruct v0.1 is a mid-tier instruction-following model from Mistral AI, suitable for general-purpose text generation tasks. It provides a balanced option in terms of pricing and context window compared to the provider's more specialized or flagship offerings.

Strengths

  • Input pricing is competitive with similarly-priced models from other providers.
  • Offers a relatively low output price point compared to many peer models.
  • Designed for reliable instruction-following across various general text tasks.
  • Provides a cost-effective solution for applications not requiring very large contexts.

Best use cases

  • Generating concise responses to direct prompts and instructions.
  • Summarizing short documents or conversations up to 4096 tokens.
  • Implementing chatbots for basic interactions and Q&A systems.
  • Developing applications with moderate context requirements and budget constraints.

Pricing position

At $0.11/M input and $0.19/M output, Mistral 7B Instruct v0.1 is positioned above Mistral Nemo ($0.02/M in) and Mistral Small 3 ($0.05/M in). Its input price is similar to many peers like Qwen3 Coder Next, while its $0.19/M output price is notably lower than many, such as Qwen3 Coder Next ($0.799/M) or Gemma 4 31B ($0.37/M).

Caveats

With a context window of 4096 tokens, this model is not suitable for processing very long documents or complex, extended conversations. Its capabilities are explicitly unknown, meaning developers cannot assume advanced features like vision or complex reasoning. For simpler, more cost-sensitive tasks or those requiring significantly larger contexts, other Mistral models like Nemo or Small 3 might be more appropriate.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Max output
3K tokens
Tracked since
2026-05-08
Last updated
2026-05-30

Features

No information available

Price history

  • 2026-05-30 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.02
1M (small app) 1 0.5 $0.21
10M (mid scale) 10 5 $2.05
100M (large) 100 50 $20.50

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API