MistralOpen SourceSep 28, 2023

Mistral: Mistral 7B Instruct v0.1

A 7.3B parameter model that outperforms Llama 2 13B on all benchmarks, with optimizations for speed and context length.

Context Window
3K
tokens
Max Output
tokens
Released
Sep 28, 2023
Arena Rank

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Frequency Penalty
Reduce repetition
Max Tokens
Output length limit
Presence Penalty
Encourage new topics
Repetition Penalty
Penalize repeated tokens
Seed
Deterministic outputs
Temperature
Controls randomness
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouter$0.11$0.19
Martian$0.11$0.19

Benchmarks

Open LLM Leaderboard
AverageOpen LLM Leaderboard
12.77/100
IFEvalOpen LLM Leaderboard
44.87/100
BBHOpen LLM Leaderboard
7.65/100
MATH Lvl 5Open LLM Leaderboard
2.27/100
GPQAOpen LLM Leaderboard
0/100
MUSROpen LLM Leaderboard
6.13/100
MMLU-PROOpen LLM Leaderboard
15.72/100

Model IDs

OpenRoutermistralai/mistral-7b-instruct-v0.1
Compare with another model

Related Models