Mistral 7B Instruct is Mistral AI's language model with a 127K context window and up to 16K output tokens, available from 9 providers, starting at $0.010 / 1M input and $0.100 / 1M output. The instruction-tuned version of Mistral's 7B model, optimized for following natural language instructions and conversational tasks.
Specifications
Canonical IDmistral-7b-instruct
TypeLanguage
StatusDeprecated
CreatorMistral AIMistral AI
Providers
Context Window127K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Parameters7B
HuggingFace Likes1,832
HuggingFace Downloads (30d)418,705
HuggingFace Downloads (all-time)16,849,185
Release Date · 3 years ago
Knowledge Cutoff
Deprecation Date
Benchmarks
Intelligence Index
7.4
#454
MMLU-Pro
0.2
#317
GPQA
0.2
#450
HLE
0.0
#354
LiveCodeBench
0.0
#314
AIME
0.0
#172
IFBench
0.2
#384
Time to First Token
0.35s
#222
SciCode
0.0
#436
MATH-500
0.1
#182
LCR
0.0
#377
TAU2
0.0
#380
Output TPS
104.3
#116

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Cydonia 24B V4.1131K$0.300$0.500Available
Mistral Small 4Available
Mistral Small 4 Non-ReasoningAvailable
Mistral Medium 3.5262K$1.50$7.50Available
Mistral Large 3 675B Instruct128K$0.500$1.50Available
Mistral Medium 3.1131K$0.400$2.00Available
Mistral Small 3.2 24B Instruct128K$0.075$0.200Available
Mistral Medium 3131K$0.400$2.00Available
Mistral Small 3.2131K$0.060$0.180Available
Mistral Small 3.1Available
Mistral 7B Instruct127K$0.010$0.100Current

Model IDs