Mistral 7B Instruct is Mistral AI's language model with a 127K context window and up to 16K output tokens, available from 8 providers, starting at $0.05 / 1M input and $0.1 / 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 · 3 years ago
Deprecation Date
Benchmarks
Intelligence Index
#523
MMLU-Pro
#334
GPQA
#525
HLE
#408
LiveCodeBench
#327
AIME
#182
IFBench
#417
Time to First Token
#344
SciCode
#508
MATH-500
#192
LCR
#449
TAU2
#412
Output TPS
#92

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

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Amazon Bedrock logo
Amazon Bedrock
mistral.mistral-7b-instruct-v0:2
$0.15$0.2
Anyscale logo
Anyscale
anyscale/mistralai/Mistral-7B-Instruct-v0.1
$0.15$0.15
Cloudflare Workers AI logo
Cloudflare Workers AI
@cf/mistral/mistral-7b-instruct-v0.1
$0.11$0.19
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k
$0.2$0.2
OpenRouter logo
OpenRouter
openrouter/mistralai/mistral-7b-instruct
$0.13$0.13
OVHcloud logo
OVHcloud
ovhcloud/Mistral-7B-Instruct-v0.3
$0.1$0.1
Perplexity logo
Perplexity
perplexity/mistral-7b-instruct
$0.07$0.28
Replicate logo
Replicate
replicate/mistralai/mistral-7b-instruct-v0.2
$0.05$0.25

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Mistral 7B Instruct, ranked by cheapest on-demand price. The model needs about 17 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
g2-standard-4GCPnvidia-l424 GB$0.705/hr
g6.xlargeAWSL422 GB$0.805/hr
g2-standard-8GCPnvidia-l424 GB$0.851/hr
7 more instances can run Mistral 7B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

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$2.00Deprecated
Mistral Small 3.2 24B Instruct256K$0.075$0.200Available
Mistral Medium 3262K$0.400$2.00Available
Mistral Small 3.1Available
Mistral Small 3.2131K$0.060$0.180Deprecated
Mistral 7B Instruct127K$0.050$0.100Current

Model IDs

@cf/mistral/mistral-7b-instruct-v0.1
accounts/fireworks/models/mistral-7b-instruct-v0p2
anyscale/mistralai/Mistral-7B-Instruct-v0.1
bedrock/eu-west-3/mistral.mistral-7b-instruct-v0:2
bedrock/us-east-1/mistral.mistral-7b-instruct-v0:2
bedrock/us-west-2/mistral.mistral-7b-instruct-v0:2
cloudflare/@cf/mistral/mistral-7b-instruct-v0.1
fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-4k
fireworks_ai/accounts/fireworks/models/mistral-7b-instruct-v0p2
huggingface-llm-mistral-7b-instruct
huggingface-llmneuron-mistral-7b-instruct
mistral-7b-instruct
mistral.mistral-7b-instruct-v0:2
mistralai/mistral-7b-instruct-v0.1
nebius/intfloat/e5-mistral-7b-instruct
ollama/mistral-7B-Instruct-v0.1
ollama/mistral-7B-Instruct-v0.2
openrouter/mistralai/mistral-7b-instruct
ovhcloud/Mistral-7B-Instruct-v0.3
perplexity/mistral-7b-instruct
replicate/mistralai/mistral-7b-instruct-v0.2
together_ai/mistralai/Mistral-7B-Instruct-v0.1