Mixtral 8x7B Instruct is Mistral AI's language model with a 33K context window and up to 16K output tokens, available from 8 providers, starting at $0.07 / 1M input and $0.15 / 1M output. Instruction-tuned variant of the Mixtral 8x7B MoE model, optimized for following user instructions and conversational tasks.
Specifications
Canonical IDmistral-mixtral-8x7b-instruct
TypeLanguage
StatusDeprecated
CreatorMistral AIMistral AI
Providers
Context Window33K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Parameters7B
Release Date · 3 years ago
Knowledge Cutoff · 3 years ago
Deprecation Date
Benchmarks
Intelligence Index
#539
MMLU-Pro
#317
GPQA
#502
HLE
#420
LiveCodeBench
#322
AIME
#184
Time to First Token
#435
SciCode
#534
MATH-500
#183
Output TPS
#242

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
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.mixtral-8x7b-instruct-v0:1
$0.45$0.7
Anyscale logo
Anyscale
anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1
$0.15$0.15
DeepInfra logo
DeepInfra
deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1
$0.4$0.4
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct
$0.5$0.5
OVHcloud logo
OVHcloud
ovhcloud/Mixtral-8x7B-Instruct-v0.1
$0.63$0.63
Perplexity logo
Perplexity
perplexity/mixtral-8x7b-instruct
$0.07$0.28
Replicate logo
Replicate
replicate/mistralai/mixtral-8x7b-instruct-v0.1
$0.3$1.00
Together AI logo
Together AI
together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1
$0.6$0.6

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Mixtral 8x7B 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 Mixtral 8x7B Instruct
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Dolphin 2.5 Mixtral 8x7B————Available
Dolphin 2.6 Mixtral 8x7B—33K$0.500$0.500Available
Dolphin 2.7 Mixtral 8x7B————Available
MiniMax M21.0M$0.255$1.02Deprecating
Mixtral 8x22B Instruct66K$0.600$0.600Available
Mixtral 8x7B Instruct33K$0.070$0.150Current
Hermes 2 Mixtral 8x7B DPO—33K$0.500$0.500Deprecated
KARAKURI LM 8x7B Instruct————Available
Mixtral————Available
Mixtral 8x22B—66K$1.20$1.20Deprecated
Mixtral 8x7B—33K$0.500$0.500Deprecated

Model IDs

accounts/fireworks/models/mixtral-8x7b-instruct
accounts/fireworks/models/mixtral-8x7b-instruct-hf
accounts/fireworks/models/mixtral-8x7b-instruct-v0-oss
anyscale/mistralai/Mixtral-8x7B-Instruct-v0.1
bedrock/eu-west-3/mistral.mixtral-8x7b-instruct-v0:1
bedrock/us-east-1/mistral.mixtral-8x7b-instruct-v0:1
bedrock/us-west-2/mistral.mixtral-8x7b-instruct-v0:1
databricks/databricks-mixtral-8x7b-instruct
deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1
fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct
fireworks_ai/accounts/fireworks/models/mixtral-8x7b-instruct-hf
huggingface-llm-mixtral-8x7b-instruct
huggingface-llm-mixtral-8x7b-instruct-gptq
mistral-mixtral-8x7b-instruct
mistral.mixtral-8x7b-instruct-v0:1
mistralai/mixtral-8x7b-instruct
mistralai/Mixtral-8x7B-Instruct-v0.1
mixtral-8x7b-instruct
ollama/mixtral-8x7B-Instruct-v0.1
ovhcloud/Mixtral-8x7B-Instruct-v0.1
perplexity/mixtral-8x7b-instruct
replicate/mistralai/mixtral-8x7b-instruct-v0.1
together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1