Mixtral 8x7B Instruct

Mistral AI · Active · available in 9 of 16 regions

Streaming Tool useVisionPrompt cachingBatch inferenceEmbeddingsFine-tuning
Context window
32K
32,000 tokens
Max output
Input / 1M
$0.450
us-east-1
Output / 1M
$0.700

Model & inference profile IDs

Base model ID — direct on-demand invoke

Pricing by region

USD per 1M tokens
Region Input Output Cache read Cache write Batch in Batch out Source
us-east-1 US East (N. Virginia) $0.450 $0.700 API
us-west-2 US West (Oregon) $0.450 $0.700 API
ca-central-1 Canada (Central) $0.520 $0.810 API
eu-west-1 EU (Ireland) $0.490 $0.760 API
eu-west-2 EU (London) $0.590 $0.910 API
eu-west-3 EU (Paris) $0.590 $0.910 API
ap-southeast-2 Asia Pacific (Sydney) $0.590 $0.910 API
ap-south-1 Asia Pacific (Mumbai) $0.540 $0.840 API
sa-east-1 South America (Sao Paulo) $0.760 $1.18 API

Region availability

TPM / RPM are default account quotas from AWS Service Quotas where a model-specific limit is published. They are per-account defaults and adjustable on request.

Common questions

How much does Mixtral 8x7B Instruct cost on Amazon Bedrock?
$0.450 per 1M input tokens and $0.700 per 1M output tokens in us-east-1.
Which AWS regions support Mixtral 8x7B Instruct?
9 of 16 regions: us-east-1, us-west-2, ca-central-1, eu-west-1, eu-west-2, eu-west-3, ap-southeast-2, ap-south-1, sa-east-1.
What is the context window of Mixtral 8x7B Instruct?
32,000 tokens (32K).
What is the model ID for Mixtral 8x7B Instruct on Bedrock?
mistral.mixtral-8x7b-instruct-v0:1.

Other Mistral AI models