AWS Bedrock model

Mistral Ministral 3 3B Instruct

Model ID: bedrock/mistral.ministral-3-3b-instruct

Mistral Ministral 3 3B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $0.04/1M input tokens and $0.04/1M output tokens. Key capabilities include Temperature 0-1, Tool choice. Best for cost-sensitive automations, background tasks, and high-volume workloads.

Input price

$0.04/1M

Cached input

N/A

Output price

$0.04/1M

Context window

128k

Pricing and limits

Pricing below is generated directly from the provider registry in Sim. All amounts are listed per one million tokens.

Input price

$0.04/1M

Cached input

N/A

Output price

$0.04/1M

Updated

Apr 1, 2026

Context window

128k tokens

Max output

Standard defaults

Provider

AWS Bedrock

Best for

Best for cost-sensitive automations, background tasks, and high-volume workloads.

Capabilities

These capability flags are generated from the provider and model definitions tracked in Sim.

Temperature 0-1
Tool choice

Temperature

0 to 1

Reasoning effort

Not supported

Verbosity

Not supported

Thinking levels

Not supported

Structured outputs

Not supported

Tool choice

Supported

Computer use

Not supported

Deep research

Not supported

Memory support

Supported

Max output tokens

Standard defaults

Browse comparable models from the same provider to compare pricing, context window, and capability coverage.

Mistral Large 3 675B Instruct

bedrock/mistral.mistral-large-3-675b-instruct

Mistral Large 3 675B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $2/1M input tokens and $6/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.

Input $2/1M
Output $6/1M
128k context
Temperature 0-1
Updated Apr 1, 2026 →

Mistral Ministral 3 14B Instruct

bedrock/mistral.ministral-3-14b-instruct

Mistral Ministral 3 14B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $0.2/1M input tokens and $0.2/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.

Input $0.2/1M
Output $0.2/1M
128k context
Temperature 0-1
Updated Apr 1, 2026 →

Mistral Ministral 3 8B Instruct

bedrock/mistral.ministral-3-8b-instruct

Mistral Ministral 3 8B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $0.1/1M input tokens and $0.1/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.

Input $0.1/1M
Output $0.1/1M
128k context
Temperature 0-1
Updated Apr 1, 2026 →

Meta Llama 4 Scout 17B Instruct

bedrock/meta.llama4-scout-17b-instruct-v1:0

Meta Llama 4 Scout 17B Instruct is a AWS Bedrock model tracked in Sim. It supports a 3.5M token context window. Pricing starts at $0.18/1M input tokens and $0.72/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.

Input $0.18/1M
Output $0.72/1M
3.5M context
Temperature 0-1
Updated Apr 1, 2026 →

Meta Llama 3 70B Instruct

bedrock/meta.llama3-3-70b-instruct-v1:0

Meta Llama 3 70B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $0.72/1M input tokens and $0.72/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.

Input $0.72/1M
Output $0.72/1M
128k context
Temperature 0-1
Updated Apr 1, 2026 →

Meta Llama 3 2 3B Instruct

bedrock/meta.llama3-2-3b-instruct-v1:0

Meta Llama 3 2 3B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $0.15/1M input tokens and $0.15/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.

Input $0.15/1M
Output $0.15/1M
128k context
Temperature 0-1
Updated Apr 1, 2026 →

Frequently asked questions

Mistral Ministral 3 3B Instruct is a AWS Bedrock model available in Sim. Mistral Ministral 3 3B Instruct is a AWS Bedrock model tracked in Sim. It supports a 128k token context window. Pricing starts at $0.04/1M input tokens and $0.04/1M output tokens. Key capabilities include Temperature 0-1, Tool choice.