Skip to content
AWS Bedrock

Ai21.J2 Mid

Ai21.J2 Mid is available via AWS Bedrock with a 8K context window and up to 8,191 output tokens. Pricing: $12.50/1M input tokens, $12.50/1M output tokens.

Ai21.J2 Mid Pricing & Specifications

Input Price$12.50 per 1M tokens
Output Price$12.50 per 1M tokens
Context Window8,191 tokens (8K)
Max Output8,191 tokens
ProviderAWS Bedrock

What is Ai21.J2 Mid?

Ai21.J2 Mid is a large language model by AWS Bedrock with a 8K context window and up to 8,191 output tokens. It costs $12.50 per 1M input tokens and $12.50 per 1M output tokens. Ai21.J2 Mid is available via AWS Bedrock with a 8K context window and up to 8,191 output tokens. Pricing: $12.50/1M input tokens, $12.50/1M output tokens.

Capabilities

text

Ai21.J2 Mid Cost Examples

Short prompt (500 tokens)

$0.006250

Medium prompt (2K tokens)

$0.02500

Long output (4K tokens)

$0.05000

Count tokens for Ai21.J2 Mid

Paste your prompt to see exact token counts and API cost estimates.

Open Token Counter

Similar Models to Ai21.J2 Mid

AWS Bedrock

Eu West 3/Mistral.Mistral Large 2402

$10.40/1M in 32K ctx

AWS Bedrock

Anthropic.Claude 3 Opus 20240229

$15.00/1M in 200K ctx

AWS Bedrock

Anthropic.Claude Opus 4 1 20250805

$15.00/1M in 200K ctx

AWS Bedrock

Anthropic.Claude Opus 4 20250514

$15.00/1M in 200K ctx

Frequently Asked Questions

How much does Ai21.J2 Mid cost per token? +
Ai21.J2 Mid costs $12.50 per 1M input tokens and $12.50 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.018750.
What is the context window for Ai21.J2 Mid? +
Ai21.J2 Mid supports a context window of 8,191 tokens (8K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Ai21.J2 Mid? +
Ai21.J2 Mid can generate up to 8,191 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Ai21.J2 Mid good for coding tasks? +
Ai21.J2 Mid can handle basic coding tasks, but there are models specifically optimized for code generation that may perform better on complex programming problems.
Token Counter | Pricing Calculator | Model Comparison | All AWS Bedrock Models