Claude 3.5 Sonnet v2

Anthropic · Active · available in 7 of 31 regions

Tool useVisionBatch inferenceStreaming Prompt cachingEmbeddingsFine-tuning
Context window
200K
200,000 tokens
Max output
Input / 1M
$6.00
ap-northeast-1
Output / 1M
$30.00

What Claude 3.5 Sonnet v2 is good for

editorial

Claude 3.5 Sonnet v2 offers a 200K-token context window with tool use at $6.00 per 1M input tokens. Callable in 7 of 31 regions.

Suits

  • Long documents. 200K tokens covers long documents and multi-file context without splitting them.
  • Tool use. Can call functions, so it can drive retrieval, look things up, and take actions rather than only answering.
  • Images. Accepts image input: screenshots, scanned documents, charts and UI captures.
  • Bulk jobs. Batch inference is available, typically at half the on-demand rate, for work that can wait — backfills, nightly enrichment, evaluation runs.

Think twice if

  • Agentic loops. No prompt caching published, so every step re-pays full price for the prompt prefix. Expensive for agents that resend a long context.
  • Invocation. Reachable only through a cross-region inference profile — calling the bare model ID returns a validation error. Use an ID such as apac.anthropic.claude-3-5-sonnet-20241022-v2:0.

This section is judgement, not data from AWS. It is composed from the capabilities, context window, price position and region coverage shown elsewhere on this page — so it stays in step with the daily snapshot rather than going stale.

Where teams typically use it

Chat and assistants

Conversational work where responsiveness matters as much as depth.

  • · A customer-facing assistant where the first token needs to appear in under a second.
  • · An in-product copilot that explains what the user is looking at and answers follow-ups.
  • · A triage bot that qualifies an incoming request before routing it to the right team.

Coding

Writing, reviewing and refactoring code, usually across more than one file.

  • · A review pass that flags real defects with a severity and leaves style alone.
  • · A framework upgrade applied across a repository, one module at a time, tests green between each.
  • · Turning a failing bug report into a reproducing test and then a fix.

Model & inference profile IDs

Base model ID — direct on-demand invoke

Cross-region inference profiles (1)

Regions marked Inference profile only require a profile ID rather than the base model ID — invoking the base ID there returns a validation error. Regional (us., eu.) profiles carry a 10% premium over global.

Pricing by region

USD per 1M tokens
Region Input Output Cache read Cache write Batch in Batch out Source
ap-northeast-1 Asia Pacific (Tokyo) $6.00 $30.00 $3.00 $15.00 curated
ap-northeast-2 Asia Pacific (Seoul) $6.00 $30.00 $3.00 $15.00 curated
ap-northeast-3 Asia Pacific (Osaka) $6.00 $30.00 $3.00 $15.00 curated
ap-south-1 Asia Pacific (Mumbai) $6.00 $30.00 $3.00 $15.00 curated
ap-south-2 Asia Pacific (Hyderabad) $6.00 $30.00 $3.00 $15.00 curated
ap-southeast-1 Asia Pacific (Singapore) $6.00 $30.00 $3.00 $15.00 curated
ap-southeast-2 Asia Pacific (Sydney) $6.00 $30.00 $3.00 $15.00 curated

Curated pricing. The AWS Price List API publishes no SKU for this model, so these figures are hand-maintained from AWS's public pricing page and verified on Sep 15, 2026. They are not machine-derived — confirm in the AWS console before committing spend. Public Extended Access rate, effective 2025-12-01 — twice the original launch price.

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.

Where this model actually runs

There is no jurisdiction where Claude 3.5 Sonnet v2 is served without the request crossing a border — every route to it is a cross-region inference profile.

Claude 3.5 Sonnet v2 appears in

Common questions

How much does Claude 3.5 Sonnet v2 cost on Amazon Bedrock?
$6.00 per 1M input tokens and $30.00 per 1M output tokens in ap-northeast-1.
Which AWS regions support Claude 3.5 Sonnet v2?
7 of 31 regions: ap-northeast-1, ap-northeast-2, ap-northeast-3, ap-south-1, ap-south-2, ap-southeast-1, ap-southeast-2. Regions marked profile-only need a cross-region inference profile ID such as apac.anthropic.claude-3-5-sonnet-20241022-v2:0 rather than the bare model ID.
What is the context window of Claude 3.5 Sonnet v2?
200,000 tokens (200K).
What is the model ID for Claude 3.5 Sonnet v2 on Bedrock?
anthropic.claude-3-5-sonnet-20241022-v2:0. In regions where it is only reachable through a cross-region inference profile, use a prefixed ID instead: apac.anthropic.claude-3-5-sonnet-20241022-v2:0.

Other Anthropic models