Claude API Request Limit: 128 MB for Messages and Token Counting
Anthropic's Claude Platform docs list a 128 MB maximum request size for Messages and Token Counting on the first-party API. Cloud-platform limits are smaller and vary by provider: 20 MB on Bedrock, 30 MB on Google-managed Claude, and up to 32 MB on Anthropic-managed cloud services. Oversized first-party requests return 413 `request_too_large`.
Anthropic's Claude Platform API overview lists a 128 MB maximum request size for first-party Messages and Token Counting requests. The cap is lower when you call Claude through cloud platforms, where documented request limits range from 20 MB to 32 MB. (Anthropic API overview)
Request Size by Platform
The 128 MB limit is for the first-party Claude API, not every hosted Claude service. The documentation states the Messages and Token Counting scope for the first-party and Anthropic-operated cloud limits below; partner-operated platforms have their own request-size limits. (Anthropic API overview)
| Platform | Maximum request size |
|---|---|
| First-party Claude API | 128 MB |
| Amazon Bedrock | 20 MB |
| Claude Models on Google Cloud (Google managed) | 30 MB |
| Claude Platform on AWS (Anthropic-operated) | Up to 32 MB |
| Claude Models on Google Cloud (Anthropic managed) | Up to 32 MB |
| Microsoft Foundry | Up to 32 MB |
Check the limit for the platform receiving the request. A payload accepted by Anthropic's first-party API may exceed the documented maximum for a cloud-hosted deployment. (Anthropic API overview)
What Happens When a Request Is Too Large
For first-party Claude API requests, Anthropic says exceeding the documented request-size limits returns a 413 request_too_large error. For cloud-platform requests, check the platform's own documentation for its current limit and response behavior. (Anthropic API overview)
Read next
Related coverage- Anthropic
Anthropic Resumes Billing for Claude Refusals Before Output in Three Safeguard Categories
Anthropic resumed billing for Claude requests refused before any output when its safeguards classify them as biology, frontier LLM development, or reasoning extraction. The charge uses the model's normal rates across platforms. Other pre-output refusals remain unbilled, but still count against rate limits.
- Claude
Claude Max and Team Plans Now Include Free Monthly API Credits: $100, $200, or Up to $500
Claude Max and Team plans now include monthly Claude API credits at no extra cost: $100 on Max 5x, $200 on Max 20x, and up to $500 pooled on Team. You claim them in claude.ai billing settings by linking one Console organization. They cover the API, Managed Agents, and the Agent SDK, not interactive Claude Code.
- Claude Code
Claude Code Auto-Continues When Usage Limits Reset, On by Default
Claude Code waits in the open session and continues your task automatically when a claude.ai usage limit resets. It is on by default from version 2.1.234 in interactive sessions signed in with a claude.ai subscription. Turn it off in /config under 'Continue automatically at usage limit' or set autoContinueAtUsageLimit to false. It resumes work; it does not raise the limit.
- Claude
Claude Max 20x Is Now Ultra: Pricing and Limits Explained
Anthropic renamed the Max 20x tier to Ultra without changing its $200 monthly web price. Ultra includes 10x Claude Pro usage per week, and verified Ultra accounts have no five-hour limit. Existing Max 20x subscribers move to Ultra automatically at the same price. The $100 Max plan keeps a five-hour limit and 5x Pro usage every five hours and every week.
Sources
- Anthropic, Claude API overview, request size limits
Frequently Asked Questions
What is the Claude API request size limit?
Anthropic's docs list a maximum request size of 128 MB for Messages and Token Counting on the first-party Claude API.
How do cloud-platform request-size limits differ?
They are smaller than the first-party limit and vary by platform. Amazon Bedrock is 20 MB, Google-managed Claude on Google Cloud is 30 MB, and Anthropic-managed services on AWS, Google Cloud, and Microsoft Foundry support up to 32 MB.
What happens if a Claude API request is too large?
Anthropic says a first-party API request over its documented limit returns a 413 `request_too_large` error.