Error reference changederrors
Nearest release: v2.1.301, published 5 hours before upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 15 Oct 2026 19:38 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 15 Oct 2026 20:07 UTC.
Upstream edited
Recorded here
Lines+78added
Lines−8removed
From line
148
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits187to this page, all time
### Response exceeded the output token maximum
The whole hunk
from line 148, old and new numbered
/
This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.
from line 148
148148| `Request too large` | [Request errors](#request-too-large) |
149149| `Request too large for the API's 32MB request limit` | [Request errors](#request-too-large) |
150150| `Image was too large` | [Request errors](#image-was-too-large) |
151| `API Error: an image in the conversation could not be processed and was removed` | [Request errors](#image-was-too-large) |
151152| `Unable to resize image` | [Request errors](#unable-to-resize-image) |
152153| `Request rejected as unprocessable by the model` | [Request errors](#request-rejected-as-unprocessable-by-the-model) |
153154| `PDF too large` / `PDF is password protected` / `pdftoppm is not installed` | [Request errors](#pdf-errors) |
from line 175
174175| `Effort '<level>' isn't available with thinking turned off on this model` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |
175176| `effort '<level>' is not supported when thinking is disabled` | [Request errors](#effort-isnt-available-with-thinking-turned-off) |
176177| `max_tokens must be greater than thinking.budget_tokens` | [Request errors](#thinking-budget-exceeds-output-limit) |
178| `Claude's response exceeded the ... output token maximum` | [Request errors](#response-exceeded-the-output-token-maximum) |
177179| `API Error: 400 due to tool use concurrency issues` | [Request errors](#tool-use-or-thinking-block-mismatch) |
178180| `API Error: 400 orphaned tool_result in conversation history` | [Request errors](#tool-use-or-thinking-block-mismatch) |
179181| `API Error: 400 duplicate tool_use ID in conversation history` | [Request errors](#tool-use-or-thinking-block-mismatch) |
from line 196
194196| `The connection dropped while downloading the update` | [Troubleshoot installation and login](/docs/en/troubleshoot-install#the-connection-dropped-while-downloading-the-update) |
195197| `Download timed out: exceeded the total deadline` | [Troubleshoot installation and login](/docs/en/troubleshoot-install#the-connection-dropped-while-downloading-the-update) |
196198| `--bg and --print conflict` | [Command-line errors](#conflict-between-bg-and-print) |
199| `Couldn't tell whether --bg is a flag or text here, so nothing was started` | [Command-line errors](#couldnt-tell-whether-bg-is-a-flag-or-text) |
197200| `Error: Cannot use both --append-subagent-system-prompt and --append-subagent-system-prompt-file. Please use only one.` | [Command-line errors](#conflict-between-a-system-prompt-flag-and-its-file-form) |
198201| `Cloud sessions cannot be created from a --restricted session` | [Command-line errors](#cloud-sessions-cannot-be-created-from-a-restricted-session) |
199202| `Cloud sessions are disabled by your organization's policy` | [Command-line errors](#cloud-sessions-are-disabled-by-your-organizations-policy) |
from line 382
379382| `Managed settings document could not be parsed as a JSON object; none of its settings are in effect. Fix or remove it.` | [Configuration warnings](#managed-settings-document-could-not-be-parsed) |
380383| `Managed settings drop-in directory could not be read` | [Configuration warnings](#managed-settings-document-could-not-be-parsed) |
381384| `Unable to read managed policy settings` | [Configuration warnings](#unable-to-read-managed-policy-settings) |
385| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settings-hooks-not-loaded) |
382386| `otelHeadersHelper failed; telemetry is not being exported. See /status: ...` | [Configuration warnings](#otelheadershelper-failed) |
383387| `"crossSessionInbound" must be one of "accept", "hold", "refuse"` | [Configuration warnings](#crosssessioninbound-must-be-one-of-accept-hold-refuse) |
384388| `API Error: ANTHROPIC_FOUNDRY_RESOURCE must be a Foundry resource name` | [Configuration warnings](#anthropic-foundry-resource-must-be-a-foundry-resource-name) |
from line 392
388392| `... has a wildcard before the rest of the command` | [Configuration warnings](#has-a-wildcard-before-the-rest-of-the-command) |
389393| `Denying Bash also turns off the PowerShell tool, so Claude has neither` | [Configuration warnings](#denying-bash-also-turns-off-the-powershell-tool) |
390394| `CLAUDE_CODE_DISABLE_1M_CONTEXT is set, but the 200K limit isn't enforced` | [Configuration warnings](#the-200k-limit-isnt-enforced) |
395| `Model "<model>" isn't recognized · context assumed to be 200k tokens` | [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) |
396| `Claude Code doesn't recognize the model "<model>", so it assumes a context window of 200k tokens` | [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id) |
391397| `[claude-code:unrecognized_model]` | [Configuration warnings](#unrecognized-model-id-on-a-request) |
392398| `is ignored — managed settings set allowManagedReadPathsOnly` / `is ignored — managed settings set allowManagedDomainsOnly` | [Configuration warnings](#sandbox-allow-entries-are-ignored-under-a-managed-lock) |
393399| `Stale sandbox mask files left by a killed session` | [Configuration warnings](#stale-sandbox-mask-files-left-by-a-killed-session) |
from line 2172
21662172* Disable MCP servers you are not using with `/mcp disable <name>` to remove their tool definitions from context
21672173* Trim large `CLAUDE.md` memory files, or move instructions into [path-scoped rules](/docs/en/memory#path-specific-rules) that load only when relevant
21682174* Auto-compact is on by default and normally prevents this error. If you turned it off in `/config` or with [`DISABLE_AUTO_COMPACT`](/docs/en/env-vars), turn it back on. If you keep it off, run `/compact` yourself before the window fills.
2175* If the error appears near 200K tokens on a model that accepts more, one cause is a model ID that Claude Code doesn't recognize. Claude Code assumes a 200K window for such an ID, so to keep working past that point, [give it the model's real context window](/docs/en/model-config#correct-the-window-for-a-gateway-or-custom-model-id).
21692176
21702177See [Explore the context window](/docs/en/context-window) for an interactive view of how context fills up.
21712178
from line 2228
22212228```text theme={null}
22222229Image was too large. Double press esc to go back and try again with a smaller image.
22232230API Error: 400 ... image dimensions exceed max allowed size
2231API Error: an image in the conversation could not be processed and was removed.
22242232```
22252233
2226Claude Code replaces the unprocessable image with a text placeholder and retries, so subsequent messages succeed. On versions before 2.1.142, a pasted image could remain in the conversation and repeat the same error on every subsequent message. To recover on those versions, press Esc twice and step back past the turn where the image was added.
2234The `could not be processed and was removed` line means the API refused an image in the conversation, such as one over the size or dimension limits.
22272235
2236If one of these errors keeps coming back, update Claude Code. On older versions, an image error could repeat for reasons such as these:
2237
2238* Before v2.1.299, in a long conversation with many images, Claude Code could remove the images you attached last instead of the one over the limit. The `was removed` line then repeated on every turn, and Claude didn't see your new images.
2239* Before v2.1.299, in VS Code, the Desktop app, and the Agent SDK, images you attached while Claude was working didn't get the resizing that other attached images get. They reached the API at their original size, which led to repeated image errors in long conversations.
2240* Before v2.1.166, a pasted image could remain in the conversation, and the same error then repeated on every subsequent message
2241
22282242**What to do:**
22292243
22302244* Resize the image before pasting. The API accepts images up to 8000 pixels on the longest edge for a single image, or 3000 pixels when more than 20 images are in context.
from line 2669
26552669* Raise [`CLAUDE_CODE_MAX_OUTPUT_TOKENS`](/docs/en/env-vars) above the thinking budget
26562670* See [Extended thinking](/docs/en/model-config#extended-thinking) for how the budget interacts with output length
26572671
2672### Response exceeded the output token maximum
2673
2674Claude's reply reached the largest number of output tokens the request allowed and was cut off there:
2675
2676```text theme={null}
2677API Error: Claude's response exceeded the ... output token maximum. To configure this behavior, set the CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable.
2678API Error: Claude's response exceeded the 64000 output token maximum for a request sent without streaming. The CLAUDE_CODE_MAX_OUTPUT_TOKENS environment variable cannot raise this limit.
2679```
2680
2681The form that names `a request sent without streaming` means a streaming request failed and Claude Code re-sent it without streaming, which limits the reply to 64,000 output tokens. Before v2.1.299, a reply cut off on such a re-sent request ended the turn without this message, as if the reply were complete.
2682
2683**What to do:**
2684
2685* If Claude wrote some text before the reply was cut off, reply `continue` in an interactive session to ask for the rest. That text stays in the conversation.
2686* If the message says to set `CLAUDE_CODE_MAX_OUTPUT_TOKENS`, see [`CLAUDE_CODE_MAX_OUTPUT_TOKENS`](/docs/en/env-vars) for how the value is capped and [Set environment variables](/docs/en/env-vars#set-environment-variables) for where to set it
2687* To keep each reply under the limit, ask Claude for the output in smaller pieces, such as one file or one section per reply
2688
26582689### Tool use or thinking block mismatch
26592690
26602691The conversation history reached the API in an inconsistent state.
from line 2768
27372768API Error: 400 ... Invalid `encrypted_content` in `search_result` block
27382769API Error: 400 ... Invalid `encrypted_index` in `text` block
27392770API Error: 400 ... Failed to decrypt web search result content
2740API Error: 400 ... Invalid `encrypted_stdout` in `encrypted_code_execution_result` block
2741```
2742
2743Results from the API's hosted [web search tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-search-tool) carry encrypted fields that only the API can read. The `encrypted_stdout` wording names the output of a hosted code execution program that read such results, which the API encrypts as well. The API refuses a request that replays content it can't decrypt, such as content produced for a different organization.
2744
2745Claude Code's own [WebSearch tool](/docs/en/tools-reference#websearch-tool-behavior) records search results as plain text, so these blocks usually reach a conversation through a proxy or [LLM gateway](/docs/en/llm-gateway) that ran hosted web search itself.
2746
2747For the three web search wordings, Claude Code leaves the search calls, results, and citations out of what it sends and retries the request once, so the session continues without showing the error. The `encrypted_stdout` wording has no such recovery, so that message still reaches you. Before v2.1.282, Claude Code kept the refused web search blocks too, and every later turn and `/compact` failed the same way.
2748
2749**What to do:**
2750
2751* If you're on v2.1.281 or earlier and every turn fails with one of the web search wordings, run `claude update` and resume the session
2752* If the error persists, or the message names `encrypted_stdout`, run `/rewind` to step back to a checkpoint before the turn that added the content, or run `/clear` to start a conversation that doesn't carry it
2753* If you run Claude Code behind a proxy or gateway, report the error to whoever operates it
2754
2755### Usage Policy refusal
2756
2757The API declined to respond because content in the conversation triggered a [Usage Policy](https://www.anthropic.com/legal/aup) check.
2758
2759If the message includes the line `` Details: `[reasoning_extraction]` ``, see [Safeguards flagged a request for Claude's reasoning](#safeguards-flagged-a-request-for-claudes-reasoning).
2760
2761The message includes a Request ID and a Message ID you can quote to support if you believe the refusal is incorrect.
2762
2763```text theme={null}
2764API Error: Opus 4.6 can't help with this. Start a new session to continue.
2765
2766Send feedback with /feedback or learn more: https://www.anthropic.com/legal/aup
2767```
2768
2769The message names the model that declined, or `Claude` when no model is recorded.
2770
2771The check evaluates the full conversation, not only your latest prompt, so sending a new message in the same session usually re-triggers the same refusal. The same applies after exiting and reopening the session with `--continue` or `--resume`, since the transcript on disk still contains the triggering content. On [Amazon Bedrock](/docs/en/amazon-bedrock), [Google Cloud's Agent Platform](/docs/en/google-vertex-ai), and [Microsoft Foundry](/docs/en/microsoft-foundry), this message also covers requests the model's safety measures flagged as a cybersecurity topic. See [Safety measures flagged a cybersecurity topic](#safety-measures-flagged-a-cybersecurity-topic).
2772
2773Before v2.1.219, the message read `Claude Code is unable to respond to this request, which appears to violate our Usage Policy (https://www.anthropic.com/legal/aup). Please double press esc to edit your last message or start a new session for Claude Code to assist with a different task.`
2774
2775**What to do:**
2776
2777* Press Esc twice or run `/rewind` to step back to a checkpoint before the turn that triggered the r
2771API Error: 400 ... Invalid `encrypted_stdout` in `encry
No line in this hunk matches that.