{"version":"2.1.299","anchor":"max-output-tokens-message-distinguishes-non-streaming","canonical_anchor":"max-output-tokens-message-distinguishes-non-streaming","heading":"Correct advice when a non-streaming reply hits the output limit","tier":"notice","area":"API Requests","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.299\/e\/max-output-tokens-message-distinguishes-non-streaming","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.299","markdown":"### Correct advice when a non-streaming reply hits the output limit\n\nThe output-limit error no longer suggests `CLAUDE_CODE_MAX_OUTPUT_TOKENS` for non-streaming requests, where it can't raise the limit\n\n**What**\n\nWhen a reply from Claude is cut off because it reached the maximum output length, Claude Code shows an error. Before, that error always suggested raising `CLAUDE_CODE_MAX_OUTPUT_TOKENS`. For requests sent without streaming (where the reply arrives all at once rather than piece by piece), the message now says that this environment variable cannot raise the limit.\n\n**Why**\n\nThe old advice was wrong for non-streaming requests, so following it did nothing. You will no longer be pointed at a setting that cannot help.\n\n- Area: API Requests\n- Names: `CLAUDE_CODE_MAX_OUTPUT_TOKENS`\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}