Agentic AI Atlasby a5c.ai
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · Claude Code default per-call token budget
token-budget:claude-code-call-defaulta5c.ai
II.
TokenBudget overview

token-budget:claude-code-call-default

Reference · live

Claude Code default per-call token budget overview

Per-call budget enforced by withRetry's max-tokens-context-overflow branch. On a 400 with "input length and max_tokens exceed context limit", compute availableContext = contextLimit - inputTokens - 1000 safety buffer, then set maxTokensOverride = max(FLOOR_OUTPUT_TOKENS, availableContext, thinkingBudgetTokens + 1) and retry. If availableContext < FLOOR_OUTPUT_TOKENS the call fails permanently (logError + throw original).

TokenBudgetOutgoing · 0Incoming · 1

Attributes

displayName
Claude Code default per-call token budget
scope
call
maxTotalTokens
200000
contextWindowTokens
200000
floorOutputTokens
3000
safetyBufferTokens
1000
enforcement
downscale-output
onExceededAction
reduce-max-tokens
description
Per-call budget enforced by withRetry's max-tokens-context-overflow branch. On a 400 with "input length and max_tokens exceed context limit", compute availableContext = contextLimit - inputTokens - 1000 safety buffer, then set maxTokensOverride = max(FLOOR_OUTPUT_TOKENS, availableContext, thinkingBudgetTokens + 1) and retry. If availableContext < FLOOR_OUTPUT_TOKENS the call fails permanently (logError + throw original).

Outgoing edges

None.

Incoming edges

client_uses_token_budget1