Skip to main content
Update · June 22, 2026As of June 22, 2026, OpenRouter maps reasoning.effort to Anthropic’s output_config.effort on Claude 4.6 and newer models — previously it was ignored. verbosity is unchanged: it still sets output_config.effort, and wins if both are passed.

What’s New

See Anthropic’s Migrating to Claude Opus 4.7 for a full overview of changes. Claude 4.7 Opus introduces three major changes:
  1. Sampling parameters removedtemperature, top_p, and top_k are no longer supported and will be ignored
  2. Adaptive-only thinking — when reasoning is enabled the only supported mode is adaptive; thinking.budget_tokens is no longer supported and reasoning.max_tokens is ignored
  3. New 'xhigh' effort level — a new effort level between 'high' and 'max' via verbosity / output_config.effort

Sampling Parameters Removed

Claude 4.7 Opus no longer accepts temperature, top_p, or top_k. If you pass these parameters, they will be silently ignored — your request will still succeed, but the parameters will have no effect.

Adaptive-Only Thinking

Claude 4.7 Opus supports only adaptive thinking. On 4.6, reasoning could be controlled via a token budget (reasoning.max_tokens / thinking.budget_tokens) or left adaptive; on 4.7, budget-based thinking is removed and adaptive is the only remaining mode when reasoning is on. Reasoning itself remains opt-in on all Anthropic models via reasoning.enabled=true — 4.7 does not change that. Concretely on 4.7:
  • reasoning.max_tokens is accepted but ignored
  • reasoning.effort maps to Anthropic’s output_config.effort (see Parameter Summary) rather than a thinking budget
  • thinking.budget_tokens is no longer supported upstream
To influence overall response effort (not reasoning-specific), use verbosity. It maps to Anthropic’s output_config.effort and applies whether or not reasoning is enabled.

New 'xhigh' Effort Level

A new 'xhigh' effort level is available between 'high' and 'max' via the verbosity parameter. This maps to Anthropic’s output_config.effort.
The full effort scale is now: lowmediumhighxhighmax.
'xhigh' is only supported on Claude 4.7 Opus. 'max' is supported on Claude 4.6+. For older models, both automatically fall back to 'high'.

Parameter Summary

With sampling parameters and reasoning budgets removed on 4.7, output_config.effort is the remaining lever for influencing overall response effort. You can set it via verbosity, or via reasoning.effort when reasoning is enabled (verbosity wins if both are passed; 'minimal' maps to 'low', and 'none' disables reasoning entirely so no output_config.effort is sent).
ParameterClaude 4.7 Opus Behavior
temperature, top_p, top_kIgnored
reasoning.max_tokensIgnored (adaptive used)
reasoning.effortSets output_config.effort (when reasoning is enabled)
verbositySets output_config.effort

Breaking Changes

FeatureOpus 4.6Opus 4.7
temperature / top_p / top_kSupportedIgnored
Thinking modes (when reasoning.enabled=true)Adaptive or budget-basedAdaptive only
reasoning.max_tokensSets a thinking budgetIgnored (adaptive used)
reasoning.effortSets output_config.effortSets output_config.effort
'xhigh' effort levelFalls back to 'high'Supported
'max' effort levelSupportedSupported