Claude 5 Sonnet Migration Guide

What’s New

See Anthropic’s model migration guide for a full overview of changes.

Claude 5 Sonnet introduces three major changes versus Sonnet 4.6:

1. Sampling parameters removed — temperature, 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

It also adds real-time cyber safeguards.

Sampling Parameters Removed

Claude 5 Sonnet 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.

1
// These parameters are ignored on Claude 5 Sonnet
2
{
3
  "model": "anthropic/claude-sonnet-5",
4
  "temperature": 0.5,
5
  "top_p": 0.9,
6
  "top_k": 50,
7
  "messages": [{ "role": "user", "content": "Hello" }]
8
}

Adaptive-Only Thinking

Claude 5 Sonnet supports only adaptive thinking. On Sonnet 4.6, reasoning could be controlled via a token budget (reasoning.max_tokens / thinking.budget_tokens) or left adaptive; on Sonnet 5, budget-based thinking is removed and adaptive is the only remaining mode when reasoning is on. The new API default is adaptive thinking on at effort high.

Reasoning itself remains opt-in on all Anthropic models via reasoning.enabled=true — Sonnet 5 does not change that.

Concretely on Sonnet 5:

• 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.

1
// Opt in to adaptive thinking — the only thinking mode on Sonnet 5
2
{
3
  "model": "anthropic/claude-sonnet-5",
4
  "reasoning": { "enabled": true },
5
  "messages": [{ "role": "user", "content": "Solve this problem step by step" }]
6
}

1
// reasoning.max_tokens is ignored (adaptive used)
2
{
3
  "model": "anthropic/claude-sonnet-5",
4
  "reasoning": { "enabled": true, "max_tokens": 10000 },
5
  "messages": [{ "role": "user", "content": "Hello" }]
6
}
7
// ↑ Equivalent to just { "reasoning": { "enabled": true } }

1
// reasoning.effort maps to output_config.effort (thinking stays adaptive)
2
{
3
  "model": "anthropic/claude-sonnet-5",
4
  "reasoning": { "enabled": true, "effort": "low" },
5
  "messages": [{ "role": "user", "content": "Hello" }]
6
}
7
// ↑ Equivalent to { "reasoning": { "enabled": true }, "verbosity": "low" }

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.

1
{
2
  "model": "anthropic/claude-sonnet-5",
3
  "verbosity": "xhigh"
4
}

The full effort scale is now: low → medium → high → xhigh → max.

Cyber Safeguards

Like Opus 4.7 and 4.8, Claude 5 Sonnet ships with real-time cyber classifiers that block some high-risk dual-use activities. Affected requests are refused upstream by Anthropic; OpenRouter surfaces the refusal as-is. See Anthropic’s Real-time cyber safeguards on Claude for details.

Parameter Summary

With sampling parameters and reasoning budgets removed on Sonnet 5, 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).

1
{ "model": "anthropic/claude-sonnet-5", "verbosity": "xhigh" }

Breaking Changes