# Claude 5.5 migration: the old requests that now return 400

> Opus 5.5 and Sonnet 5.5 break old request code: disabled thinking, forced tool_choice and the old computer-use tool now return a 400. Per-model checklist.

URL: https://bartlomiejkrupa.dev/articles/claude-5-5-migration/
Published: 2026-09-30
Tags: claude, opus-5-5, sonnet-5-5, migration, api, model-selection
Summary: Opus 5.5 and Sonnet 5.5 break old request code: disabled thinking, forced tool_choice and the old computer-use tool now return a 400. Per-model checklist.

Claude Opus 5.5 (September 22, 2026) costs $4/$20 per million tokens, down from Opus 5's $5/$25. Claude Sonnet 5.5 (September 28, 2026) keeps Sonnet 5's $2/$10.

Neither is a drop-in swap. Anthropic lists **four** breaking API changes for Opus 5.5 and **five** for Sonnet 5.5, and each one fails loudly with an HTTP 400. One more change fails silently: streaming UIs go quiet between tool calls.

## Definitions

- **Effort** - the `output_config.effort` setting (`low` to `max`) that controls how much the model thinks.
- **`between_tools`** - Sonnet 5.5's lowest thinking setting: no thinking up front, short progress notes between tool calls.
- **Forced tool use** - `tool_choice` set to `any` or to a named `tool`, which makes the model call a tool instead of replying.
- **Adaptive thinking** - the model decides per request how much to think; you steer it with effort, not a token budget.
- **`strict: true`** - a tool setting that makes the model's tool input match the tool's JSON schema exactly.
- **Structured outputs** - a request mode that constrains the reply itself to a JSON schema.
- **Advisor tool** - a beta tool that lets the model consult a second model during a turn.
- **Append-only history** - never editing or deleting earlier turns; new instructions go at the end.
- **MTok** - one million tokens.

## What shipped

| | Claude Opus 5.5 | Claude Sonnet 5.5 |
| --- | --- | --- |
| Released | 2026-09-22 | 2026-09-28 |
| API ID | `claude-opus-5-5` | `claude-sonnet-5-5` |
| Price (input / output per MTok) | $4 / $20 | $2 / $10 |
| Cache reads per MTok | $0.20 | $0.20 |
| Context / max output | 1M / 128K | 1M / 128K |
| Thinking | Adaptive, always on | Adaptive; `between_tools` to turn off |
| Default effort | `medium` | `high` |
| Minimum cacheable prompt | 512 tokens | 512 tokens |
| Reliable knowledge cutoff | June 2026 | June 2026 |

Anthropic's launch claims: Opus 5.5 "generates output more than 30% faster than Opus 5" and "costs 40% less to run than Opus 5" at default settings on typical workloads. Sonnet 5.5 "runs 30%+ faster" and "costs up to 30% less for most work". These are per-task claims from the launch pages. The per-token saving is only on Opus: 20% on input and output, and cache reads drop from $0.50 to $0.20 (60%).

## What breaks: the 400s

Anthropic counts "thinking can't be disabled" as one change; the table splits it into its two request shapes.

| Old request | Opus 5.5 | Sonnet 5.5 | Fix |
| --- | --- | --- | --- |
| `thinking: {"type": "disabled"}` | 400 | 400 (message points to `between_tools`) | Opus: omit `thinking` and lower effort. Sonnet: send `{"type": "between_tools"}` at `high` effort or below |
| `thinking: {"type": "enabled", "budget_tokens": N}` | 400 | 400 | Adaptive thinking plus an effort level |
| `tool_choice` `any` or `tool` | 400 | 400 | `auto` plus `strict: true`, or structured outputs; say in the prompt when the tool applies |
| `computer_20251124` tool (Claude API, Google Cloud) | 400 | 400 | `{"type": "computer_toolset_20260801"}`; Amazon Bedrock still accepts the old tool |
| Replaying a thinking block after editing earlier history | 400 on accounts created on or after 2026-08-31 | Same | Keep history append-only; to change instructions, append a new system message instead of editing earlier turns |
| Advisor tool with an Opus 4.8, Opus 4.7 or Sonnet 5 advisor | - | 400 | Opus 5.5, Opus 5, a [Fable or Mythos model](https://platform.claude.com/docs/en/models/overview), or Sonnet 5.5 itself |

The exact error for forced tool use, identical on both models:

```text
tool_choice: type "tool" and "any" are not supported for this model.
```

On Sonnet 5.5, `between_tools` has sharp edges of its own. It takes no other field (`display`, `budget_tokens` or `block_binding` alongside it returns a 400), it returns a 400 at `xhigh` and `max`, and it prevents changing effort on individual messages. To vary effort per turn, use adaptive thinking instead.

## What breaks silently: progress text

On both models, the notes the model writes between tool calls arrive as `thinking` blocks, not `text` blocks. At the default `display: "omitted"` their text is empty, so a UI that streams those notes to users goes quiet mid-turn with no error. Two fixes:

- Adaptive thinking: set `thinking.display` to `"updates"` (beta, `thinking-display-updates-2026-08-18` header) to get a short summary of each note.
- Sonnet 5.5 only: `between_tools` returns the notes with their summary text and needs no `display` field.

A related trap on both models: a response can now start with a `thinking` block, whether you use adaptive thinking or `between_tools`. Code that reads `content[0]` as the answer breaks. Select blocks by `type`.

## Migration checklist

Opus 5 to Opus 5.5:

1. Change the model ID to `claude-opus-5-5`.
2. Remove `thinking: disabled` and `budget_tokens`; set `effort` explicitly, because the default fell from `high` to `medium`.
3. Replace forced `tool_choice` with `auto` plus `strict: true`.
4. Move `computer_20251124` to `computer_toolset_20260801` on the Claude API and Google Cloud.
5. Set `thinking.display` if users see text between tool calls.
6. Keep conversations append-only.

Sonnet 5 to Sonnet 5.5:

1. Change the model ID to `claude-sonnet-5-5`.
2. Replace `thinking: disabled` with `between_tools`, at `high` effort or below.
3. Replace forced `tool_choice` with `auto` plus `strict: true`.
4. Move `computer_20251124` to the toolset on the Claude API and Google Cloud.
5. Swap any Opus 4.8, Opus 4.7 or Sonnet 5 advisor.
6. Set `thinking.display` if users see text between tool calls (not needed with `between_tools`).
7. Re-run your effort sweep: the levels are recalibrated even though the default is still `high`.

## Refusals

Both models run safety classifiers. A decline is HTTP 200 with `stop_reason: "refusal"` and a `stop_details` category. Server-side fallback (a beta option that re-runs a declined request on another model) covers only some categories:

| | Opus 5.5 | Sonnet 5.5 |
| --- | --- | --- |
| Categories | `cyber`, plus new `bio` and `reasoning_extraction` | `cyber`, `bio`, `frontier_llm`, `reasoning_extraction`, `general_harms` |
| Retried by server-side fallback | Not `reasoning_extraction` | Only `cyber` and `frontier_llm` (requests that could help develop competing AI models) |

The practical risk is `reasoning_extraction`: any prompt that asks the model to write its reasoning into the response can now be refused, and fallback won't rescue it. See [why "show your reasoning" gets refused](/notes/reasoning-extraction-refusal) and the wider [refusal-as-contract pattern](/notes/refusal-as-api-contract).

## Prompts, not just requests

The API changes are half the migration. The other half is prompt text written for older models: "minimize tool calls", "include your reasoning", "don't think". [Claude 5.5 prompt audit: the bad lines weren't there](/articles/claude-5-5-prompt-audit) covers which lines the 5.5 guides retire and what Claude Code's `/doctor prompt-audit` actually found on a real repo. Run the audit [twice](/notes/run-prompt-audit-twice), since one pass can miss findings; ["minimize tool calls"](/notes/dont-discourage-tool-calls) is the line to delete first.

## Bottom line

Opus 5.5 is the cheaper Opus, and Sonnet 5.5 is the faster Sonnet at the same price. Both punish request code that disables thinking or forces tools, and both change the shape of streamed responses. Update the request code first, then the prompts. For the tier decision itself, start from [why most agents default to the wrong Claude tier](/articles/claude-model-tier-comparison), and see [how effort and thinking settings work](/articles/claude-effort-thinking-fast-mode) for the lever that replaces disabled thinking.

Sources:
- What's new in Claude Opus 5.5: https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5
- What's new in Claude Sonnet 5.5: https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5
- Models overview: https://platform.claude.com/docs/en/models/overview
- Introducing Claude Opus 5.5: https://www.anthropic.com/claude-opus-5-5
- Introducing Claude Sonnet 5.5: https://www.anthropic.com/claude-sonnet-5-5