# What's new in Claude Opus 5

> Source: <https://platform.claude.com/docs/en/about-claude/models/whats-new-opus-5>
> Published: 2026-07-24 17:20:31+00:00

We use cookies to deliver and improve our services, analyze site usage, and if you agree, to customize or personalize your experience and market our services to you. You can read our Cookie Policy [here](https://www.anthropic.com/legal/cookies).

Claude Opus 5 is a step-change improvement over Claude Opus 4.8, with the largest gains in deep reasoning, agentic and long-horizon tasks, and test-time compute scaling. This page summarizes everything new in Claude Opus 5, including thinking on by default, mid-conversation tool changes, and a breaking change to when thinking can be disabled.

| Model | API model ID | Description |
|---|---|---|
| Claude Opus 5 | `claude-opus-5` | For complex agentic coding and enterprise work |

Claude Opus 5 has a [1M token context window](/docs/en/build-with-claude/context-windows) (1M tokens is both the default and the maximum; there is no smaller context variant), 128k max output tokens, and [thinking](/docs/en/build-with-claude/thinking) on by default.

For complete pricing and specs, see the [models overview](/docs/en/about-claude/models/overview).

`max`

Claude Opus 5 supports the full [effort](/docs/en/build-with-claude/effort) ladder, `low`

, `medium`

, `high`

, `xhigh`

, and `max`

, with `max`

as the explicit top tier for the deepest possible reasoning. No beta header is required. When running at `xhigh`

or `max`

effort, set a large `max_tokens`

so the model has room to think and act across subagents and tool calls.

```
client = anthropic.Anthropic()

with client.messages.stream(
    model="claude-opus-5",
    max_tokens=64000,
    output_config={"effort": "max"},
    messages=[
        {
            "role": "user",
            "content": "Explain why the sum of two even numbers is always even.",
        }
    ],
) as stream:
    response = stream.get_final_message()

print(response)
```

Thinking is [on by default](#thinking-on-by-default) on Claude Opus 5, so no `thinking`

field is needed.

You can add or remove tools between turns of a conversation while preserving the prompt cache, instead of resending a fixed tool list for the life of a session. Mid-conversation tool changes are in beta: include the `mid-conversation-tool-changes-2026-07-01`

beta header in your requests. See [Mid-conversation system messages](/docs/en/build-with-claude/mid-conversation-system-messages) for usage.

The `fallbacks`

parameter supports a new `"default"`

mode, which applies Anthropic's recommended fallback models by refusal category instead of a model list you maintain yourself. Server-side fallback is in beta, and the `"default"`

mode requires the `server-side-fallback-2026-07-01`

beta header. See [Refusals and fallback](/docs/en/build-with-claude/refusals-and-fallback).

The minimum cacheable prompt length on Claude Opus 5 is 512 tokens, down from 1,024 tokens on Claude Opus 4.8. Prompts that were too short to cache on Claude Opus 4.8 can now create cache entries with no code changes. See [Prompt caching](/docs/en/build-with-claude/prompt-caching#cache-limitations) for per-model minimums.

[Fast mode](/docs/en/build-with-claude/fast-mode) (research preview) is available for Claude Opus 5 on the Claude API only; it is not currently available on Amazon Bedrock, Google Cloud, or Microsoft Foundry. Fast mode for Claude Opus 5 is priced at $10 per million input tokens and $50 per million output tokens. See [Fast mode](/docs/en/build-with-claude/fast-mode) for access, supported models, and pricing.

On Claude Opus 4.8, requests run without thinking unless you set `thinking: {"type": "adaptive"}`

. On Claude Opus 5, the same requests run with [thinking](/docs/en/build-with-claude/thinking) on: the model decides when and how much to think on each turn, and the [effort parameter](/docs/en/build-with-claude/effort) is the control for thinking depth. The wire value is unchanged; `thinking: {"type": "adaptive"}`

remains valid and equivalent to the default.

Because `max_tokens`

is a hard limit on total output (thinking plus response text), revisit it for workloads that ran without thinking on Claude Opus 4.8.

The API keeps the option to disable thinking, subject to the effort restriction below.

`high`

or belowOn Claude Opus 5, `thinking: {"type": "disabled"}`

is accepted only when the effort level is `high`

or below. Setting `thinking: {"type": "disabled"}`

with effort `xhigh`

or `max`

returns a 400 error. This is generally available behavior on Claude Opus 5 onward, enforced on each request, and it is a breaking change from Claude Opus 4.8, where disabling thinking was independent of the effort level. If you disable thinking at high effort levels today, either keep thinking disabled and set effort to `high`

or below, or keep the effort level and remove the `thinking`

field.

With thinking disabled, Claude Opus 5 can occasionally write a tool call into its text output instead of emitting a `tool_use`

block, or include internal XML tags in its visible response. Where possible, keep thinking enabled and control token cost with lower effort levels; for integrations that must keep thinking disabled, see [Running with thinking disabled](/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5#running-with-thinking-disabled) for prompting mitigations.

Beyond the API changes above, Claude Opus 5 behaves differently from Claude Opus 4.8 in ways you may notice without changing any code. Default user-facing responses and written deliverables run longer. In agentic sessions, the model narrates its progress to the user more often. In multi-agent frameworks, it delegates to subagents more readily. It also verifies its own work without being told to, so remove verification instructions carried over from earlier models ("include a final verification step," "use a subagent to verify"); they cause over-verification on Claude Opus 5. For prompting patterns that tune each of these behaviors, see [Prompting Claude Opus 5](/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5).

Compared with Claude Opus 4.8, Claude Opus 5 is a step-change improvement rather than an incremental one, and it delivers frontier intelligence at half the cost of Claude Fable 5. The largest gains are in:

`max`

level) into better results.`low`

and `medium`

For the prompting patterns that get the most out of these capabilities, see [Prompting Claude Opus 5](/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5#capability-improvements).

Claude Opus 5 is priced at $5 per million input tokens and $25 per million output tokens, unchanged from Claude Opus 4.8.

See [Pricing](/docs/en/about-claude/pricing) for complete pricing, including batch processing, prompt caching, and fast mode rates.

Claude Opus 5 is available on:

`claude-opus-5`

.`anthropic.claude-opus-5`

. Claude Opus 5 is also reachable through the `InvokeModel`

API on `bedrock-runtime`

, served by the same infrastructure; the `claude-opus-5`

.Claude Opus 4.8 remains available on all of these platforms.

To migrate from Claude Opus 4.8, update your model ID:

```
model = "claude-opus-4-8"  # Before
model = "claude-opus-5"  # After
```

Then review the two [behavior changes](#behavior-changes): thinking is on by default, and disabling thinking with effort `xhigh`

or `max`

returns a 400 error. See the [migration guide](/docs/en/about-claude/models/migration-guide#migrating-from-claude-opus-4-8-to-claude-opus-5) for step-by-step instructions.

Complete specs and pricing for all current Claude models.

Behavioral differences and prompting patterns specific to Claude Opus 5.

Control how many tokens Claude uses when responding, from low to max.

How thinking works when it's on by default, and when it can be disabled.

Give Claude an advisory token budget to pace its work against.

Guide for migrating to the latest Claude models from previous Claude versions.

Get higher output tokens per second from Claude Opus models at premium pricing.

Was this page helpful?