Or, for the model with the same capabilities and no access approval requirement: changedabout-claude/models/migration-guide
Nearest release: v2.1.238, published under an hour after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+4added
Lines−4removed
From line
1,315
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits5to this page, all time
The whole hunk
from line 1315, old and new numbered
/
from line 1315
13151315
13161316 To increase tool usage, raise the effort setting. `high` or `xhigh` effort settings show substantially more tool usage in agentic search and coding. You can also adjust your prompt to explicitly instruct the model about when and how to properly use its tools.
13171317
13188. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics may lead to refusals. For legitimate security work such as penetration testing, vulnerability research, or red-teaming, apply to the [Cyber Verification Program](https://claude.com/form/cyber-use-case) to request reduced restrictions. See [Safeguards, warnings, and appeals](https://support.claude.com/en/articles/8241253-safeguards-warnings-and-appeals) for background.
13188. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics may lead to refusals. For legitimate security work such as penetration testing, vulnerability research, or red-teaming, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet) to request reduced restrictions. The application route depends on how you access Claude.
13191319
132013209. **High-resolution image support:** Claude Opus 4.7 is the first Claude model with high-resolution image support. Maximum image resolution is 2,576 pixels on the long edge, up from 1,568 pixels on prior models. This unlocks gains on vision-heavy workloads and is particularly valuable for computer use, screenshot understanding, and document analysis.
13211321
from line 1447
14471447* If you use [web fetch](https://platform.claude.com/docs/en/agents-and-tools/tool-use/web-fetch-tool), plan an alternative: it is not available on Claude Opus 5.
14481448* If your organization has a [Priority Tier](https://platform.claude.com/docs/en/api/service-tiers#supported-models) commitment, note that Priority Tier is not supported on Claude Opus 5.
14491449* Remove verification and self-check instructions carried over from prompts tuned for earlier models; they cause over-verification on Claude Opus 5.
1450* If your product does legitimate security work, apply to the [Cyber Verification Program](https://claude.com/form/cyber-use-case) for access to lower restrictions on cyber content.
1450* If your product does legitimate security work, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet) for access to lower restrictions on cyber content.
14511451
14521452#### Migrating from Claude Opus 4.5 or earlier
14531453
from line 2569
25692569
257025705. **Sampling parameters removed:** Sampling parameters (`temperature`, `top_p`, `top_k`) set to a non-default value are not accepted and return a 400 error.
25712571
25726. **Cybersecurity safeguards:** Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity topics may be refused. Refusals return as a successful HTTP 200 response with `stop_reason: "refusal"`, not an error. See [Safeguards, warnings, and appeals](https://support.claude.com/en/articles/8241253-safeguards-warnings-and-appeals) for background.
25726. **Cybersecurity safeguards:** Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity topics may be refused. Refusals return as a successful HTTP 200 response with `stop_reason: "refusal"`, not an error. See [Real-time cyber safeguards on Claude Opus and Sonnet](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet) for what the safeguards block and how legitimate security work can apply to the Cyber Verification Program.
25732573
25742574#### Migration checklist
25752575
from line 2673
26732673
267426745. **Pricing:** Claude Haiku 4.5 is priced at $1/$5 per million input/output tokens. Claude Sonnet 5 is priced at $2/$10 per million input/output tokens. See [Claude pricing](https://platform.claude.com/docs/en/about-claude/pricing).
26752675
26766. **Cybersecurity safeguards:** Claude Sonnet 5 has real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity topics may be refused, returned as a successful HTTP 200 response with `stop_reason: "refusal"`. See [Safeguards, warnings, and appeals](https://support.claude.com/en/articles/8241253-safeguards-warnings-and-appeals) for background.
26766. **Cybersecurity safeguards:** Claude Sonnet 5 has real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity topics may be refused, returned as a successful HTTP 200 response with `stop_reason: "refusal"`. See [Real-time cyber safeguards on Claude Opus and Sonnet](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus-and-sonnet) for what the safeguards block and how legitimate security work can apply to the Cyber Verification Program.
26772677
26782678#### Migration checklist
26792679
No line in this hunk matches that.