One read of Claude Developer Platformapi-20260928T183714Z
65 pages moved out of 637 read.
Pages moved
65
significant first
Pages read
637
in this capture
Captured
18:37 UTC
Corpus hash
5998d0f2c1b1
corpus-hash
What this read moved
51-65 of 65, page 3 of 3This capture is too large to show at once. Changes 51-65 of 65 are below, significant first; the rest are on the following screens.
build-with-claude/compaction-keep-recent-turns Changed · +1 / -0 lines
from line 16
1616 - claude-opus-4-8
1717 - claude-opus-4-7
1818 - claude-opus-4-6
19 - claude-sonnet-5-5
1920 - claude-sonnet-5
2021 - claude-sonnet-4-6
2122 supportedPlatforms:
build-with-claude/compaction-on-demand Changed · +1 / -0 lines
from line 16
1616 - claude-opus-4-8
1717 - claude-opus-4-7
1818 - claude-opus-4-6
19 - claude-sonnet-5-5
1920 - claude-sonnet-5
2021 - claude-sonnet-4-6
2122 supportedPlatforms:
build-with-claude/compaction-thinking-blocks Changed · +1 / -0 lines
from line 16
1616 - claude-opus-4-8
1717 - claude-opus-4-7
1818 - claude-opus-4-6
19 - claude-sonnet-5-5
1920 - claude-sonnet-5
2021 - claude-sonnet-4-6
2122 supportedPlatforms:
build-with-claude/context-editing Changed · +1 / -1 lines
from line 62
6262
6363Context editing is applied server-side before the prompt reaches Claude. Your client application maintains the full, unmodified conversation history. You do not need to sync your client state with the edited version. Continue managing your full conversation history locally as you normally would.
6464
65On Claude Fable 5.1 and Claude Opus 5.5, server-side context management never invalidates thinking blocks. Client-side edits to earlier turns can invalidate the thinking blocks in every later assistant turn. For new accounts created on or after August 31, 2026, a request that replays an invalidated block is rejected unless you opt into dropping it. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
65On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, server-side context management never invalidates thinking blocks. Client-side edits to earlier turns can invalidate the thinking blocks in every later assistant turn. For new accounts created on or after August 31, 2026, a request that replays an invalidated block is rejected unless you opt into dropping it. See [Keeping the prefix unchanged](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#prefix-check).
6666
6767### Context editing and prompt caching
6868
build-with-claude/context-windows Changed · +2 / -2 lines
from line 33
3333
3434## Context window sizes by model
3535
36Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5, Claude Sonnet 4.6, and [Claude Mythos Preview](https://anthropic.com/glasswing) have a 1M-token context window. A single request to any of them can generate up to 128k output tokens (`max_tokens`). Other Claude models, including Claude Sonnet 4.5, have a 200k-token context window.
36Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6, and [Claude Mythos Preview](https://anthropic.com/glasswing) have a 1M-token context window. A single request to any of them can generate up to 128k output tokens (`max_tokens`). Other Claude models, including Claude Sonnet 4.5, have a 200k-token context window.
3737
3838For every model with a 1M-token context window, 1M is the default: you don't need a beta header, and long-context requests are billed at [standard pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing).
3939
from line 121
121121
122122Image tokens are included in these budgets.
123123
124Claude Opus 4.7 and later Opus models, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5 don't receive these injected tags. On these models, you can give the model an explicit budget with [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), which are in beta.
124Claude Opus 4.7 and later Opus models, Claude Sonnet 5.5, Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, and Claude Mythos 5 don't receive these injected tags. On these models, you can give the model an explicit budget with [task budgets](https://platform.claude.com/docs/en/build-with-claude/task-budgets), which are in beta.
125125
126126<Tip>
127127 For agents that span multiple sessions, design your state artifacts so that context recovery is fast when a new session starts. The [memory tool's multisession pattern](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool#multisession-software-development-pattern) walks through a concrete approach. See also [Effective harnesses for long-running agents](https://www.anthropic.com/engineering/effective-harnesses-for-long-running-agents).
build-with-claude/extended-thinking Changed · +1 / -1 lines
from line 354
354354You need to migrate off `type: "enabled"` if:
355355
356356* You use Claude Opus 4.6 or Claude Sonnet 4.6, where `budget_tokens` is deprecated.
357* You use Claude 4.7 or a later model, such as Claude Opus 5.5, Claude Sonnet 5, or Claude Fable 5.1, where `type: "enabled"` returns a 400 error.
357* You use Claude 4.7 or a later model, such as Claude Opus 5.5, Claude Sonnet 5, Claude Sonnet 5.5, or Claude Fable 5.1, where `type: "enabled"` returns a 400 error.
358358
359359The mapping is small: remove `budget_tokens`, set `thinking: {type: "adaptive"}`, and control reasoning depth with `output_config: {effort: ...}` instead of a token budget.
360360
build-with-claude/fallback-credit Changed · +1 / -1 lines
from line 622
622622 * **`fallback-credit-*`:** keep this header on both requests. The retry needs it to redeem the token.
623623
624624 <Note>
625 On models that include the 1M token context window by default, such as Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8, the `context-1m-2025-08-07` beta header has no effect. To keep the two requests identical, omit that header on both rather than sending it on one and not the other.
625 On models that include the 1M token context window by default, such as Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Sonnet 5.5, and Claude Sonnet 5, the `context-1m-2025-08-07` beta header has no effect. To keep the two requests identical, omit that header on both rather than sending it on one and not the other.
626626 </Note>
627627</Accordion>
628628
build-with-claude/handling-stop-reasons Changed · +1 / -1 lines
from line 1946
19461946
19471947On a refusal, the `stop_details` object identifies the policy category that triggered it. The categories and the full refusal response shape are covered on [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). `stop_details` is `null` for all stop reasons other than `refusal`.
19481948
1949A refused request on Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5 can usually be served by retrying on another Claude model. [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) shows how to set up that retry, server-side or in your client. If you build the retry yourself from Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, or Claude Opus 5, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) covers how to avoid paying the prompt-cache cost twice.
1949A refused request on Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5 can usually be served by retrying on another Claude model. [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) shows how to set up that retry, server-side or in your client. If you build the retry yourself from Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, or Claude Sonnet 5.5, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) covers how to avoid paying the prompt-cache cost twice.
19501950
19511951### model\_context\_window\_exceeded
19521952
build-with-claude/structured-outputs Changed · +1 / -0 lines
from line 18
1818 - claude-opus-4-8
1919 - claude-opus-4-7
2020 - claude-opus-4-6
21 - claude-sonnet-5-5
2122 - claude-sonnet-5
2223 - claude-sonnet-4-6
2324 - claude-sonnet-4-5-20250929
build-with-claude/task-budgets Changed · +2 / -0 lines
from line 14
1414 - claude-opus-5
1515 - claude-opus-4-8
1616 - claude-opus-4-7
17 - claude-sonnet-5-5
1718---
1819
1920Task budgets let you tell Claude how many tokens it has for a full agentic loop, including thinking, tool calls, tool results, and output. The model sees a running countdown and uses it to prioritize work and finish gracefully as the budget is consumed.
from line 651
650651| Claude Opus 5 | Beta (set `task-budgets-2026-03-13` header) |
651652| Claude Fable 5 | Beta (set `task-budgets-2026-03-13` header) |
652653| Claude Mythos 5 | Beta (set `task-budgets-2026-03-13` header) |
654| Claude Sonnet 5.5 | Beta (set `task-budgets-2026-03-13` header) |
653655| Claude Sonnet 5 | Not supported |
654656| Claude Opus 4.8 | Beta (set `task-budgets-2026-03-13` header) |
655657| Claude Opus 4.7 | Beta (set `task-budgets-2026-03-13` header) |
build-with-claude/working-with-messages Changed · +1 / -1 lines
from line 323
323323
324324### System role in messages
325325
326On Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, and Claude Opus 5, you can include messages with `"role": "system"` after a user turn (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)) to add a new system instruction partway through a conversation. A `system` message cannot be the first entry in `messages`. Use the top-level `system` field for instructions that apply from the start.
326On Claude Fable 5.1, [Claude Mythos 5.1](https://anthropic.com/glasswing), Claude Fable 5, [Claude Mythos 5](https://anthropic.com/glasswing), Claude Opus 5.5, Claude Opus 4.8, Claude Opus 5, and Claude Sonnet 5.5, you can include messages with `"role": "system"` after a user turn (subject to [placement rules](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#limitations)) to add a new system instruction partway through a conversation. A `system` message cannot be the first entry in `messages`. Use the top-level `system` field for instructions that apply from the start.
327327
328328A mid-conversation system message has the same authority as the top-level `system` field, but because it is appended to the end of the message history, it does not invalidate any cached prefix that came before it. Use the top-level `system` field for instructions that should apply from the very first turn, and a mid-conversation system message for instructions that only become relevant later.
329329
home Changed · +1 / -1 lines
from line 243
243243
244244 * [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) (`claude-fable-5-1`) — New — *For demanding reasoning and long-horizon agentic work* — Most capable · Research · Multi-day tasks
245245 * [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) (`claude-opus-5-5`) — New — *For long-running agentic coding and knowledge work* — Complex projects · Agents · Coding
246 * [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) (`claude-sonnet-5`) — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient
246 * [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) (`claude-sonnet-5-5`) — New — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient
247247 * [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (`claude-haiku-4-5`) — *The fastest model with near-frontier intelligence* — Fastest · Lowest cost · High volume
248248 </HomeSection>
249249
intro Changed · +1 / -1 lines
from line 23
2323
2424* [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) (`claude-fable-5-1`) — New — *For demanding reasoning and long-horizon agentic work* — Most capable · Research · Multi-day tasks
2525* [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) (`claude-opus-5-5`) — New — *For long-running agentic coding and knowledge work* — Complex projects · Agents · Coding
26* [Claude Sonnet 5](https://platform.claude.com/docs/en/models/sonnet-5/overview) (`claude-sonnet-5`) — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient
26* [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) (`claude-sonnet-5-5`) — New — *The best combination of speed and intelligence* — Everyday tasks · Writing · Cost-efficient
2727* [Claude Haiku 4.5](https://platform.claude.com/docs/en/models/haiku-4-5/overview) (`claude-haiku-4-5`) — *The fastest model with near-frontier intelligence* — Fastest · Lowest cost · High volume
2828
2929[Compare models](https://platform.claude.com/docs/en/models/overview)
managed-agents/events-and-streaming Changed · +1 / -1 lines
from line 2637
26372637### Sending system messages
26382638
26392639<Note>
2640 `system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8. If the agent's primary model does not support mid-conversation system injection, the event is rejected with a `model_does_not_support_mid_conversation_system` validation error. Subagent models are not checked, because `system.message` lands on the primary thread only.
2640 `system.message` is supported by Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, and Claude Sonnet 5.5. If the agent's primary model does not support mid-conversation system injection, the event is rejected with a `model_does_not_support_mid_conversation_system` validation error. Subagent models are not checked, because `system.message` lands on the primary thread only.
26412641</Note>
26422642
26432643Send a `system.message` event to give the agent privileged system-level context that applies to the accompanying turn and all subsequent turns. Unlike the `system` field on the agent definition (which sets the top-level system prompt), `system.message` content is appended to the session's system context as a `role: "system"` turn rather than replacing that prompt. Use it when the agent needs updated system-level guidance mid-session: a different persona, revised constraints, or context fetched at runtime that should shape the model's behavior going forward.
models/sonnet-5/whats-new-sonnet-5 Changed · +4 / -0 lines
from line 4
44description: Overview of new features and behavior changes in Claude Sonnet 5.
55---
66
7<Note>
8 Claude Sonnet 5.5 is the current Sonnet model. See [What's new in Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5).
9</Note>
10
711Claude Sonnet 5 is the next generation of Anthropic's Sonnet model family. It is a drop-in upgrade for Claude Sonnet 4.6 with three behavior changes: [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is on by default, manual extended thinking now returns a 400 error (it was deprecated on Claude Sonnet 4.6), and setting sampling parameters (`temperature`, `top_p`, `top_k`) to non-default values returns a 400 error. This page summarizes everything new at launch, including a new tokenizer.
812
913## New model