One read of Claude Developer Platformapi-20261109T190724Z
158 pages moved out of 890 read.
Pages moved
158
significant first
Pages read
890
in this capture
Captured
19:07 UTC
Corpus hash
9f3c80475665
index-hash
What this read moved
126-150 of 158, page 6 of 7This capture is too large to show at once. Changes 126-150 of 158 are below, significant first; the rest are on the following screens.
managed-agents/self-hosted-sandboxes-operations Changed · +2 / -0 lines
from line 11
1111 eligibility: not-eligible
1212 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1313 supportedModels:
14 - claude-fable-5-2
15 - claude-mythos-5-2
1416 - claude-fable-5-1
1517 - claude-mythos-5-1
1618 - claude-fable-5
managed-agents/self-hosted-sandboxes-reference Changed · +2 / -0 lines
from line 11
1111 eligibility: not-eligible
1212 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1313 supportedModels:
14 - claude-fable-5-2
15 - claude-mythos-5-2
1416 - claude-fable-5-1
1517 - claude-mythos-5-1
1618 - claude-fable-5
managed-agents/self-hosted-sandboxes-security Changed · +2 / -0 lines
from line 11
1111 eligibility: not-eligible
1212 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1313 supportedModels:
14 - claude-fable-5-2
15 - claude-mythos-5-2
1416 - claude-fable-5-1
1517 - claude-mythos-5-1
1618 - claude-fable-5
managed-agents/self-hosted-sandboxes-workers Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/session-observability Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/session-operations Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/session-threads Changed · +2 / -0 lines
from line 11
1111 eligibility: not-eligible
1212 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1313 supportedModels:
14 - claude-fable-5-2
15 - claude-mythos-5-2
1416 - claude-fable-5-1
1517 - claude-mythos-5-1
1618 - claude-fable-5
managed-agents/sessions Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/skills Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/tools Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/tools-web-restrictions Changed · +2 / -0 lines
from line 8
88 url: https://platform.claude.com/docs/en/managed-agents/overview
99 betaHeader: managed-agents-2026-04-01
1010 supportedModels:
11 - claude-fable-5-2
12 - claude-mythos-5-2
1113 - claude-fable-5-1
1214 - claude-mythos-5-1
1315 - claude-fable-5
managed-agents/vaults Changed · +2 / -0 lines
from line 11
1111 eligibility: not-eligible
1212 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1313 supportedModels:
14 - claude-fable-5-2
15 - claude-mythos-5-2
1416 - claude-fable-5-1
1517 - claude-mythos-5-1
1618 - claude-fable-5
managed-agents/webhooks Changed · +2 / -0 lines
from line 12
1212 eligibility: not-eligible
1313 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1414 supportedModels:
15 - claude-fable-5-2
16 - claude-mythos-5-2
1517 - claude-fable-5-1
1618 - claude-mythos-5-1
1719 - claude-fable-5
managed-agents/workflow-runs Changed · +2 / -0 lines
from line 11
1111 eligibility: not-eligible
1212 note: Sessions are stateful resources; transcripts persist until you delete them. Applies to all Managed Agents sub-features, including Self-hosted sandboxes.
1313 supportedModels:
14 - claude-fable-5-2
15 - claude-mythos-5-2
1416 - claude-fable-5-1
1517 - claude-mythos-5-1
1618 - claude-fable-5
models/haiku-4-5/overview Changed · +2 / -2 lines
from line 18
1818
1919| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
2020| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
21| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Adaptive (always on) | `high` | Jun 2026 |
2222| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
2323| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
2424| [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) | 1M | 128K | From $0.10 / $0.50 | Adaptive | `medium` | Jun 2026 |
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/haiku-5-5/migration-guide Changed · +1 / -1 lines
from line 109
109109
110110Claude Haiku 5.5 accepts a forced `tool_choice` (`any` or a named tool), but the response starts with the tool call and has no `thinking` block. To let the model think before it calls a tool, use `tool_choice: {"type": "auto"}` and say in the prompt when to use the tool.
111111
112Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models. So a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn’t read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5’s blocks. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
112Claude Haiku 5.5 reads thinking blocks from Claude Sonnet 5, Claude Opus 4.8, Claude Haiku 4.5, and earlier models. So a conversation you switch from Claude Haiku 4.5 onto Claude Haiku 5.5 keeps its reasoning. It doesn’t read blocks from Claude Opus 5, Claude Opus 5.5, Claude Sonnet 5.5, or any Claude Fable or Claude Mythos model; the API drops those without an error. On the Claude API and Claude Models on Google Cloud (Google managed), Claude Opus 5.5 and Claude Sonnet 5.5 read Claude Haiku 5.5’s blocks, as do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
113113
114114## Remove sampling parameters
115115
models/haiku-5-5/overview Changed · +2 / -2 lines
from line 26
2626
2727| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
2828| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
29| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
29| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Moderate | Adaptive (always on) | `high` | Jun 2026 |
3030| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
3131| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
3232| **Claude Haiku 5.5** (this model) | 1M | 128K | From $0.10 / $0.50 | Fastest | Adaptive | `medium` | Jun 2026 |
from line 33
3333
3434* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3535* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
36* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
36* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3737* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3838* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3939* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/opus-4-5/overview Changed · +2 / -2 lines
from line 18
1818
1919| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
2020| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
21| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Adaptive (always on) | `high` | Jun 2026 |
2222| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
2323| **Claude Opus 4.5** (this model) | 200K | 64K | $5 / $25 | Extended | `high` | May 2025 |
2424| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-6/overview Changed · +2 / -2 lines
from line 18
1818
1919| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
2020| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :----------------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
21| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Adaptive (always on) | `high` | Jun 2026 |
2222| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
2323| **Claude Opus 4.6** (this model) | 1M | 128K | $5 / $25 | Adaptive (extended deprecated) | `high` | May 2025 |
2424| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-7/overview Changed · +2 / -2 lines
from line 18
1818
1919| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
2020| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
21| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Adaptive (always on) | `high` | Jun 2026 |
2222| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
2323| **Claude Opus 4.7** (this model) | 1M | 128K | $5 / $25 | Adaptive | `high` | Jan 2026 |
2424| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-4-8/overview Changed · +2 / -2 lines
from line 16
1616
1717| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
1818| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------------------- | :------------- | :--------------- |
19| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
19| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Adaptive (always on) | `high` | Jun 2026 |
2020| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
2121| **Claude Opus 4.8** (this model) | 1M | 128K | $5 / $25 | Adaptive | `high` | Jan 2026 |
2222| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
from line 24
2424
2525* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2626* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
27* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
27* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
2828* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
2929* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3030* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.
models/opus-5-5/migration-guide Changed · +2 / -2 lines
from line 280
280280* Set `effort` explicitly: the default is `medium`, where Claude Opus 5’s is `high`.
281281* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
282282* If you use an earlier computer use tool version, declare `computer_toolset_20260801` (no beta header) instead and update your agent loop for the toolset. On Amazon Bedrock, `computer_20251124` also works.
283* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5’s thinking blocks. Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them. Claude Opus 5.5 itself reads thinking from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads thinking from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read thinking from Claude Fable or Claude Mythos models.
283* If a router or fallback can move a conversation from Claude Opus 5.5 to another model, expect that model to run without Claude Opus 5.5’s thinking blocks. Claude Fable 5.1 and Claude Mythos 5.1 on the Claude API are the exception and keep them. So do Claude Fable 5.2 and Claude Mythos 5.2 there. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. Claude Opus 5.5 itself reads thinking from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads thinking from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read thinking from Claude Fable or Claude Mythos models.
284284* Read content blocks by `type`, and pass `thinking` blocks back unmodified in tool-use loops.
285285* If your interface renders text between tool calls, set `display: "updates"` (beta) or `"summarized"` and render the non-empty `thinking` blocks.
286286* If your code edits earlier turns, the `system` prompt, or `tools` mid-conversation, follow [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
from line 876
876876
877877#### Thinking blocks are tied to the model and the conversation
878878
879On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks. No other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In the other direction, Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads them from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read them from Claude Fable or Claude Mythos models. Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid; Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. On accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms, a request that replays a thinking block after such an edit and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
879On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks. So do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. No other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In the other direction, Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads them from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read them from Claude Fable or Claude Mythos models. Keep the conversation append-only (no edits to the `system` prompt, `tools`, or earlier messages mid-conversation) so the blocks stay valid; Claude Code, claude.ai, Claude Managed Agents, and the Claude Agent SDK already do. On accounts created on or after August 31, 2026, 00:00 UTC, on the Claude API and on cloud platforms, a request that replays a thinking block after such an edit and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error. There is no code change for append-only integrations. See [Thinking blocks are tied to the model and the conversation](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#thinking-blocks-are-tied-to-the-model-that-produced-them) and [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking).
880880
881881#### Some computer use tool versions are not supported
882882
models/opus-5-5/overview Changed · +2 / -2 lines
from line 22
2222
2323| Model | Context | Max output | Price / MTok | Latency | Thinking | Default effort | Knowledge cutoff |
2424| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------- | :------------------- | :------------- | :--------------- |
25| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Slower | Adaptive (always on) | `high` | Jun 2026 |
25| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Moderate | Adaptive (always on) | `high` | Jun 2026 |
2626| **Claude Opus 5.5** (this model) | 1M | 128K | $4 / $20 | Moderate | Adaptive (always on) | `medium` | Jun 2026 |
2727| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Fast | Adaptive | `high` | Jun 2026 |
2828| [Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overview) | 1M | 128K | From $0.10 / $0.50 | Fastest | Adaptive | `medium` | Jun 2026 |
from line 29
2929
3030* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
3131* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
32* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
32* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3333* **Latency:** Comparative latency, relative to the current lineup, as published in the models overview. Actual latency depends on prompt length, output length, and thinking effort.
3434* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3535* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
models/opus-5-5/whats-new-opus-5-5 Changed · +1 / -1 lines
from line 51
5151
5252### Thinking blocks are tied to the model and the conversation
5353
54Every thinking block records which model produced it, and each model reads its own blocks and only some other models’. Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads blocks from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read blocks from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5. No other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. One that moves from Claude Opus 5.5 to any model other than those two runs the turns after the switch without the previous model’s reasoning. So does one that moves onto Claude Opus 5.5 from a Claude Fable or Claude Mythos model. When a request carries a block the target model can’t read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
54Every thinking block records which model produced it, and each model reads its own blocks and only some other models’. Claude Opus 5.5 reads thinking blocks from Claude Opus 5 and from earlier Opus, Sonnet, and Haiku models. On the Claude API and Claude Models on Google Cloud (Google managed), it also reads blocks from Claude Sonnet 5.5 and Claude Haiku 5.5. It doesn’t read blocks from Claude Fable or Claude Mythos models. On the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read thinking blocks from Claude Opus 5.5. So do Claude Fable 5.2 and Claude Mythos 5.2 on the Claude API. On Claude Models on Google Cloud (Google managed), Claude Fable 5.2 and Claude Mythos 5.2 read the same blocks as on the Claude API. No other model does. A conversation that moves from Claude Opus 5 onto Claude Opus 5.5, or from Claude Opus 5.5 up to Claude Fable 5.1 or Claude Mythos 5.1 on the Claude API, keeps its reasoning. So does one that moves from Claude Opus 5.5 up to Claude Fable 5.2 or Claude Mythos 5.2 on the Claude API. One that moves from Claude Opus 5.5 to any model other than those four runs the turns after the switch without the previous model’s reasoning. So does one that moves onto Claude Opus 5.5 from a Claude Fable or Claude Mythos model. When a request carries a block the target model can’t read, the API drops it before the model sees it: the request succeeds, and dropped blocks aren’t billed. With the `thinking-binding-controls-2026-08-01` beta header, the drop is reported in a top-level `input_transformations` array. See [Switching models mid-conversation](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking#switching-models).
5555
5656The API also checks whether anything before a Claude Opus 5.5 thinking block (the `system` prompt, the `tools`, or an earlier message) has changed since the block was produced. Keep the conversation append-only: change instructions or tools with [mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) rather than edits. A request that replays a block after such a change and leaves `thinking.block_binding.prefix_mismatch_behavior` unset gets a 400 error on accounts created on or after August 31, 2026, 00:00 UTC. This applies on the Claude API and on cloud platforms. On accounts created before that date, the request gets the error only when it sets the field to `"error"`. To drop the affected blocks instead, send the `thinking-binding-controls-2026-08-01` beta header and set the field to `"drop_block"`. See [Preserved thinking](https://platform.claude.com/docs/en/build-with-claude/preserved-thinking) and the migration guide’s [note on thinking blocks](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide#thinking-blocks).
5757
models/opus-5/overview Changed · +2 / -2 lines
from line 18
1818
1919| Model | Context | Max output | Price / MTok | Thinking | Default effort | Knowledge cutoff |
2020| :---------------------------------------------------------------------------------- | :------ | :--------- | :----------------- | :------------------- | :------------- | :--------------- |
21| [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) | 1M | 128K | $10 / $50 | Adaptive (always on) | `high` | Jun 2026 |
21| [Claude Fable 5.2](https://platform.claude.com/docs/en/models/fable-5-2/overview) | 1M | 128K | $8 / $40 | Adaptive (always on) | `high` | Jun 2026 |
2222| [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) | 1M | 128K | $4 / $20 | Adaptive (always on) | `medium` | Jun 2026 |
2323| **Claude Opus 5** (this model) | 1M | 128K | $5 / $25 | Adaptive | `high` | May 2026 |
2424| [Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overview) | 1M | 128K | $2 / $10 | Adaptive | `high` | Jun 2026 |
from line 26
2626
2727* **Context:** 1M tokens is roughly 555k words or 2.5M Unicode characters on the current tokenizer (introduced with Claude Opus 4.7); models before it fit about 750k words in 1M tokens. 200k tokens is roughly 150k words.
2828* **Max output:** Synchronous Messages API limit. On the Message Batches API, Claude Opus 5.5, Claude Opus 5, Claude Sonnet 5.5, Claude Sonnet 5, Claude Haiku 5.5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 support up to 300k output tokens with the output-300k-2026-03-24 beta header.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.1 and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
29* **Price / MTok:** Input / output, base price per million tokens. Batch API requests are 50% off; prompt caching reads cost 10% of the base input price (2.5% on Claude Fable 5.2, Claude Mythos 5.2, Claude Fable 5.1, and Claude Mythos 5.1, 5% on Claude Opus 5.5 and Claude Sonnet 5.5). See Pricing for the full list.
3030* **Thinking:** Adaptive thinking lets the model decide how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models.
3131* **Default effort:** The effort parameter’s default on the Claude API. Models without a value don’t support the parameter.
3232* **Knowledge cutoff:** Reliable knowledge cutoff: the date through which the model’s knowledge is most extensive and reliable.