Follow Discord
Sweep 09 Oct 2026 · 17:27Z Build v2.1.296 517 read Stable v2.1.287 Latest v2.1.296 Next v2.1.296 Feeds RSS JSON llms.txt llms-full.txt Unofficial
One change · api

Create a Message Batch changedapi/beta/messages/batches/create

Nearest release: v2.1.296, published 4 hours before 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+10added
Lines−14removed
From line 179 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits20to this page, all time

The whole hunk

from line 179, old and new numbered
/
lines
from line 179
179179 
180180 Each input message must be an object with a `role` and `content`. You can specify a single `user`-role message, or you can include multiple `user` and `assistant` messages.
181181 
182 If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response.
182 If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's response. This is called prefill. On models that don't support prefill, creating a message that ends with a partial `assistant` response returns a 400 error. See [Prefill not supported](https://platform.claude.com/docs/en/api/errors#prefill-not-supported).
183183 
184184 Example with a single `user` message:
185185 
from line 197
197197 ]
198198 ```
199199 
200 Example with a partially-filled response from Claude:
200 Example with a partially-filled response from Claude, for models that support prefill:
201201 
202202 ```json
203203 [
from line 3184
31843184 
31853185 - `"claude-haiku-4-5"`
31863186 
3187 Fastest model with near-frontier intelligence
3188 
31893187 - `"claude-haiku-4-5-20251001"`
31903188 
3191 Fastest model with near-frontier intelligence
3192 
31933189 - `"claude-opus-4-5"`
31943190 
31953191 Powerful intelligence for long-running agents and coding
from line 3780
37843780 
37853781 - `fallbacks: optional BetaFallbacksParam or null`
37863782 
3787 Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. The string "default" requests the requested model's server-defined default fallback configuration.
3783 Opt-in server-side retry on one or more substitute models when the requested model declines for policy reasons. Tried in order: if the first entry also declines, the second is tried, and so on. Some models don't support fallbacks; on those models, a list of fallback models returns a 400 error. See [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback). The string "default" requests the requested model's server-defined default fallback configuration. On a model that doesn't support fallbacks, the request runs on the requested model alone, so a declined request stays declined.
37883784 
37893785 - `array of BetaFallbackParam`
37903786 
from line 3878
38823878 
38833879 - `display: optional "summarized" or "omitted" or "updates" or null`
38843880 
3885 Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
3881 Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).
38863882 
38873883 - `"summarized"`
38883884 
from line 3904
39083904 
39093905 - `display: optional "summarized" or "omitted" or "updates" or null`
39103906 
3911 Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. Defaults to `summarized`.
3907 Controls how thinking content appears in the response. When set to `summarized`, thinking is returned normally. When set to `omitted`, thinking content is redacted but a signature is returned for multi-turn continuity. The default depends on the model; see [Controlling thinking display](https://platform.claude.com/docs/en/build-with-claude/thinking#controlling-thinking-display).
39123908 
39133909 - `"summarized"`
39143910 
from line 4010
40144010 
40154011 - `thinking: optional BetaThinkingConfigParam`
40164012 
4017 Configuration for enabling Claude's extended thinking.
4013 Configuration for Claude's thinking.
40184014 
4019 When enabled, responses include `thinking` content blocks showing Claude's thinking process before the final answer. Requires a minimum budget of 1,024 tokens and counts towards your `max_tokens` limit.
4015 With `{"type": "adaptive"}`, Claude decides when and how much to think. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit.
40204016 
4021 See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details.
4017 Which `type` values are accepted, and what happens when you omit `thinking`, depend on the model. See [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#configuring-thinking) for each model's behavior.
40224018 
40234019 - `BetaThinkingConfigEnabled object`
40244020 
Feedback