Create a Message Batch changedapi/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+9added
Lines−13removed
From line
73
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits18to this page, all time
The whole hunk
from line 73, old and new numbered
/
from line 73
7373
7474 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.
7575
76 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.
76 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).
7777
7878 Example with a single `user` message:
7979
from line 91
9191 ]
9292 ```
9393
94 Example with a partially-filled response from Claude:
94 Example with a partially-filled response from Claude, for models that support prefill:
9595
9696 ```json
9797 [
from line 1153
11531153
11541154 - `"claude-haiku-4-5"`
11551155
1156 Fastest model with near-frontier intelligence
1157
11581156 - `"claude-haiku-4-5-20251001"`
11591157
1160 Fastest model with near-frontier intelligence
1161
11621158 - `"claude-opus-4-5"`
11631159
11641160 Powerful intelligence for long-running agents and coding
from line 1331
13351331
13361332 - `thinking: optional ThinkingConfigParam`
13371333
1338 Configuration for enabling Claude's extended thinking.
1334 Configuration for Claude's thinking.
13391335
1340 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.
1336 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.
13411337
1342 See [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) for details.
1338 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.
13431339
13441340 - `ThinkingConfigEnabled object`
13451341
from line 1353
13571353
13581354 - `display: optional "summarized" or "omitted" or null`
13591355
1360 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`.
1356 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).
13611357
13621358 - `"summarized"`
13631359
from line 1373
13771373
13781374 - `display: optional "summarized" or "omitted" or null`
13791375
1380 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`.
1376 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).
13811377
13821378 - `"summarized"`
13831379
No line in this hunk matches that.