Completions changedapi/completions
Nearest release: v2.1.245, published 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+30added
Lines−15removed
From line
1
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits24to this page, all time
### Headers ### Body parameters #### Response (200) ## Domain types ### Header Parameters ### Body Parameters #### Response ## Domain Types
The whole hunk
from line 1, old and new numbered
/
from line 1
1---
2title: Completions
3url: https://platform.claude.com/docs/en/api/completions
4---
5
61# Completions
72
83## Create a Text Completion
94
10**post** `/v1/complete`
5**POST** `/v1/complete`
116
127[Legacy] Create a Text Completion.
138
from line 10
1510
1611Future models and features will not be compatible with Text Completions. See our [migration guide](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) for guidance in migrating from Text Completions to Messages.
1712
18### Header Parameters
13### Headers
1914
2015- `"anthropic-beta": optional array of AnthropicBeta`
2116
from line 88
9388
9489 - `"mid-conversation-tool-changes-2026-07-01"`
9590
96### Body Parameters
91### Body parameters
9792
9893- `max_tokens_to_sample: number`
9994
from line 96
10196
10297 Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate.
10398
99 minimum: 1
100
104101- `model: Model`
105102
106103 The model that will complete your prompt.
from line 192
195192
196193 See [prompt validation](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and our guide to [prompt design](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview) for more details.
197194
195 minLength: 1
196
198197- `metadata: optional Metadata`
199198
200199 An object describing metadata about the request.
from line 204
205204
206205 This should be a uuid, hash value, or other opaque identifier. Anthropic may use this id to help detect abuse. Do not include any identifying information such as name, email address, or phone number.
207206
207 maxLength: 512
208
208209- `stop_sequences: optional array of string`
209210
210211 Sequences that will cause the model to stop generating.
from line 222
221222
222223- `temperature: optional number`
223224
225 **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting temperature. A value of 1.0 of will be accepted for backwards compatibility, all other values will be rejected with a 400 error.
226
224227 Amount of randomness injected into the response.
225228
226229 Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0` for analytical / multiple choice, and closer to `1.0` for creative and generative tasks.
from line 230
227230
228231 Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
229232
233 maximum: 1, minimum: 0
234
230235- `top_k: optional number`
231236
237 **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not accept top_k; any value will be rejected with a 400 error.
238
232239 Only sample from the top K options for each subsequent token.
233240
234241 Used to remove "long tail" low probability responses. [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
from line 242
235242
236243 Recommended for advanced use cases only.
237244
245 minimum: 0
246
238247- `top_p: optional number`
239248
249 **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not support setting top_p. A value >= 0.99 will be accepted for backwards compatibility, all other values will be rejected with a 400 error.
250
240251 Use nucleus sampling.
241252
242253 In nucleus sampling, we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified by `top_p`.
from line 254
243254
244255 Recommended for advanced use cases only.
245256
257 maximum: 1, minimum: 0
258
246259### Returns
247260
248- `Completion object { id, completion, model, 2 more }`
261- `Completion object`
249262
250263 - `id: string`
251264
from line 359
346359
347360 For Text Completions, this is always `"completion"`.
348361
349 - `"completion"`
362 default: completion
350363
364- `Completion object`
365
351366### Example
352367
353```http
368```bash
354369curl https://api.anthropic.com/v1/complete \
355370 -H 'Content-Type: application/json' \
356371 -H 'anthropic-version: 2023-06-01' \
from line 381
366381 }'
367382```
368383
369#### Response
384#### Response (200)
370385
371386```json
372387{
from line 393
378393}
379394```
380395
381## Domain Types
396## Domain types
382397
383398### Completion
384399
385- `Completion object { id, completion, model, 2 more }`
400- `Completion object`
386401
387402 - `id: string`
388403
from line 498
483498
484499 For Text Completions, this is always `"completion"`.
485500
486 - `"completion"`
501 default: completion
487502
No line in this hunk matches that.