Source Intelligence
Sweep 28 Aug 2026 · 00:00Z Build v2.1.250 478 read Stable v2.1.236 Latest v2.1.250 Next v2.1.251 Feeds RSS JSON llms.txt
Reading a new release v2.1.251 Analysing changes · 2/5 Deeper second pass · 0/5 agents 427 findings $12.75 so far

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

One change

Completions

api/completions

first seen The page's own history The capture it came from

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.

api/completions Changed · +30 / -15 lines

### Headers ### Body parameters #### Response (200) ## Domain types ### Header Parameters ### Body Parameters #### Response ## Domain Types

from line 1
----
-title: Completions
-url: https://platform.claude.com/docs/en/api/completions
----
-
 # Completions
 
 ## Create a Text Completion
 
-**post** `/v1/complete`
+**POST** `/v1/complete`
 
 [Legacy] Create a Text Completion.
 
from line 10
 
 Future 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.
 
-### Header Parameters
+### Headers
 
 - `"anthropic-beta": optional array of AnthropicBeta`
 
from line 88
 
     - `"mid-conversation-tool-changes-2026-07-01"`
 
-### Body Parameters
+### Body parameters
 
 - `max_tokens_to_sample: number`
 
from line 96
 
   Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate.
 
+  minimum: 1
+
 - `model: Model`
 
   The model that will complete your prompt.
from line 192
 
   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.
 
+  minLength: 1
+
 - `metadata: optional Metadata`
 
   An object describing metadata about the request.
from line 204
 
     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.
 
+    maxLength: 512
+
 - `stop_sequences: optional array of string`
 
   Sequences that will cause the model to stop generating.
from line 222
 
 - `temperature: optional number`
 
+  **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.
+
   Amount of randomness injected into the response.
 
   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
 
   Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
 
+  maximum: 1, minimum: 0
+
 - `top_k: optional number`
 
+  **Deprecated**: Deprecated. Models released after Claude Opus 4.6 do not accept top_k; any value will be rejected with a 400 error.
+
   Only sample from the top K options for each subsequent token.
 
   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
 
   Recommended for advanced use cases only.
 
+  minimum: 0
+
 - `top_p: optional number`
 
+  **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.
+
   Use nucleus sampling.
 
   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
 
   Recommended for advanced use cases only.
 
+  maximum: 1, minimum: 0
+
 ### Returns
 
-- `Completion object { id, completion, model, 2 more }`
+- `Completion object`
 
   - `id: string`
 
from line 359
 
     For Text Completions, this is always `"completion"`.
 
-    - `"completion"`
+    default: completion
 
+- `Completion object`
+
 ### Example
 
-```http
+```bash
 curl https://api.anthropic.com/v1/complete \
     -H 'Content-Type: application/json' \
     -H 'anthropic-version: 2023-06-01' \
from line 381
         }'
 ```
 
-#### Response
+#### Response (200)
 
 ```json
 {
from line 393
 }
 ```
 
-## Domain Types
+## Domain types
 
 ### Completion
 
-- `Completion object { id, completion, model, 2 more }`
+- `Completion object`
 
   - `id: string`
 
from line 498
 
     For Text Completions, this is always `"completion"`.
 
-    - `"completion"`
+    default: completion