Anthropic API (unofficial showcase)
POST/v1/complete

Create a Text Completion

[Legacy] Create a Text Completion.

The Text Completions API is a legacy API. We recommend using the Messages API going forward.

Future models and features will not be compatible with Text Completions. See our migration guide for guidance in migrating from Text Completions to Messages.

  • IdempotentThe SDK sends Idempotency-Key, so a retried request is only applied once.

3 parameters · 9 body fields
anthropic-versionstringoptional
The version of the Claude API you want to use. Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).
anthropic-betastringoptional
Optional header to specify the beta version(s) you want to use. To use multiple betas, use a comma separated list like `beta1,beta2` or specify the header multiple times for each beta.
anthropic-workspace-idstringoptional
Optional header to select the Workspace for this request. The value is a Workspace ID (for example, `wrkspc_011CZkZaBF1tNoB5wlCeusgy`). Only needed for credentials that can act on more than one Workspace. A credential that belongs to a specific Workspace may omit it; if sent, it must match that Workspace.
modelstringrequired
The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
promptstringrequired
The prompt that you want Claude to complete. For proper response generation you will need to format your prompt using alternating `\n\nHuman:` and `\n\nAssistant:` conversational turns. For example: ``` "\n\nHuman: {userQuestion}\n\nAssistant:" ``` 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.
max_tokens_to_sampleintegerrequired
The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum number of tokens to generate.
stop_sequencesarray<string>optional
Sequences that will cause the model to stop generating. Our models stop on `"\n\nHuman:"`, and may include additional built-in stop sequences in the future. By providing the stop_sequences parameter, you may include additional strings that will cause the model to stop generating.
temperaturenumberdeprecatedoptional
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. Note that even with `temperature` of `0.0`, the results will not be fully deterministic.
top_pnumberdeprecatedoptional
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`. Recommended for advanced use cases only.
top_kintegerdeprecatedoptional
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). Recommended for advanced use cases only.
metadataobjectoptional
An object describing metadata about the request.
streambooleanoptional
Whether to incrementally stream the response using server-sent events. See [streaming](https://platform.claude.com/docs/en/build-with-claude/streaming) for details.

17 status codes
200Text Completion object.
completionstringrequired
The resulting completion up to and excluding the stop sequences.
idstringrequired
Unique object identifier. The format and length of IDs may change over time.
modelstringrequired
The model that will complete your prompt. See [models](https://docs.anthropic.com/en/docs/models-overview) for additional details and options.
stop_reasonstringrequired
The reason that we stopped. This may be one the following values: * `"stop_sequence"`: we reached a stop sequence — either provided by you via the `stop_sequences` parameter, or a stop sequence built into the model * `"max_tokens"`: we exceeded `max_tokens_to_sample` or the model's maximum
typestringrequired
Object type. For Text Completions, this is always `"completion"`.
Default:completion
400Invalid argument - The client specified an invalid argument
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
401Unauthenticated - The request does not have valid authentication credentials
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
403Permission denied - The caller does not have permission to execute the specified operation
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
404Not found - Some requested entity was not found
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
408Deadline exceeded - The deadline expired before the operation could complete
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
409Aborted - The operation was aborted due to concurrency issue
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
412Failed precondition - Operation was rejected because the system is not in required state
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
413Out of range - Operation was attempted past the valid range
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
429Resource exhausted - Some resource has been exhausted (rate limiting)
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
431Request header fields too large - Request metadata was too large
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
499Cancelled - The operation was cancelled by the client
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
500Internal - Internal server error
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
501Unimplemented - The operation is not implemented or supported
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
503Unavailable - The service is currently unavailable
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
504Deadline exceeded - Upstream service did not respond in time
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error
529Overloaded - The service is temporarily overloaded
errorobjectrequired
request_idstringrequired
Default:null
typestringrequired
Default:error

Error handling

A 400 is returned: Invalid argument - The client specified an invalid argument. A 401 is returned: Unauthenticated - The request does not have valid authentication credentials. A 403 is returned: Permission denied - The caller does not have permission to execute the specified operation. A 404 is returned: Not found - Some requested entity was not found. A 408 is returned: Deadline exceeded - The deadline expired before the operation could complete. A 409 is returned: Aborted - The operation was aborted due to concurrency issue. A 412 is returned: Failed precondition - Operation was rejected because the system is not in required state. A 413 is returned: Out of range - Operation was attempted past the valid range. A 429 is returned: Resource exhausted - Some resource has been exhausted (rate limiting). A 431 is returned: Request header fields too large - Request metadata was too large. A 499 is returned: Cancelled - The operation was cancelled by the client. A 500 is returned: Internal - Internal server error. A 501 is returned: Unimplemented - The operation is not implemented or supported. A 503 is returned: Unavailable - The service is currently unavailable. A 504 is returned: Deadline exceeded - Upstream service did not respond in time. A 529 is returned: Overloaded - The service is temporarily overloaded.