> For the complete documentation index, see [llms.txt](https://developer.jylo.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.jylo.ai/api-reference/inference/completions.md).

# Completions

## Creates a new chat completion response using the specified AI model.

> Sends a chat completion request to generate AI responses based on the provided messages. Supports both streaming and non-streaming modes with automatic token billing.

```json
{"openapi":"3.0.4","info":{"title":"Inference API","version":"v1"},"servers":[{"url":"https://api.{tenant}.{region}.jylo.ai","variables":{"tenant":{"default":"example","description":"Tenant name"},"region":{"default":"uk","description":"Region","enum":["uk","us","eu","au","jp"]}}}],"security":[{"Bearer":[]}],"components":{"securitySchemes":{"Bearer":{"type":"http","description":"Bearer authentication with JWT","scheme":"bearer","bearerFormat":"JWT"}},"schemas":{"Jylo.Inference.Core.Models.ChatCompletionRequest":{"required":["messages"],"type":"object","properties":{"messages":{"type":"array","items":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.Message"},"nullable":true},"stream":{"type":"boolean"},"response_format":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.ResponseFormat"},"max_tokens":{"type":"integer","format":"int32","nullable":true}},"additionalProperties":false},"Jylo.Inference.Core.Models.Message":{"required":["content","role"],"type":"object","properties":{"role":{"type":"string","nullable":true},"content":{"type":"string","nullable":true}},"additionalProperties":false},"Jylo.Inference.Core.Models.ResponseFormat":{"required":["type"],"type":"object","properties":{"type":{"type":"string","nullable":true},"schema":{"type":"string","nullable":true}},"additionalProperties":false},"Jylo.Inference.Core.Models.ChatCompletionResponse":{"required":["choices"],"type":"object","properties":{"id":{"type":"string","nullable":true},"model":{"type":"string","nullable":true},"choices":{"type":"array","items":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.Choice"},"nullable":true},"usage":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.Usage"}},"additionalProperties":false},"Jylo.Inference.Core.Models.Choice":{"required":["message"],"type":"object","properties":{"index":{"type":"integer","format":"int32"},"message":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.Message"},"finishReason":{"type":"string","nullable":true}},"additionalProperties":false},"Jylo.Inference.Core.Models.Usage":{"type":"object","properties":{"promptTokens":{"type":"integer","format":"int32"},"completionTokens":{"type":"integer","format":"int32"},"totalTokens":{"type":"integer","format":"int32"}},"additionalProperties":false},"Microsoft.AspNetCore.Mvc.ProblemDetails":{"type":"object","properties":{"type":{"type":"string","nullable":true},"title":{"type":"string","nullable":true},"status":{"type":"integer","format":"int32","nullable":true},"detail":{"type":"string","nullable":true},"instance":{"type":"string","nullable":true}},"additionalProperties":{}}}},"paths":{"/inference/completions/{modelIdentifier}":{"post":{"tags":["Completions"],"summary":"Creates a new chat completion response using the specified AI model.","description":"Sends a chat completion request to generate AI responses based on the provided messages. Supports both streaming and non-streaming modes with automatic token billing.","parameters":[{"name":"modelIdentifier","in":"path","description":"The unique identifier of the AI model to use for completion.","required":true,"schema":{"type":"string","format":"uuid"}}],"requestBody":{"description":"The chat completion request containing messages and configuration.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.ChatCompletionRequest"}},"text/json":{"schema":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.ChatCompletionRequest"}},"application/*+json":{"schema":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.ChatCompletionRequest"}}}},"responses":{"200":{"description":"Successfully generated chat completion response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Jylo.Inference.Core.Models.ChatCompletionResponse"}}}},"400":{"description":"Invalid request - token limit exceeded or malformed input","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Microsoft.AspNetCore.Mvc.ProblemDetails"}}}},"401":{"description":"Unauthorized","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Microsoft.AspNetCore.Mvc.ProblemDetails"}}}},"402":{"description":"Insufficient credits to process the request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Microsoft.AspNetCore.Mvc.ProblemDetails"}}}},"403":{"description":"Forbidden","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Microsoft.AspNetCore.Mvc.ProblemDetails"}}}},"404":{"description":"Specified model not found","content":{"application/json":{"schema":{"$ref":"#/components/schemas/Microsoft.AspNetCore.Mvc.ProblemDetails"}}}},"500":{"description":"Internal server error during processing"}}}}}}
```


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://developer.jylo.ai/api-reference/inference/completions.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.