Ollama API
  1. Generate a completion
Ollama API
  • Endpoints
  • Conventions
  • Generate a completion
    • Overview
    • Generate request (Streaming)
      POST
    • Request (No streaming)
      POST
    • Request (with suffix)
      POST
    • Request (Structured outputs)
      POST
    • Request (JSON mode)
      POST
    • Request (with images)
      POST
    • Request (Raw Mode)
      POST
    • Request (Reproducible outputs)
      POST
    • Generate request (With options)
      POST
    • Load a model
      POST
    • Unload a model
      POST
  • Generate a chat completion
    • Overview
    • Chat Request (Streaming)
      POST
    • Chat request (No streaming)
      POST
    • Chat request (Structured outputs)
      POST
    • Chat request (With History)
      POST
    • Chat request (with images)
      POST
    • Chat request (Reproducible outputs)
      POST
    • Chat request (with tools)
      POST
    • Load a model
      POST
    • Unload a model
      POST
  • Create a Model
    • Overview
    • Create a new model
      POST
    • Quantize a model
      POST
    • Create a model from GGUF
      POST
    • Create a model from a Safetensors directory
      POST
  • Check if a Blob Exists
    • Overview
  • Push a Blob
    • Overview
  • List Local Models
    • Overview
    • Examples
  • Show Model Information
    • Overview
    • Examples
  • Copy a Model
    • Overview
    • Examples
  • Delete a Model
    • Overview
    • Examples
  • Pull a Model
    • Overview
    • Examples
  • Push a Model
    • Overview
  • Generate Embeddings
    • Overview
    • Examples
    • Request (Multiple input)
  • List Running Models
    • Overview
    • Examples
  • Generate Embedding
    • Overview
    • Examples
  • Version
    • Overview
  1. Generate a completion

Overview

POST /api/generate
Generate a response for a given prompt with a provided model. This is a streaming endpoint, so there will be a series of responses. The final response object will include statistics and additional data from the request.

Parameters#

model: (required) the model name
prompt: the prompt to generate a response for
suffix: the text after the model response
images: (optional) a list of base64-encoded images (for multimodal models such as llava)
Advanced parameters (optional):
format: the format to return a response in. Format can be json or a JSON schema
options: additional model parameters listed in the documentation for the Modelfile such as temperature
system: system message to (overrides what is defined in the Modelfile)
template: the prompt template to use (overrides what is defined in the Modelfile)
stream: if false the response will be returned as a single response object, rather than a stream of objects
raw: if true no formatting will be applied to the prompt. You may choose to use the raw parameter if you are specifying a full templated prompt in your request to the API
keep_alive: controls how long the model will stay loaded into memory following the request (default: 5m)
context (deprecated): the context parameter returned from a previous request to /generate, this can be used to keep a short conversational memory

Structured outputs#

Structured outputs are supported by providing a JSON schema in the format parameter. The model will generate a response that matches the schema. See the structured outputs example below.

JSON mode#

Enable JSON mode by setting the format parameter to json. This will structure the response as a valid JSON object. See the JSON mode example below.
Important
It's important to instruct the model to use JSON in the prompt. Otherwise, the model may generate large amounts whitespace.
Modified at 2025-03-14 07:55:41
Previous
Conventions
Next
Generate request (Streaming)
Built with