ollama.com

Use Ollama thinking models via the think parameter and read the separated thinking field

Send images to a multimodal (vision) model through the Ollama API (/api/generate images or /api/chat message images)

Tune Ollama concurrency: parallel requests, multiple loaded models, and the 503 overload queue

Expose an Ollama server on the network and allow browser/CORS origins (OLLAMA_HOST, OLLAMA_ORIGINS)

Set Ollama sampling and runtime options per request (num_ctx, num_predict, seed, temperature, stop) via the options object

Copy, delete, and check Ollama models over the REST API (/api/copy, /api/delete)

Import a local GGUF file into Ollama via the blob API then POST /api/create

Create a customized Ollama model from an existing one with POST /api/create (system prompt, params, quantization)

Inspect an Ollama model's template, parameters, capabilities, and metadata with POST /api/show

Check which Ollama models are loaded in memory (and whether they are on GPU) with GET /api/ps

List locally installed Ollama models via GET /api/tags

Pull a model from the Ollama library programmatically with POST /api/pull and track download progress

Preload an Ollama model into memory and unload it immediately (keep_alive control)

Generate embeddings with Ollama POST /api/embed (single or batched input) and avoid the legacy /api/embeddings shape

Use Ollama JSON mode (format: "json") and avoid the infinite-whitespace failure

Get schema-conforming JSON from Ollama with structured outputs (format = JSON schema) on /api/generate or /api/chat

Use Ollama native tool calling: pass tools to /api/chat, execute the call, and return the result with role tool

Run a multi-turn chat conversation against a local Ollama model with POST /api/chat

Stream tokens from Ollama /api/generate and parse the NDJSON stream correctly

Generate a one-shot (non-streaming) completion from a local Ollama model via POST /api/generate

Call Ollama's OpenAI-compatible API at http://localhost:11434/v1 with any api key string

Call Ollama's OpenAI-compatible API at http://localhost:11434/v1 with any api key string