Sign in

One API for the best coding models.

Ollima is an OpenAI-compatible router. Point any tool — Cline, Aider, Cursor, or your own code — at one endpoint and one key.

Get an API key Read the docs

Models

Kimi K2
kimi-2.7
long-context agentic coder
DeepSeek V4
deepseek-v4
strong general coder
DeepSeek V4 Flash
deepseek-v4-flash
fast + cheap
Qwen3 Coder
qwen3-coder-next
autocomplete / fill-in-middle
GLM 5.2
glm-5.2
alternative coder
GPT-4o mini / GPT-5
gpt-4o-mini
OpenAI models

Use it anywhere

Any OpenAI-compatible tool works — set the base URL and your key:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ollima.com/v1",
    api_key="sk-t0-...",   # from https://app.ollima.com
)

r = client.chat.completions.create(
    model="deepseek-v4",
    messages=[{"role": "user", "content": "Write a binary search in Python."}],
)
print(r.choices[0].message.content)
ClineAiderCursorContinueLangChainOpen WebUI