AI Models for Coding

High-performance models optimized for coding tasks. All models support tool calling, JSON output, streaming, and prompt caching.

Execute code, run commands, and interact with external APIs.

Structured responses for seamless integration with your tools.

Real-time responses for faster feedback during development.

Reduce costs and latency with intelligent prompt caching.

Featured Coding Models

We default to cheap frontier open-weight models — flagship is one tab away when you need it.

Recommended for coding agents

Frontier open-weight models — best price per token.

GLM-5.1

glm-5.1

Context: 200K

$1.40 in/$4.40 out/M tokens

Kimi K2.6

kimi-k2.6

Context: 262K

$0.95 in/$4.00 out/M tokens

DeepSeek V4 Pro

deepseek-v4-pro

Context: 1.1M

$0.43 in/$0.87 out/M tokens

Get your DevPass and access all coding models with a single API key.