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.

Coding Models

We recommend the latest models from open-weight-first labs — the full standard and premium catalogue is one tab away.

Coding models

The latest open-weight lab models — the best value for coding agents.

DeepSeek V4.1 Flash

deepseek-v4.1-flash

starting from$0.33 in/$1.31 out/M tokens

GLM-5.3 Flash

glm-5.3-flash

Context: 128k

starting from$0.09 in/$0.32 out/M tokens

Qwen3.8 Flash

qwen3.8-flash

Context: 128k

starting from$0.14 in/$0.45 out/M tokens

Premium

Kimi K3

kimi-k3

Context: 128k

starting from$3.29 in/$16.44 out/M tokens

MiniMax M3

minimax-m3

Context: 128k

starting from$0.39 in/$1.57 out/M tokens

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