Every plan includes fast, affordable models. Pro unlocks the frontier — Claude, GPT and Gemini — the same models behind tools like Claude Code. Use auto and we pick, or name any model.
| Model | Best for | Context | Input /1M | Output /1M |
|---|---|---|---|---|
Mason Auto default
auto |
Smart default — routes to the best-value model | 131k | — | — |
DeepSeek V3
deepseek-v3 |
Fast, excellent general coding | 131k | $0.20 | $0.80 |
DeepSeek R1
deepseek-reasoner |
Deep reasoning for hard problems | 164k | $0.70 | $2.50 |
Qwen3 Coder
qwen3-coder |
Code-specialised, 1M context | 1M | $0.22 | $1.80 |
Kimi K2
kimi-k2 |
Long context, agentic coding | 131k | $0.57 | $2.30 |
GLM-4.6
glm-4.6 |
Strong all-rounder | 200k | $0.43 | $1.75 |
GLM-5.2
glm-5.2 |
Latest Zhipu flagship, 1M context | 1M | $0.93 | $3.00 |
Llama 3.3 70B
llama-3.3-70b |
Open model, blazing-fast & low-cost | 131k | $0.10 | $0.32 |
| Model | Best for | Context | Input /1M | Output /1M |
|---|---|---|---|---|
Claude Sonnet 5 Pro
claude-sonnet |
Best-in-class agentic coding | 1M | $2.00 | $10.00 |
Claude Opus 4.8 Pro
claude-opus |
Maximum capability, hardest tasks | 1M | $5.00 | $25.00 |
Claude Haiku 4.5 Pro
claude-haiku |
Fast, lower-cost frontier model | 200k | $1.00 | $5.00 |
GPT-5.4 Pro
gpt-5 |
OpenAI flagship | 1M | $2.50 | $15.00 |
Gemini 3.1 Pro Pro
gemini-pro |
Google flagship, 1M context | 1M | $2.00 | $12.00 |
Prices are indicative per 1M tokens. Frontier models cost more, so they draw down your monthly budget faster — auto keeps costs low by default.