Pricing
Pay per token.
Top up, create a key, and go.
| Model | Input$ per 1M tokens | Output$ per 1M tokens | Cache read$ per 1M tokens |
|---|---|---|---|
DeepSeek V4.1 FlashFeatured DeepSeek's latest flash model, built for fast agentic coding ⚡ A 552B MoE (8B active per token on prefill, 16B on decode) with native image understanding and a 1M context window. The default for new chats and CLI setups. Umans Coder and Umans Flash are aliases for this model, at the same rates. | $0.15 | $0.60 | $0.028 |
Kimi K3.1 Pro Moonshot's newest open model, post-trained from Kimi K3: a 2.8T MoE (104B active per token) with native image understanding and a 1M context window. Thinks at maximum reasoning effort by default; none, low, high or max trade depth for speed. | $2.00 | $10.00 | $0.20 |
GLM 5.3 Z.ai's flagship coding model: the GLM 5.2 successor on the same base, with large gains on complex, long-horizon tasks and a 1M context window. Always thinks (dial low to max). | $1.40 | $4.40 | $0.26 |
Kimi K3Deprecated · discontinued Nov 9, 2026 The first open 3T-class model, built for repository-scale agentic coding. 1M context, native vision. Replaced by Kimi K3.1 Pro. | $3.00 | $15.00 | $0.30 |
USD per 1M tokens. Top up the wallet, create a key, and every request debits exactly what the model used.
Top up & startLabs experiments are free for seat holders while they run, and founding users have priority on seats. Watch the status page for openings and retirements.