Skip to content

Pricing: Pay only for what you use

Per token, with no subscription and no per-seat fees.

Open the dashboard

$1 free for a new account

Models

USD per million tokens

ModelInputCached inputOutputCache hit rate
DeepSeek V4.1 Flash 1017DeepSeekUSD 0.15USD 0.01USD 0.6099.0%
GLM 5.3Z.aiUSD 1.30USD 0.13USD 4.2096.3%
GLM 5.3 FlashZ.aiUSD 0.11USD 0.03USD 0.4598.8%
Hy4 flashTencentUSD 0.06USD 0.01USD 0.2599.3%
Nemotron 3.5 Lightning 30BNVIDIAUSD 0.05USD 0.01USD 0.15
Qwen3.8 27BQwenUSD 0.10USD 0.01USD 0.4089.8%
Ornith 1.5 35BOrnithUSD 0.10USD 0.01USD 0.4098.3%
DeepSeek V4.1 FlashDeepSeekUSD 0.14USD 0.03USD 0.5898.7%
RightNow decision modelRightNowUSD 0.19USD 0.019USD 0.00Plus USD 0.0001 per answered question and USD 0.00001 per answered call Full price list

Capacity

Four ways to run

CapacityWhat it isPrice
Pay as you goWhat it isBilled per token with no subscription, on shared capacity.The rates above
Reserved capacityWhat it isCapacity held for your traffic.USD 0.25 per hour for each reserved concurrent request on Ornith 1.5 35B. Tokens at the rates above.
Dedicated deploymentsWhat it isA deployment that serves your company only.USD 9.58 per GPU hour
BatchWhat it isA big job on idle capacity, for less.Half of list price

Teams

What a team gets

No per-seat fees
Your price does not change with the size of your team.
Limits that grow with you
10,000 requests a minute per key to start, 50,000 after your first purchase, 200,000 once your purchases reach USD 200.
A spending limit on any key
Set a monthly budget for each key.
Top-ups up to USD 1,000,000
From USD 5, with optional auto-recharge. Top-ups stay valid for one year.
Zero data retention by default
Request and response content is never used for training. Data retention
Prompt caching built in
Caching is automatic and best effort, with no header or parameter required.

Credits and top-ups