Starter
$10 a month
About $12 of usage a month
- 5-hour limit
- $1.11
- Weekly limit
- $2.77
- Free Standby
- Up to $0.20 of chat a day
- Requests at once per model, when busy
- 4 to 32
Pick the way that fits how you work.
Hosted Model APIs, per token, on one prepaid balance.
$5 minimum top-up. Pay per token.
What's included
New accounts start with $1 free to test the Model APIs.
Add creditsDedicated infrastructure, compliance, and custom volume.
Everything self-serve includes, plus
Model APIs
Price per 1M tokens
Input
$0.05Cached input
$0.0192.2% cache hit, last 24 hours
Output
$0.15Input
$0.10Cached input
$0.0194.2% cache hit, last 24 hours
Output
$0.40Input
$0.10Cached input
$0.0198.5% cache hit, last 24 hours
Output
$0.40Input
$0.11Cached input
$0.0399.0% cache hit, last 24 hours
Output
$0.45Input
$0.14Cached input
$0.0399.5% cache hit, last 24 hours
Output
$0.58Limits and modality-specific capabilities are listed on each model page.
Pay as you go is self-serve, funded by credit top-ups. Enterprise adds private infrastructure, reserved capacity, compliance, and custom terms.
Compare pay-as-you-go API costs with renting GPUs. Compare GPU fit, rental costs, idle time and API costs for your model and traffic.
Can't find what you're looking for? Get in touch
How does the balance work?
You add credits with one-time top-ups, starting at $5, and spend from one balance, in dollars. Optional auto-recharge adds credits automatically when your balance runs low. Top-ups stay valid for one year. Use your balance for Model APIs.
One API key for the OpenAI and Anthropic SDKs.
$10 a month
About $12 of usage a month
$29 a month
About $35 of usage a month
$99 a month
About $119 of usage a month
Cached context
Up to 99.5% cache hit rate, last 24 hours. From $0.01 per 1M cached input tokens, so your plan goes further.
Every plan is shared by its workspace, not per member.
Limits
Limits reset
Every 5 hours
Every week
What happens at a limit
Plan
Credits
Your choice: a cap, or no limit
Standby
Free, slower chat
Stop
Until a reset
Setup
Review each connection before it is applied.
Let your coding agent set it up
19 agents ready
Preview
Preview agents may need extra setup. Each connection makes one small test request.
Can't find what you're looking for? Get in touch
What happens at a limit?
If you turned on Keep full speed on credits, credits pay with your choice of a cap per billing period or no limit. When credits cannot pay, free Standby serves chat. Choose at checkout and change it in Coding plan. If neither can serve a request, it stops with the reason, reset time and next step.