Usage-based pricing · start free
Pricing
Billing
Billing is prepaid. Load credits, and each request draws down your balance at per-token rates. Requests pause at $0 until you top up. Auto-reload refills your balance before it runs out, and spend alerts email you as usage climbs. Or go flat-rate with Ultra.
- Prepaid
- load credits, pay per token
- No limits
- practically no rate limits
- 200 req
- free every month
Join the teams behind 400+ production agents.
Read customer stories
Inference at work today
Private tokens / dayProduction agentsFast Apply throughputDedicated availability
Private tokens / dayProduction agentsFast Apply throughputDedicated availability
Open Source Models
Frontier open weights, served on custom kernels for codegen.
Chat
Kimi K3.1 ProFeatured
Input$2.50/1M
Cache read$0.29/1M
Output$14.00/1M
Context1M
GLM-5.3 744B
Input$1.19/1M
Cache read$0.20/1M
Output$6.00/1M
Context1M
GLM-5.3-Flash
Input$0.20/1M
Cache read$0.04/1M
Output$0.70/1M
Context1M
DeepSeek V4.1 Flash
Input$0.12/1M
Cache read$0.008/1M
Output$0.80/1M
Context1M
DeepSeek V4.1 Flash 1017
Input$0.12/1M
Cache read$0.008/1M
Output$0.80/1M
Context1M
DeepSeek V4.1 Flash AbliteratedFastGated
Input$0.30/1M
Cache read$0.03/1M
Output$1.20/1M
Context1M
| Model | Input | Cache Read | Output | Context |
|---|---|---|---|---|
Kimi K3.1 ProFeatured | $2.50/1M | $0.29/1M | $14.00/1M | 1M |
GLM-5.3 744B | $1.19/1M | $0.20/1M | $6.00/1M | 1M |
GLM-5.3-Flash | $0.20/1M | $0.04/1M | $0.70/1M | 1M |
DeepSeek V4.1 Flash | $0.12/1M | $0.008/1M | $0.80/1M | 1M |
DeepSeek V4.1 Flash 1017 | $0.12/1M | $0.008/1M | $0.80/1M | 1M |
DeepSeek V4.1 Flash AbliteratedFastGated | $0.30/1M | $0.03/1M | $1.20/1M | 1M |
Specialized Models
Purpose-built APIs that offload the bottlenecks: code editing, search, context management, and per-turn classification.
Fast Apply
Merges LLM code edits into files at 98% accuracy.Fastest model
Price
$0.80in$1.20out/1M
Context262k
Most diversePopular
Price
$0.90in$1.90out/1M
Context262k
Code Search
Agentic repo search. #1 on SWE-Bench Pro.Fast context for agentsNew
Price
$0.80/100K
Context100K (1M for Pro)
Compaction
Verbatim context compression, shrinking context 50–70%.Verbatim context compaction
Price
$0.20in$0.50out/1M
Context1M
System One
Typed decisions: a state in, a probability distribution per question out.Typed decisions, no generationNew
Price
$0.042in$0.002cached/1M
Context64K
| Model | Price | Context | |
|---|---|---|---|
Fast Apply Merges LLM code edits into files at 98% accuracy. | |||
Fastest model | $0.80in$1.20out/1M | 262k | Try |
Most diversePopular | $0.90in$1.90out/1M | 262k | Try |
Code Search Agentic repo search. #1 on SWE-Bench Pro. | |||
Fast context for agentsNew | $0.80/100K | 100K (1M for Pro) | Try |
Compaction Verbatim context compression, shrinking context 50–70%. | |||
Verbatim context compaction | $0.20in$0.50out/1M | 1M | Try |
System One Typed decisions: a state in, a probability distribution per question out. | |||
Typed decisions, no generationNew | $0.042in$0.002cached/1M | 64K | |
Router
What is the Router?Difficulty-based model routing
Price$0.005/request
Context—
| Model | Price | Context |
|---|---|---|
Difficulty-based model routing | $0.005/request | — |
Our fastest endpoints are private deployments
Over 1 trillion tokens per day served on dedicated capacity with custom speculators and caching, at large discounts over the public pricing above. Includes SSO, custom rate limits, and priority support.
Get in touch