$149/week
- No monthly token cap
- Run agents for as long as you need
- Keeps a baseline at peak hours
- One developer per subscription
- Switch to Monthly any time; unused days credited
Pay per token with Standard One or the Standard API. Product Plan prices are indicative and confirmed in your order before paid use.
Choose a size and pay per input token. Each answer is a short value, so output is free.
Estimate your monthly Standard One cost.
Enter zero or more text and image tokens to update the estimate.
$2.35 / month
Planning estimate only. Actual charges follow metered usage and exclude tax and separately agreed services.
Usage is metered after requests complete; prepaid credits do not impose a hard spending cap. Charges for accepted requests may post after completion, and future prices may change prospectively under the Terms.
Compare input, output, and cache-read rates for each model. The Standard API is available; model access depends on your workspace and current capacity. A listed model may be unavailable or not yet released.
| Model | Input / 1M tokens | Output / 1M tokens | Cache read / 1M tokens | Context window |
|---|---|---|---|---|
| our price $0.24 | our price $0.96 | our price $0.0048 | 1.05M | |
| our price $1.40 | our price $4.40 | our price $0.26 | 1.05M | |
| 1.05M | ||||
| our price $0.037 | our price $0.17 | — | 131K | |
| our price $0.25 | 1.05M | |||
| our price $1.056 | our price $3.168 | our price $0.0352 | 1.05M | |
| 1.05M | ||||
| 262K |
Estimate your monthly API cost.
Estimate a chat or agent workloadEnter zero or more input and output tokens to update the estimate.
$4.56 / month
Planning estimate only. Actual charges follow metered usage and exclude tax and separately agreed services.
A unit is one model’s base allocation of output throughput. Choose how many units you keep all month, and add more for busy periods in 2-hour blocks.
$1,200 per unit, per model, per month
Reserved capacity on one model, available through the month under the conditions in your order.
Example: two units of GLM-5.3 are $2,400 a month.
$5 per extra unit, per 2-hour period
Extra units you add on top of your base during a traffic peak, billed only for the 2-hour periods they run.
Example: one extra unit for a 6-hour peak is $15.
Estimate your monthly Product Plan cost.
$1,205 / month
Planning estimate, before tax. Extra peak periods in the month are charged separately. For an estimate from your own traffic, use the Product Plan capacity calculator.
What one busy day looks like.
Your base runs all month. Each peak block is one 2-hour period of auto scaling on top of it.
Monthly baseAuto scaling
Auto scaling requires your authorization and available capacity. Billing is monthly with a one-month minimum; adding units mid-month charges only the prorated difference for the rest of the month.
| Charge | Price | What it covers |
|---|---|---|
| Kimi K3 allocation | $1,200 per unit, per model, per month | 80 aggregate output tokens per second. |
| GLM-5.3 allocation | $1,200 per unit, per model, per month | 135 aggregate output tokens per second. |
| DeepSeek V4.1 Flash allocation | $1,200 per unit, per model, per month | 550 aggregate output tokens per second. |
| Three-model bundle | $3,000 per month | One allocation each of Kimi K3, GLM-5.3, and DeepSeek V4.1 Flash. Save $600 per month compared with three individual plans. |
| Free extra capacity | No extra charge | Capacity above your base only while the shared pool has room. It is not reserved. |
| Auto scaling | $5 per extra unit, per two-hour period | Auto scaling adds capacity for traffic peaks after your authorization, subject to availability and plan terms. |
Current lineup: Kimi K3, GLM-5.3, and DeepSeek V4.1 Flash; model selection may change under the terms. $149 per 7-day period or $549 per 30-day period, per developer. No monthly token allowance.
Access configuration, queueing, model selection, billing, and training terms are described in the Coding Plan terms.
Tell us whether you are building an application or choosing a coding plan.
Estimate API cost from input and output tokens. For a Product Plan, choose a model allocation and account for auto scaling charges. Compare service conditions as well as the total. How to buy AI inference for a product walks through the comparison.
A plan for one developer, with the current lineup of Kimi K3, GLM-5.3, and DeepSeek V4.1 Flash. $149 per week or $549 per 30-day period. No 5-hour window, weekly quota, or monthly token allowance; requests may be slower at peak hours. Model selection and access configuration may change under the terms. Request access
Account creation, product access, and plan activation are separate steps. Check access and plan conditions before activation.