Pay per token, from a prepaid balance
Modellane prices per 1M tokens for input, cached input and output, charged from a prepaid balance. No subscription required.
/pricing
No seats and no minimums. Start with a one-time top-up or take a monthly plan; every request is charged from your balance at the model's per-token rate.
Top-ups and plans
Top-ups
Pay as you go. Add balance with a one-time payment and spend it at per-token rates. No subscription, no minimum monthly spend.
Packages
- $30
- $50
- $100
- $200
Plans
Monthly. An optional monthly plan adds a plan balance each period that is spent before your top-up balance.
- Modellane Starter $25 / month, $30 plan balance each period · 16% off
- Modellane Pro $50 / month, $60 plan balance each period · 16% off
Top-up credit equals the amount paid and does not expire. Plan balance is spent first and resets each period. Payments are processed by our merchant of record.
/rates
Every model, every rate.
Each model has an input, a cached-input and an output rate. The same rates apply in all three API formats.
| Model | API id | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
| GLM-5.3 Unrestricted | glm-5.3-unrestricted | 1M | $6.00 | $0.60 | $10.00 |
| Qwen3.5 Unrestricted | qwen3.5-unrestricted | 256K | $2.00 | $0.20 | $6.00 |
Reasoning tokens are billed as output. Cached input applies when a prompt prefix is served from cache.
/billing
How a request is billed.
Your balance is checked before the model runs and charged once, when the response is finished. You never pay for more than the request used.
Add balance
top-up or plan. Top up once or subscribe. Plan balance is spent first, then top-up credit.
Hold
before the model runs. We hold the most the request could cost: up to one token per byte of prompt text plus max_tokens of output. A lower max_tokens keeps the hold small.
Charge
when it finishes. Actual usage is charged and the rest of the hold is released. A request that fails before any content reaches you costs nothing.
What counts as a token
Cached input
When the start of a prompt matches a prefix processed recently, those input tokens are billed at the cached-input rate instead of the full input rate. Long system prompts, tool definitions and shared documents placed first in the conversation benefit most.
Reasoning tokens
Some models think before they answer. Those reasoning tokens are counted as output and billed at the output rate, so a hard question can cost more output than the visible reply suggests.
Images
Images sent to a model with image input are converted to input tokens and billed at the input rate.
/faq
Billing questions
- How is usage billed?
- Per token, from your prepaid balance. Input, cached input and output tokens each have their own rate per 1M tokens, listed in the pricing table. Each request is charged once, when it finishes.
- What are cached input tokens?
- When a request starts with a prompt prefix that was processed recently, the matching input tokens can be served from cache and are billed at the lower cached-input rate. Keep long system prompts and shared context at the start of the conversation to make hits more likely.
- Are reasoning tokens billed?
- Yes. Tokens a model spends reasoning before its answer are billed as output tokens, at the output rate.
- Are there rate limits?
- Yes. Each project has a limit on concurrent requests and on requests per minute. Above it the API returns HTTP 429 and you can retry after a short pause. The current limits are in the Rate limits page of the docs.
- Can I get a refund?
- Refunds follow our Refund Policy, linked in the footer. Write to support with your project name and the time of the payment.