Pricing.
Nine models at public list prices. Pay per token. No subscription, no minimum.
Price list
| Model | Context | In | Out | Cache write | Cache read |
|---|---|---|---|---|---|
avelin-fastChat, fast | 256K | $0.30 | $1.20 | $0.38 | $0.03 |
avelin-proChat, pro | 256K | $1.40 | $4.40 | $1.75 | $0.26 |
avelin-ultraChat, ultra | 256K | $2.50 | $12.50 | $3.13 | $0.52 |
avelin-coding-fastCoding, fast | 1M | $0.30 | $1.20 | $0.38 | $0.03 |
avelin-coding-proCoding, pro | 1M | $1.40 | $4.40 | $1.75 | $0.26 |
avelin-coding-ultraCoding, ultra | 1M | $2.50 | $12.50 | $3.13 | $0.52 |
avelin-agentic-fastAgents, fast | 256K | $0.285 | $1.14 | $0.36 | $0.0285 |
avelin-agentic-proAgents, pro | 256K | $1.26 | $3.96 | $1.58 | $0.23 |
avelin-agentic-ultraAgents, ultra | 256K | $2.38 | $11.88 | $2.98 | $0.49 |
USD per 1M tokens, list price, as of 3 Oct 2026. A repeated prompt prefix is billed once at the cache write rate and then at the lower cache read rate. The API publishes the same prices as machine-readable JSON. Audio, image and web endpoints are in the full reference.
Chat and coding share list prices, and coding has the longer context window. The agents tiers have their own, slightly lower, list prices. The nine models are described on the models page.
Decision Layer and enterprise
The Decision Layer is priced per request and quoted in a POC. Sharing is opt-in and off by default: how sharing works.
Enterprise and on-premise deployments are priced in a written scope: sovereign AI platform, private deployment.
Estimate a task
Cost per task is the formula on the Method page. Enter the shape of one task, and the table prices it at each list price.
An agent task often makes several.
Prompt, history and tool results.
Include reasoning tokens: they bill as output.
A number from 0 to 100. Enter 0 to price every input token at the input rate.
Compare with what you pay today
Your provider's list price, or your own effective rate.
Needed with the price in.
Leave empty to price cached tokens at your input price.
The table then adds your price and shows the difference as plain arithmetic on the numbers you typed. It is not a savings claim: it does not say whether a tier does your task as well.
Blend tiers
One family, three tiers.
Any numbers: 6, 3 and 1 means six in ten.
Leave a tier empty for none.
The shares are scaled to add up.
| Model | One task | 1,000 tasks |
|---|---|---|
avelin-fastChat, fast. $0.30 in, $1.20 out | $0.0054 | $5.40 |
avelin-proChat, pro. $1.40 in, $4.40 out | $0.0234 | $23.40 |
avelin-ultraChat, ultra. $2.50 in, $12.50 out | $0.0488 | $48.75 |
avelin-coding-fastCoding, fast. $0.30 in, $1.20 out | $0.0054 | $5.40 |
avelin-coding-proCoding, pro. $1.40 in, $4.40 out | $0.0234 | $23.40 |
avelin-coding-ultraCoding, ultra. $2.50 in, $12.50 out | $0.0488 | $48.75 |
avelin-agentic-fastAgents, fast. $0.285 in, $1.14 out | $0.0051 | $5.13 |
avelin-agentic-proAgents, pro. $1.26 in, $3.96 out | $0.0211 | $21.06 |
avelin-agentic-ultraAgents, ultra. $2.38 in, $11.88 out | $0.0464 | $46.38 |
Price a log of your own tasks
Have a log of your own model calls? Load it and it is priced at each list price, per call and per task, beside what you paid if the log has a cost column. It is the same arithmetic as the estimator, run on your numbers, in your browser. A POC starts from a sample like this one.
JSON Lines, a JSON array or CSV, one row per model call. It needs input and output token counts (prompt_tokens and completion_tokens, or input_tokens and output_tokens). Optional: cached tokens, a task id to group calls, and the cost you paid. The file is read in your browser. Nothing is uploaded.
Controls
A budget and rate limits on every key.
A workload or a team can be capped on its own key. A key's budget and rate limits are applied before a request is answered.
Live usage and spend.
Usage is recorded per key, with budget alerts.
One list price per model.
You pay the list price of the model that answers.
Billing terms
These are the billing terms in the API terms of service, which control if this page differs.
- Usage is billed per token at the published prices in effect at the time of use.
- Usage is charged at the end of each billing period or drawn from prepaid credits, depending on how your account is set up.
- Fees are exclusive of taxes.
- Fees and prepaid credits are non-refundable, except where an order is cancelled or the law requires a refund.
- Published prices and payment terms can change for future use, and a change takes effect when it is posted. A change does not affect usage that has already happened.
- There is no guaranteed service level unless one is agreed in a separately signed agreement.
For invoicing, purchase orders, volume terms or committed-use pricing, ask in your POC request: a signed agreement controls over these terms, and a POC scope states the prices it uses. Private deployments are priced per deployment: Private deployment.
Model calls are billed at the list price of the tier that answers. The Decision Layer is priced separately, per request, and quoted in a POC.
Next step
Send one workload and we price it at list beside your current bill. Or start on your own: change the base URL, and leave by changing it back.
Questions about pricing
What do the AVELIN models cost?
You pay per token at public list prices, with no subscription and no minimum. Input prices run from $0.285 to $2.50 per 1M tokens, and output prices from $1.14 to $12.50, as of 3 Oct 2026.
How is cost per task counted?
Cost per task is the sum of every model call a task makes, each priced at list price: tokens in and out multiplied by the published rate, with cached tokens at the cache rate. Agents make many calls per task, so price per token alone hides the bill.
What are cache write and cache read rates?
A repeated prompt prefix is billed once at the cache write rate and then at the lower cache read rate. Both rates are in the price list for every model.
What does a deployment on our own GPUs cost?
Enterprise and on-premise deployments are priced in a written scope. AVELIN Cloud has public list prices.
Bring one workload. See its cost per task.
Start with a POC on one of your workloads.