Alibaba Cloud (Qwen) · API pricing

Qwen API pricing

6 Qwen models on one OpenAI-compatible API, billed per token from a prepaid balance — no subscription. From €0.0252 per 100k input tokens and €0.0773 per 100k output tokens, margin and VAT included. Qwen3 Coder 30B, Qwen3.6 35B A3B, Qwen3.5 397B, Qwen3.8 27B and Qwen3 235B run on EU-sovereign infrastructure; Qwen3.8 Flash is fast access, through US providers.

Models live
6
Input from
€0.0252
per 100k tokens
Output from
€0.0773
per 100k tokens
Largest context
1M
Qwen3.8 Flash

Qwen API pricing per model

per 100k tokens · margin and VAT included · from our live catalog when this page is built

ModelInputOutputCached inContextMax outputJurisdiction
Qwen3.8 Flash
qwen3.8-flashtoolsvision
€0.0252€0.0773—1M—Fast access (US)
Qwen3 Coder 30B
qwen3-coder-30btools
€0.0336€0.1344—256K—EU sovereign
Qwen3.6 35B A3B
qwen3.6-35btoolsvision
€0.0420€0.2520—256K32KEU sovereign
Qwen3.5 397B
qwen3.5-397btoolsvision
€0.1008€0.6048—250K16KEU sovereign
Qwen3.8 27B
qwen3.8-27btoolsvision
€0.1008€0.5544€0.0202256K—EU sovereign
Qwen3 235B
qwen3-235btools
€0.1260€0.3780—250K16KEU sovereign
Qwen3.6 27B
qwen3.6-27btoolsvisiontemporarily paused since 2026-10-20
€0.0672€0.4536—256K—EU sovereign
Qwen3.5 9B
qwen3.5-9btoolsvisiontemporarily paused since 2026-10-20
€0.0168€0.0252—256K—EU sovereign
Qwen2.5-VL 72B
qwen2.5-vl-72bvisiontemporarily paused since 2026-10-20
€0.1529€0.1529—32K—EU sovereign
Qwen3.8 Max
qwen3.8-maxtemporarily paused since 2026-09-23
€0.3024€0.9072—1M—Fast access (US)

Input, output and cached input are the prices debited from your prepaid balance per 100,000 tokens, margin and VAT included. Context is the window as served on Frontière AI; max output is the provider's cap on max_tokens (— when it sets none we know of). Tool calling is measured with a real call per model.

Where each Qwen model runs, and what Qwen's own API does with your data →

Qwen API cost calculator

Pick a model and a workload, or type your own token counts: the estimate uses the prices in the table above, margin and VAT included.

Example workload

Roughly 1,000 tokens ≈ 750 English words.

No discounted cache rate on this model: every input token is billed at the input rate.

Per request

€0.00097

Per day

€0.9744

Per month

€29.23

30 days

A €10 top-up covers about 10,262 requests · Qwen3 Coder 30B

Where the money goes

  • Input€15.12 · 52%
  • Output€14.11 · 48%

Estimate, margin and VAT included, from the prices on this page. You are billed on the tokens the provider reports for each call, debited from a prepaid balance — no subscription.

Same workload on every model

ModelPer month
Qwen3.8 FlashFast access (US)€19.45
Qwen3 Coder 30BEU sovereign€29.23Selected
Qwen3.6 35B A3BEU sovereign€45.36
Qwen3 235BEU sovereign€96.39
Qwen3.8 27BEU sovereign€103.57
Qwen3.5 397BEU sovereign€108.86

Call Qwen models

The API is OpenAI-compatible: keep your SDK, change base_url and the key, and pass the model id. One key covers the whole catalog.

curl https://getfrontiereai.eu/api/v1/chat/completions \
  -H "Authorization: Bearer $FRONTIERE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-coder-30b",
    "messages": [{"role": "user", "content": "Bonjour"}]
  }'
API reference →

Frequently asked

How much does the Qwen API cost?

On Frontière AI, Qwen models cost from €0.0252 to €0.126 per 100,000 input tokens and from €0.0773 to €0.6048 per 100,000 output tokens, depending on the model — margin and VAT included, that is the amount debited from your prepaid balance. The table lists each model's price; the calculator turns it into a monthly cost for your workload.

Which Qwen model is the cheapest?

Qwen3.8 Flash, the cheapest on both input (€0.0252) and output (€0.0773) per 100k tokens.

Which Qwen model has the largest context window?

Qwen3.8 Flash, with 1M tokens of context as served on Frontière AI.

Is the Qwen API hosted in Europe on Frontière AI?

Partly. Scaleway (France) for Qwen3 Coder 30B, Qwen3.6 35B A3B, Qwen3.5 397B, Qwen3.8 27B and Qwen3 235B: these are labeled EU sovereign. Qwen3.8 Flash is served by US providers and labeled fast access — the API flags it before you call.

Is there a subscription or a minimum spend?

No subscription. You top up a prepaid balance from €10 and each call is debited at the per-token price. Calls are refused once the balance reaches zero; a call already running can take it slightly below — deducted from your next top-up.

Do I need to change my code to call Qwen models?

No, if your code already uses an OpenAI SDK: point base_url at https://getfrontiereai.eu/api/v1, use a Frontière AI key and pass the model id, for example “qwen3-coder-30b”. Streaming and tool calling are relayed as-is.

How are cached input tokens billed?

Qwen3.8 27B has a discounted rate for prompt tokens the provider serves from its cache (€0.0202 per 100k tokens on Qwen3.8 27B). The provider reports these tokens on each call and we bill them at that rate; on a model without a cache rate, every input token is billed at the input rate.

Other providers

Per-token prices for every publisher in our catalog

All model prices on one page →

Start calling Qwen in minutes

Create an account, top up €10, change two lines of code.

Create an account