How much does Qwen3.8 Max cost on Velqa?

Qwen3.8 Max costs $2.350 per million input tokens and $7.050 per million output tokens, in USD. It is sold outside the plans, per token, on Boost credit.

Can I use Qwen3.8 Max without a subscription?

Yes. Qwen3.8 Max can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.

Is Qwen3.8 Max compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "qwen3.8-max" — Qwen3.8 Max answers on the standard chat completions endpoint, streaming included.

Qwen3.8 Max API — pricing and access

Flagship 2.4T — code et travail pro, hors forfait

Input: $2.350 USD / 1M tokens
Output: $7.050 USD / 1M tokens
Context: 256k
Available on: Boost credit (pay as you go)
Provider: Alibaba

Qwen3.8 Max is the flagship of the Qwen family, positioned for code and demanding professional work. It isn't included in any plan: it's billed per token on Boost credit, which makes it an occasional pick rather than a default model — complex code generation, in-depth review, tasks where quality outweighs the cost per call.

Against Qwen3.7 Max, its smaller sibling in the same family but included in the Pro plan at a noticeably lower price, Qwen3.8 Max only makes sense when the task genuinely exceeds what Qwen3.7 Max delivers: in most cases Qwen3.7 Max is enough and costs less. Against Kimi K3, another out-of-plan model in a similar price range, Qwen3.8 Max stands out for its code and professional-work focus, while Kimi K3 leans on a far wider context window.

It is not the right choice for everyday use covered by a subscription: Qwen3.7 Max, included in the Pro plan, or DeepSeek V4 Pro cover most needs on a predictable budget, without per-token billing.

Measured on Velqa

Time to first token: 1.56 s
Throughput: 48.9 tokens/s

Median of 5 streamed calls against api.velqa.dev, 2026-08-10.

Results announced by the provider

SWE-bench Pro : 67.7 source (2026-08-03)

Call it

OpenAI-compatible endpoint — change the base URL and the model id, nothing else.

curl https://api.velqa.dev/v1/chat/completions \
  -H "Authorization: Bearer $VELQA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.8-max",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does Qwen3.8 Max cost on Velqa?: Qwen3.8 Max costs $2.350 per million input tokens and $7.050 per million output tokens, in USD. It is sold outside the plans, per token, on Boost credit.
Can I use Qwen3.8 Max without a subscription?: Yes. Qwen3.8 Max can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.
Is Qwen3.8 Max compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "qwen3.8-max" — Qwen3.8 Max answers on the standard chat completions endpoint, streaming included.