How much does Qwen3.7 Max cost on Velqa?

Qwen3.7 Max costs $1.630 per million input tokens and $4.870 per million output tokens, in USD. It is available on the Pro plan.

Can I use Qwen3.7 Max without a subscription?

Yes. Qwen3.7 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 Qwen3.7 Max compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "qwen3.7-max" — Qwen3.7 Max answers on the standard chat completions endpoint, streaming included.

Qwen3.7 Max API — pricing and access

Raisonnement premium, contexte 256k

Input: $1.630 USD / 1M tokens
Output: $4.870 USD / 1M tokens
Context: 256k
Available on: Pro
Provider: Alibaba

Qwen3.7 Max is a premium reasoning model, restricted to the Pro plan, built for tasks where context window matters as much as reasoning depth: reviewing a very large legal or financial file, analyzing code across a whole repository, synthesizing multiple long sources. Its 256k window is the widest among reasoning models included in a subscription plan — Kimi K3 goes further, at 1M, but sits outside any plan on Boost credit.

Against DeepSeek V4 Pro, its direct competitor at the same Pro tier and a very close price, the gap comes down to context: 256k versus 160k, a clear edge for a very large document. Against Qwen3.8 Max, its bigger sibling in the same family but outside any plan, Qwen3.7 Max stays the default as long as the budget needs to sit inside a fixed subscription rather than pay-per-token.

It is not the right choice for high-volume chat: the cost per token is high for that case, and GLM-4.7 or DeepSeek V4 Flash cover it for much less. It also isn't a specialized coding model: for agentic development sessions, Kimi K2.6 remains better suited.

Measured on Velqa

Time to first token: 1.33 s
Throughput: 56.6 tokens/s

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

Results announced by the provider

SWE-bench Verified : 80.4 source (2026-05-21)

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": "qwen3.7-max",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does Qwen3.7 Max cost on Velqa?: Qwen3.7 Max costs $1.630 per million input tokens and $4.870 per million output tokens, in USD. It is available on the Pro plan.
Can I use Qwen3.7 Max without a subscription?: Yes. Qwen3.7 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 Qwen3.7 Max compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "qwen3.7-max" — Qwen3.7 Max answers on the standard chat completions endpoint, streaming included.