KymaKyma
Alibaba

Alibaba

Qwen 3.7 Max

Alibaba's newest closed-weight flagship, carrying a 1M-token context window with top-tier reasoning and multilingual strength. Reach for it when the job is too large or too hard for everyday-tier models.

Modalities

Text → Text

Input

$2.56 /1M

Output

$7.676 /1M

Cached input

$0.256 /1M90% off

Context

1M

Speed

medium

Performance

Live production data from real requests on Kyma — not synthetic benchmarks.

Rank

#23

of 87 active models

Tokens served

3.8M

all-time

Success rate

100%

last 7 days

Median throughput50 tok/s
Total requests513
Platform share0.2%
Tokens · last 15 daysJul 19 → Aug 2

Top apps using this model

1Node.js App282.2K tok
2Claude Code194.4K tok

Public apps sending the most traffic to this model — a signal of what real workloads it fits.

Pricing

Pay per token. Cached input is billed at 10% of the input rate.

$2.56 /1M input$7.676 /1M output
Hobby10 req/day · 2K in / 500 out
~$2.69/mo
Production1,000 req/day · 2K in / 500 out
~$269/mo
Scale20,000 req/day · 2K in / 500 out
~$5,375/mo
+ Estimate your workload
1,000
2,000
500
30%

Estimated monthly cost

$227

$7.58 / day on Qwen 3.7 Max

Same workload on:

Qwen 3.7 Flash$5.73-97%
Qwen 3.6 Plus$65.82-71%

Estimates use list pricing with cached input billed at the 90%-discount rate. Actual bills depend on real token counts — every response includes its exact cost.

When to use Qwen 3.7 Max

Updated 2026-06-10

Where this model earns its cost — and where it doesn't.

Qwen 3.7 Max is Alibaba's newest closed-weight flagship — a premium model built for general work, reasoning, multilingual tasks, and long context. It is the model to pick when output quality matters more than cost per token.

On Kyma it runs through the same OpenAI-compatible endpoint as every other model, with automatic failover rerouting requests if a serving path degrades. Prompt caching is supported, so workloads that resend a long system prompt or document prefix pay 10% of the input rate on the repeated part — which matters at premium pricing. Every response reports its exact cost in usage.cost.

The 1M-token context window pairs with function calling, structured outputs, and extended reasoning, with up to 32K tokens of output per request. It is text-in, text-out only — no image inputs.

Hard reasoning problems

Extended reasoning works through math, planning, and analysis tasks where step-by-step thinking decides the outcome.

Whole-corpus analysis

The 1M context takes entire codebases, document sets, or transcript archives in one request instead of a retrieval pipeline.

Multilingual production work

Translation, localization, and cross-language analysis where quality has to hold up beyond English.

High-stakes coding

Code review, architecture decisions, and complex refactors where a premium model earns its rate.

Structured agent pipelines

Function calling plus structured outputs keep multi-step agents reliable on long-horizon tasks.

Not ideal for: Image inputs (it's text-only — pick a vision model), and high-volume or latency-sensitive workloads, where its premium pricing and medium speed make a cheaper, faster tier the better fit.

How it compares

Against the peers people actually weigh it against.

SpecQwen 3.7 MaxQwen 3.7 FlashQwen 3.6 Plus
Input /1M$2.56$0.0458$0.4388
Output /1M$7.676$0.1987$2.633
Context1M1M131K
ToolsYesYesYes
ReasoningYesYesYes
Speedmediumfastmedium

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit, no card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-3.7-max",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-3.7-max",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Qwen 3.7 Max?

Qwen 3.7 Max has a 1M-token context window — roughly 1471 pages of text in a single request.

How much does the Qwen 3.7 Max API cost?

$2.56 per 1M input tokens and $7.676 per 1M output tokens, with cached input at $0.256/1M — a 90% discount on repeated prompt prefixes. No subscription; you pay only for what you use.

Does Qwen 3.7 Max support function calling?

Yes — Qwen 3.7 Max supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

How do I use Qwen 3.7 Max?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to qwen-3.7-max. Signing up is free and includes $0.50 of credit — no card required.

How fast is Qwen 3.7 Max in production?

It sits in the medium speed tier, with a median of 62 tokens per second on recent Kyma production traffic and a 100% success rate over that window. Automatic failover reroutes requests if a serving path degrades, so a single bad path doesn't take your requests down.

Is Qwen 3.7 Max worth its premium price?

For the right workloads, yes: tasks that span huge inputs, demand careful multi-step reasoning, or run in multiple languages benefit from the flagship tier. Prompt caching softens the bill — repeated prompt prefixes cost 10% of the input rate — and usage.cost in every response shows exactly what each call cost, so you can verify the trade-off on your own traffic.

Why use Qwen 3.7 Max through Kyma?

One API key and one OpenAI-compatible endpoint cover this and every other model on the platform. You get automatic failover when a serving path has issues, prompt caching at a 90% discount on repeated input, transparent per-request cost reporting, and $0.50 of free credit at signup — no card required.

Start with $0.50 free credit — no card required.Create account →

More models by Alibaba

ModelContextInputOutput
AlibabaQwen 3.7 Flash1M$0.0458$0.1987
AlibabaQwen 3.7 Plus1M$0.4482$1.793
AlibabaQwen 3.6 Plus131K$0.4388$2.633
AlibabaQwen 3 Coder131K$0.297$1.35
AlibabaQwen3 Embedding 8B33K$0.0135$0.00
AlibabaQwen 3 32B33K$0.108$0.378