Qwen3.7 Max
Qwen3.7 Max is the flagship of Alibaba's Qwen3.7 series, a text model designed for agent-centric workloads in coding, office productivity, and autonomous execution.
input · usd / 1m tok
$2.50
output · usd / 1m tok
$7.50
context window
1.05mtokens
modalities · in → out
takes text in, gives text out
pricing
base api ratesusd per 1m tokens
- input
- $2.50
- output
- $7.50
- cache read
- $0.50
providers
Qwen hosts Qwen3.7 Max. Impossibl routes your request intelligently and handles failover automatically when a provider is down.
- Qwen
specifications
takes text in, gives text outqwen/qwen3.7-max
- creatorQwen
- model typeText generation
- context window1,048,576 tokens
- maximum outputnot published
- input
takes text in, gives text out
- outputtext
- tool callingnot verified
- releasedmay 21, 2026
- endpoint
/v1/chat/completions
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
try it · your prompt, this model, live
# responses API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["IMPOSSIBL_API_KEY"],
base_url="https://api.impossibl.com/v1",
)
resp = client.responses.create(
model="qwen/qwen3.7-max",
input="",
)
print(resp.output_text)
edit the prompt, then run
benchmarks
intelligence index
29.9#35 of 90 models on the gateway
- coding index66.0#32 of 60
- agentic index23.9#34 of 49
- omniscience13.5#21 of 86
- gpqa92.3%#21 of 88
- humanity’s last exam40.5%#28 of 89
- terminal-bench v2.174.5%#31 of 57
- Tau294.7%
- GPQA92.3%
- Harvey LAB83.4%
- IFBench80.5%
- AA-LCR79.0%
- Terminal-Bench v2.174.5%
- Terminal-Bench Hard50.8%
- SciCode49.5%
- ITBench42.5%
- Humanity’s Last Exam40.5%
- AutomationBench Partial23.0%
- AnalystAgent18.8%
- CritPt13.4%
- Tau Banking11.8%
- GDP.pdf All-pass8.6%
- Terminal-Bench v4.01.5%
- Intelligence Index29.87
- Omniscience Index13.48
- GDPval Elo1189.86
- coding index (API)66
- agentic index (API)23.9
- intelligence index (API)29.9
each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-09-11.
compare Qwen3.7 Max with other models
frontier labs and open weights, best-ranked firstusd / 1m tok · in / out
- anthropic/claude-fable-5-1$10.00 / $50.00compare →
- openai/gpt-6-astra$10.00 / $50.00compare →
- meta/muse-spark-1.3$1.25 / $4.25compare →
- zai/glm-5.3$1.40 / $4.40compare →
frequently asked questions
What is Qwen3.7 Max?
Qwen3.7 Max is the flagship of Alibaba's Qwen3.7 series, a text model designed for agent-centric workloads in coding, office productivity, and autonomous execution. It ships with thinking mode enabled by default and supports explicit caching for repeated prompts.
How much does Qwen3.7 Max cost?
Qwen3.7 Max costs $2.50 per million input tokens and $7.50 per million output tokens through the Impossibl API. Cache reads cost $0.50 per million tokens. All rates are in USD.
What is the context length of Qwen3.7 Max?
Qwen3.7 Max has a 1,048,576-token context window through the Impossibl API.
What inputs and outputs does Qwen3.7 Max support?
Qwen3.7 Max accepts text as input. Qwen3.7 Max returns text.
How do I use Qwen3.7 Max through an API?
Qwen3.7 Max is available through the Impossibl API. Use qwen/qwen3.7-max as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
When was Qwen3.7 Max released?
Qwen released Qwen3.7 Max on May 21, 2026.
this page describes Qwen3.7 Max as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.
view the source catalog ↗model as markdown ↗report a correction →