Qwen3.7 Max vs Qwen3.8 Max

As of October 21, 2026, Qwen3.7 Max costs 25% more per input token than Qwen3.8 Max ($2.50 vs $2.00 per 1M), and both have a 992K-token context window.

Prices from LiteLLM's price fileChecked October 21, 2026

Qwen3.7 Max vs Qwen3.8 Max side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of October 21, 2026.
	Qwen3.7 Max	Qwen3.8 Max
Input, per 1M tokens	$2.50	$2.00
Output, per 1M tokens	$7.50	$6.00
Cache read, per 1M tokens	$0.50	$0.25
Cache write, per 1M tokens	$3.125	–
Context window	991,808 tokens	991,808 tokens
Max output	65,536 tokens	131,072 tokens
Image input	–	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	6	8
Price shown is from	Alibaba Cloud Model Studio	Alibaba Cloud Model Studio
Added to LiteLLM	July 29, 2026	August 7, 2026

Cheapest provider for each

Qwen3.7 Max: Novita AI at $1.25 input and $3.75 output per 1M tokens (novita/qwen/qwen3.7-max)
Qwen3.8 Max: DeepInfra at $1.65 input and $4.951 output per 1M tokens (deepinfra/Qwen/Qwen3.8-Max)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of August 27, 2026. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	Qwen3.7 Max	Qwen3.8 Max
Reasoning and knowledge
GPQA Diamond	90.9%	92.7% (xhigh)
SimpleQA Verified	55.8%	45.8% (xhigh)
Math
FrontierMath (tiers 1-3)	64.6%	74.7% (xhigh)
FrontierMath (tier 4)	34.1%	46.3% (xhigh)
OTIS Mock AIME 2024-2025	95.6%	99.4% (xhigh)

When to pick which

Pick Qwen3.8 Max for

Costs 20% less per input token: $2.00 vs $2.50 per 1M.
Returns up to 131,072 tokens per response, vs 65,536.

From differences in the data above only; where the data is equal, no reason is given.

Call Qwen3.7 Max or Qwen3.8 Max with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# Qwen3.7 Max
response = completion(model="dashscope/qwen3.7-max", messages=messages)

# Qwen3.8 Max
response = completion(model="dashscope/qwen3.8-max", messages=messages)

# Qwen3.7 Max, falling back to Qwen3.8 Max if the call fails
response = completion(model="dashscope/qwen3.7-max", messages=messages, fallbacks=["dashscope/qwen3.8-max"])

FAQ

Which is cheaper, Qwen3.7 Max or Qwen3.8 Max?

Qwen3.8 Max is cheaper at 3 input tokens per output token: $3.00 per 1M tokens blended ($2.00 input, $6.00 output), versus $3.75 ($2.50 and $7.50) for Qwen3.7 Max, as of October 21, 2026.

Which has the larger context window, Qwen3.7 Max or Qwen3.8 Max?

Both have a 991,808-token context window.

Can I switch from Qwen3.7 Max to Qwen3.8 Max without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "dashscope/qwen3.7-max" to "dashscope/qwen3.8-max", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.