Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

Qwen/Qwen3-Max-Thinking pricing

The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques Qwen/Qwen3-Max-Thinking from DeepInfra costs $1.20 per 1M input tokens and $6.00 per 1M output tokens. Cached input is $0.240 per 1M. Context window 256,000 tokens.

API id Qwen/Qwen3-Max-Thinking · DeepInfra · source · updated 2026-09-25 · general-purpose

$1.20
Input / 1M tokens
$6.00
Output / 1M tokens
$0.240
Cached input / 1M
256K
Context window

Qwen/Qwen3-Max-Thinking specifications

Provider
DeepInfra
API id
Qwen/Qwen3-Max-Thinking
Model type
general-purpose
Context window
256K tokens
Max output
not published
Currency
USD
Price source
Provider API
Last checked
2026-09-25

Tags

  • flagship
  • reasoning

Qwen3 Max Thinking across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

ProviderInput /1MCached /1MOutput /1M1M in + 1M outvs vendor
Alibaba (Qwen)VendorCheapest
$0.780—$3.90$4.68—
$0.780—$3.90$4.68—
DeepInfraHostviewing
$1.20$0.240$6.00$7.20+54%

What Qwen/Qwen3-Max-Thinking costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0042
Document summary50,0002,000$0.07
1M tokens in, 200K out1,000,000200,000$2.40

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does Qwen/Qwen3-Max-Thinking cost per 1M tokens?
Qwen/Qwen3-Max-Thinking costs $1.20 per 1M input tokens and $6.00 per 1M output tokens on the standard tier. Cached input is $0.240 per 1M.
What is Qwen/Qwen3-Max-Thinking's context window?
Qwen/Qwen3-Max-Thinking accepts up to 256,000 tokens in a single request.
Is there a cheaper DeepInfra model than Qwen/Qwen3-Max-Thinking?
Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $1.20 for Qwen/Qwen3-Max-Thinking, with a 1,048,576 token context window.
Where does this Qwen/Qwen3-Max-Thinking price come from?
From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.

Head-to-head comparisons

Other DeepInfra models

See all DeepInfra pricing →