Qwen

Qwen3-235B-A22B

Qwen3's flagship open-weight MoE (235B total, 22B active), available across inference gateways in instruct and thinking snapshots.

ActiveReleased April 29, 2025Available from 15 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: Qwen (Alibaba Model Studio) pricing, Qwen models, Metadata verification, Field resolution verification

Price per 1M tokens
$0.2 in / $0.6 out
Context window262,144
Max output32,768
Input
  • Text
Output
  • Text
Priced across15 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.2 / M
Output$0.6 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$76.00
at current list prices
Fresh input$40.00
Output incl. thinking$36.00
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformRegionInput / MOutput / MCache read / MBatchAccess
Together AI
-$0.2$0.6--Direct
DeepInfraLowest
-$0.09$0.1--via OpenRouter
GMICloud
-$0.0875$0.35$0.0175-via OpenRouter
Novita
-$0.09$0.58--via OpenRouter
Alibaba
-$0.1495$0.598--via OpenRouter
Nebius
-$0.2$0.6--via OpenRouter
Together AI
-$0.2$0.6--via OpenRouter
Venice
-$0.15$0.75--via OpenRouter
Parasail
-$0.14$0.8$0.05-via OpenRouter
Friendli
-$0.2$0.8--via OpenRouter
Crusoe
-$0.22$0.8$0.11-via OpenRouter
StreamLake
-$0.21$0.84--via OpenRouter
AtlasCloud
-$0.2$0.88$0.2-via OpenRouter
AWS Bedrock
$0.22$0.88-✓Direct
Google
-$0.25$1--via OpenRouter

Some hosts price by region. Shown rates match the selected region.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.2 / $0.6 per 1M since May 6, 2026.

More from Qwen

Other models from the same provider.

Qwen3.8-Omni-Flash
qwen/qwen3.8-omni-flash
$0.15 / $0.47 in / out per 1M
Qwen3.8-Flash
qwen/qwen3.8-flash
$0.15 / $0.47 in / out per 1M
Qwen3.8-27B
qwen/qwen3.8-27b
$0.0248 / $4.35 in / out per 1M
Qwen3.8-Max
qwen/qwen3.8-max
$2 / $6 in / out per 1M
Qwen3.7-Flash
qwen/qwen3.7-flash
$0.03 / $0.13 in / out per 1M
Qwen3.7-Plus
qwen/qwen3.7-plus
$0.32 / $1.28 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every Qwen3-235B-A22B call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.