← Model list

Qwen3 235B A22B Thinking 2507

alibaba·alibaba/qwen3-235b-a22b-thinking-2507·GA·Open weights·qwen series·NEW

Qwen reasoning model for deliberate problem solving, math, and coding

At a glance
Reference price$0.40 / $4.00 per 1M
Cache read · Vercel AI Gateway
Lowest paid$0.20 / $0.60
submodel Gateway · 2.3× spread
1 more $0 channels
Context131,072
⚠ Providers report 128,000–262,144; the table below is authoritative
Output limit32,768
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-04
Released / updated2025-07-25 / 2026-06-11

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 10 providers8 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
ModelScope
Qwen/Qwen3-235B-A22B-Thinking-2507
CloudFree262,144131,072
submodel
Qwen/Qwen3-235B-A22B-Thinking-2507
Gateway$0.20$0.60262,144131,072
OpenRouterGateway$0.23$2.30262,14432,768
Hugging Face
Qwen/Qwen3-235B-A22B-Thinking-2507
Cloud$0.30$3.00262,144131,072
Jiekou.AIGateway$0.30$3.00131,072131,072
NovitaAIGateway$0.30$3.00131,07232,768
DevPass (LLM Gateway)Gateway$0.30$3.00262,0008,192
Venice AIGateway$0.45$3.50128,00016,384
Vercel AI Gateway
alibaba/qwen3-235b-a22b-thinking
Cloud$0.40$4.00131,07232,768
QiniuGateway262,1444,096hostTable.undisclosed

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1submodel$70.00
2OpenRouter$161.00
3Hugging Face$210.00
4Jiekou.AI$210.00
5NovitaAI$210.00
6DevPass (LLM Gateway)$210.00

1 more channels offer $0 (ModelScope); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

Toggle (on / off)effort = loweffort = mediumeffort = highbudget_tokens ≥ 1 ≤ 81,920

6 / 10 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$4.00$02026-08-052026-08-132026-08-05 · Input list $0.402026-08-06 · Input list $0.402026-08-07 · Input list $0.402026-08-08 · Input list $0.402026-08-09 · Input list $0.302026-08-10 · Input list $0.302026-08-11 · Input list $0.302026-08-12 · Input list $0.302026-08-13 · Input list $0.402026-08-05 · Output list $4.002026-08-06 · Output list $4.002026-08-07 · Output list $4.002026-08-08 · Output list $4.002026-08-09 · Output list $0.502026-08-10 · Output list $0.502026-08-11 · Output list $0.502026-08-12 · Output list $0.502026-08-13 · Output list $4.002026-08-05 · Min blended $0.102026-08-06 · Min blended $0.102026-08-07 · Min blended $0.102026-08-08 · Min blended $0.102026-08-09 · Min blended $0.352026-08-10 · Min blended $0.352026-08-11 · Min blended $0.352026-08-12 · Min blended $0.352026-08-13 · Min blended $0.30