Alibaba logo

Qwen3 235B A22B Thinking

Deprecated
Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 235B A22B Thinking is Alibaba's language model with a 262K context window and up to 118K output tokens, available from 4 providers, starting at $0.22 / 1M input and $0.88 / 1M output. A thinking-mode variant of the Qwen3 235B A22B MoE model that scales chain-of-thought reasoning depth for improved quality on complex tasks.
Specifications
Canonical IDalibaba-qwen3-235b-a22b-thinking
TypeLanguage
StatusDeprecated
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output118K tokens
Input ModalitiesImagePDFText
Output ModalitiesText
Reasoning Effortsdefault
Parameters235B
HuggingFace Likes404
HuggingFace Downloads (30d)56,151
HuggingFace Downloads (all-time)464,961
Release Date · 1 year ago
Knowledge Cutoff · 1 year ago
Deprecation Date

Capabilities

Input3/5
Text✓
Image✓
Audio·
Video·
PDF✓
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities6/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
DeepInfra logo
DeepInfra
deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507
$0.3$2.90
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507
$0.22$0.88
Novita logo
Novita
novita/qwen/qwen3-235b-a22b-thinking-2507
$0.3$3.00
OpenRouter logo
OpenRouter
qwen/qwen3-235b-a22b-thinking-2507
$0.45$3.50

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 235B A22B Thinking, ranked by cheapest on-demand price. The model needs about 564 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
p4de.24xlargeAWS8× A100640 GB$27.45/hr
Standard_ND96amsr_A100_v4Azure8× NVIDIA A100 (80GB)640 GB$32.77/hr
g7e.48xlargeAWS8× RTX PRO Server 6000768 GB$33.14/hr
7 more instances can run Qwen3 235B A22B Thinking
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MiroThinker 1.7————Available
Qwen3 30B A3B Thinking262K$0.900$0.900Deprecated
Qwen3 Coder 30B A3B Instruct262K$0.070$0.270Deprecated
Qwen3 30B A3B Instruct262K$0.100$0.300Deprecated
Qwen3 235B A22B Thinking262K$0.220$0.880Current
Qwen3 Coder262K$0.220$1.00Deprecated
Qwen3 235B A22B262K$0.090$0.540Deprecated
Qwen3 30B A3B131K$0.051$0.200Deprecated
Qwen3 235B A22B Instruct—262K$0.090$0.550Deprecated
Qwen3 Coder 480B A35B Instruct—262K$0.220$1.55Deprecated
KwaiPilot KAT Coder—262K$0.900$0.900Available

Model IDs

accounts/fireworks/models/qwen3-235b-a22b-thinking-2507
alibaba-qwen3-235b-a22b-thinking
alibaba/qwen3-235b-a22b-thinking
deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507
fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-thinking-2507
novita/qwen/qwen3-235b-a22b-thinking-2507
openrouter/qwen/qwen3-235b-a22b-thinking-2507
qwen/qwen3-235b-a22b-thinking-2507
Qwen/Qwen3-235B-A22B-Thinking-2507
qwen3-235b-a22b-thinking-2507
together_ai/Qwen/Qwen3-235B-A22B-Thinking-2507
wandb/Qwen/Qwen3-235B-A22B-Thinking-2507