Qwen
·Released on Sep 23, 2025

Qwen3 Max API Benchmarks, Pricing & Provider Data

Compare Qwen3 Max with another model

Choose a model to open its comparison page.

Share on X
LLM

Qwen3 Max benchmark, API pricing, and provider data cover 359 API providers, with prices starting at $0.010/request. Qwen3 Max free API options are available from 1 provider. The page also shows measured API speed and first-token latency.

Alibaba Qwen3 Max is the largest Qwen3-tier model, targeting frontier reasoning, long-context understanding, coding, and agent tasks at maximum capability.

Quality
0.0
LMSpeed score
Speed
38char/s
7.37 s
Cost
#118of 181
$0.010/ 1M · 8:1 in:out
$0.0016 in · $0.0084 out

Category Performance

Observed-capability estimates with uncertainty reported separately from independent benchmark families.

Coverage
6 / 8
Methodology
V3.0
Category PerformanceObserved-capability estimates with uncertainty reported separately from independent benchmark families.Agents47.5Coding45.1Reasoning48.9Knowledge40.6Math51.4Multilingual-Multimodal-Instruction following44.6
#1Math51.4Provisional1/4 Measured dimensions
80% interval: 35.367.5
foundational math51.4
aa_math_index · artificial_analysis_math_index
competition mathPrior only
proof frontierPrior only
applied tool mathPrior only
#2Reasoning48.9RatedGlobal rank #453/4 Measured dimensions
80% interval: 40.257.5
abstract logicPrior only
scientific causal48.1
critpt · critpt / gpqa · gpqa / hle · hle
multistep constraints55.3
mmlu_pro · mmlu_pro
evidence verification43.4
lcr · lcr
#3Agents47.5Estimated2/4 Measured dimensions
80% interval: 35.759.4
planning47.3
deep_planning · gert_labs
tool use47.8
tau · tau2_bench
environment executionPrior only
recovery reliabilityPrior only
#4Coding45.1Estimated2/4 Measured dimensions
80% interval: 33.956.3
code generation53.2
livecodebench · livecodebench / scicode · scicode
repository engineering37
vibecode · vibe_code_bench
debugging testingPrior only
tooling qualityPrior only
#5Instruction following44.6Provisional1/4 Measured dimensions
80% interval: 28.660.6
constraint followingPrior only
structured outputPrior only
novel instruction generalization44.6
ifbench · aa_if_bench
long multiturn instructionPrior only
#6Knowledge40.6Provisional1/4 Measured dimensions
80% interval: 24.656.6
broad knowledge40.6
aa_omniscience · aa_omniscience_index
professional knowledgePrior only
factualityPrior only
retrieval open bookPrior only
No data:MultilingualMultimodal

Specifications

Input and output token limits for this model, plus how it ranks on long-context understanding.

INPUT
262.1Ktokens
314.6 pages of text
OUTPUT
65.5Ktokens
8K128K1M4M
262.1K

Features

Technical Details

Input
Output
Released
Sep 2025
Knowledge cutoff
2025-06-30
Documentation
Tokenizer
Qwen3
Architecture
text->text
Moderated
No
Supported parameters
frequency_penaltylogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Rankings

Excels at

Falls behind in

Detailed scores

Updated: Sep 1, 2026

Pricing

undefined metric} other undefined metrics}}

Input price$1.20/M#118 / 181Output price$6.00/M#125 / 181
Input price
LMSpeed rank#118
Score$1.20/M
UpdatedSep 1, 2026
Confidence4
Output price
LMSpeed rank#125
Score$6.00/M
UpdatedSep 1, 2026
Confidence4

Agents

V3.0

undefined metric} other undefined metrics}} · Estimated

Score47.580% interval35.7–59.42/4 Measured dimensionsΤ²-bench results74.3#58 / 82Gert Labs43.7#31 / 49
Dimensions and evidence
Planning & decomposition47.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
deep_planning · gert_labs · z -0.35 · q 1.00
Tool use47.8
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
tau · tau2_bench · z -0.41 · q 1.00
Environment & long-horizon executionPrior only
Recovery & completion reliabilityPrior only
Τ²-bench resultsV3 evidence
LMSpeed rank#58
Score74.3
UpdatedAug 14, 2026
Confidence1
Gert LabsV3 evidence
LMSpeed rank#31
Score43.7
UpdatedAug 14, 2026
Confidence1

Coding

V3.0

undefined metric} other undefined metrics}} · Estimated

Score45.180% interval33.9–56.32/4 Measured dimensionsLiveCodeBench65.1%#38 / 115SciCode37.0%#111 / 206
Dimensions and evidence
Code generation53.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z 0.82 · q 1.00
scicode · scicode · z 0.03 · q 1.00
Repository engineering37
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
vibecode · vibe_code_bench · z -1.74 · q 1.00
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
LiveCodeBenchV3 evidence
LMSpeed rank#38
Score65.1%
UpdatedSep 1, 2026
Confidence4
SciCodeV3 evidence
LMSpeed rank#111
Score37.0%
UpdatedSep 1, 2026
Confidence4
Vibe Code BenchV3 evidence
LMSpeed rank#31
Score3.5
UpdatedAug 14, 2026
Confidence1
AA-SciCodeV3 evidence
LMSpeed rank#77
Score38.3
UpdatedAug 14, 2026
Confidence1

Reasoning

V3.0

undefined metric} other undefined metrics}} · Rated

Score48.9#4580% interval40.2–57.53/4 Measured dimensionsMMLU-Pro83.8%#35 / 129GPQA76.4%#112 / 213
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning48.1
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
critpt · critpt · z -0.72 · q 1.00
gpqa · gpqa · z -0.04 · q 1.00
hle · hle · z -0.11 · q 1.00
Multi-step constraints55.3
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z 0.50 · q 1.00
Evidence integration & verification43.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
lcr · lcr · z -1.24 · q 1.00
MMLU-ProV3 evidence
LMSpeed rank#35
Score83.8%
UpdatedSep 1, 2026
Confidence4
GPQAV3 evidence
LMSpeed rank#112
Score76.4%
UpdatedSep 1, 2026
Confidence4
HLEV3 evidence
LMSpeed rank#115
Score10.1%
UpdatedSep 1, 2026
Confidence4
AA-LCRV3 evidence
LMSpeed rank#82
Score48.3
UpdatedAug 14, 2026
Confidence1

Knowledge

V3.0

undefined metric} other undefined metrics}} · Provisional

Score40.680% interval24.6–56.61/4 Measured dimensionsArtificial Analysis Intelligence Index24.4#79 / 111AA-GPQA Diamond76.4#78 / 108
Dimensions and evidence
Broad knowledge40.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_omniscience · aa_omniscience_index · z -1.34 · q 1.00
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only
Artificial Analysis Intelligence IndexV3 evidence
LMSpeed rank#79
Score24.4
UpdatedAug 14, 2026
Confidence1
AA-GPQA Diamond
LMSpeed rank#78
Score76.4
UpdatedAug 14, 2026
Confidence1
AA-HLE
LMSpeed rank#79
Score11.9
UpdatedAug 14, 2026
Confidence1
AA-Omniscience Accuracy
LMSpeed rank#71
Score24.4
UpdatedAug 14, 2026
Confidence1
AA-Omniscience Hallucination Rate
LMSpeed rank#20
Score89.9
UpdatedAug 14, 2026
Confidence1

Math

V3.0

undefined metric} other undefined metrics}} · Provisional

Score51.480% interval35.3–67.51/4 Measured dimensions
Dimensions and evidence
Foundational math51.4
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aa_math_index · artificial_analysis_math_index · z 0.58 · q 1.00
Competition mathPrior only
Advanced proofsPrior only
Applied & tool-assisted mathPrior only

Multilingual

V3.0

undefined metric} other undefined metrics}} · No data

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Cross-language understandingPrior only
Multilingual generationPrior only
Reasoning transferPrior only
Low-resource robustnessPrior only

Multimodal

V3.0

undefined metric} other undefined metrics}} · No data

80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1141.0#60 / 75
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoningPrior only
Video & grounded actionPrior only
Design Arena Website
LMSpeed rank#60
Score1141.0
UpdatedAug 14, 2026
Confidence1

Instruction following

V3.0

undefined metric} other undefined metrics}} · Provisional

Score44.680% interval28.6–60.61/4 Measured dimensionsAA-IFBench44.1#60 / 84
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalization44.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
ifbench · aa_if_bench · z -0.99 · q 1.00
Multi-turn & long instructionsPrior only
AA-IFBenchV3 evidence
LMSpeed rank#60
Score44.1
UpdatedAug 14, 2026
Confidence1

OpenRouter endpoints

1 endpoints

Third-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.

Provider endpointInputOutput1d uptime30m latency30m throughputContext / output
Alibaba
alibaba
$0.780/M$3.90/M100%undefined tokens / undefined tokens

Pricing Comparison

Compare Qwen3 Max API pricing across 358 providers. Prices range from $0.010/request to $150.00/M. 素墨API offers the lowest rate at $0.010/request. 1 provider offers free API credits or a free tier.

ProviderHealthModel VariantGroupInput ($/M)Output ($/M)Speed (t/s)First tokenAudit
L1
99%
qwen3-max
default
$16.06/M
Cache read$1.61/M
$64.25/M
33.2 t/s
50.28 s
L1
100%
qwen3-max
default
-86%$0.171/M
-89%$0.685/M
L1
100%
qwen3-max-2026-01-23
default
-86%$0.171/M
-89%$0.685/M
L1
100%
qwen3-max-preview
default
-66%$0.411/M
-73%$1.64/M
L1
100%
qwen3-max
bailian
-85%$0.179/M
Cache read$0.036/M
-88%$0.714/M
L1
100%
qwen3-max
default
$3.20/M
$12.80/M
L1
100%
qwen3-max-preview
qwen
$2.40/M
$9.60/M
L1
100%
qwen3-max
default
-71%$0.342/M
-77%$1.37/M
L1
100%
qwen3-max-2026-01-23
default
-71%$0.342/M
-77%$1.37/M
L1
100%
qwen3-max-preview
default
-32%$0.822/M
-45%$3.29/M
L1
100%
qwen3-max-2026-01-23
default
-20%$0.959/M
-36%$3.84/M
L1
100%
qwen3-max-2025-09-23
default
$1.37/M
-9%$5.48/M
L1
100%
qwen3-max
default
$1.37/M
-9%$5.48/M
L1
100%
qwen3-max-preview
default
$2.05/M
$8.22/M
L1
100%
qwen3-max-2025-10-30
default
$10.27/M
$10.27/M
L1
100%
qwen3-max
default
$1.80/M
$7.20/M
L1
100%
qwen3-max
default
-86%$0.171/M
-89%$0.685/M
L1
100%
qwen3-max-2026-01-23
default
-86%$0.171/M
-89%$0.685/M
L1
100%
qwen3-max-preview
default
-66%$0.411/M
-73%$1.64/M
L1
99%
qwen/qwen3-max
other
-58%$0.500/M
Cache read$0.100/M
-58%$2.50/M
Showing 20 model IDs of 99.

Alternatives & Similar Models

Frequently Asked Questions

What benchmark data does Qwen3 Max include?
LMSpeed shows Qwen3 Max benchmark context, API price, output speed, first-token latency, and provider data across 359 providers when those signals are available.
What is the Qwen3 Max API price?
Qwen3 Max has pricing from 359 providers, ranging from $0.010/request to $150.00/M. 素墨API has the lowest listed price.
What does the Qwen3 Max API pricing table include?
The Qwen3 Max API pricing table compares 359 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
Which provider has the cheapest Qwen3 Max API pricing?
素墨API currently has the lowest listed Qwen3 Max price at $0.010/request across 359 providers.
Can I compare Qwen3 Max API price and speed together?
Yes. LMSpeed shows Qwen3 Max API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
Is Qwen3 Max API free?
Yes, Qwen3 Max free API options are available through 1 providerundefined other undefined} on LMSpeed, including Claw API. These providers offer free API credits or a free tier with no per-token charges.
Where can I get Qwen3 Max free API access?
LMSpeed currently lists 1 free API providerundefined other undefined} for Qwen3 Max: Claw API. Check each provider row before using it because free tier limits can change.

Also known as

OR-qwen/qwen3-maxQwen/Qwen3-MaxQwen/qwen3-maxQwen/qwen3-max-previewQwen3-Max

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Standard benchmark data may include BenchLM and other public sources.

Build with LMSpeed Data

Free

Free public API for LLM pricing, benchmarks & provider data

  • Real-time pricing & availability
  • Speed & latency benchmarks
  • 300+ models, 600+ providers
  • 1,000 requests/day
View API Documentation