Qwen
·Released on Apr 28, 2025

Qwen3 8B API Benchmarks, Pricing & Provider Data

Compare Qwen3 8B with another model

Choose a model to open its comparison page.

Share on X
LLM

Qwen3 8B benchmark, API pricing, and provider data cover 24 API providers, with prices starting at $0.027/M.

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode f...

Cost
#30of 180
$0.027/ 1M · 8:1 in:out
$0.0044 in · $0.023 out

Category Performance

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

Coverage
3 / 8
Methodology
V3.0
Category PerformanceObserved-capability estimates with uncertainty reported separately from independent benchmark families.Agents-Coding32.6Reasoning42.2Knowledge-Math48.5Multilingual-Multimodal-Instruction following-
#1Math48.5Estimated2/4 Measured dimensions
80% interval: 36.760.3
foundational math47.9
math_500 · math_500
competition math49
aime · aime
proof frontierPrior only
applied tool mathPrior only
#2Reasoning42.2Estimated2/4 Measured dimensions
80% interval: 31.153.3
abstract logicPrior only
scientific causal37.2
gpqa · gpqa / hle · hle
multistep constraints47.2
mmlu_pro · mmlu_pro
evidence verificationPrior only
#3Coding32.6Provisional1/4 Measured dimensions
80% interval: 18.746.5
code generation32.6
livecodebench · livecodebench / scicode · scicode
repository engineeringPrior only
debugging testingPrior only
tooling qualityPrior only
No data:AgentsKnowledgeMultilingualMultimodalInstruction following

Specifications

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

INPUT
131.1Ktokens
157.3 pages of text
OUTPUT
8.2Ktokens
8K128K1M4M
131.1K

Features

Technical Details

Input
Output
Total parameters
8B
Released
Apr 2025
Knowledge cutoff
2025-03-31
Tokenizer
Qwen3
Architecture
text->text
Instruct type
qwen3
Moderated
No
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Rankings

Excels at

Detailed scores

Updated: Aug 23, 2026

Pricing

undefined metric} other undefined metrics}}

Input price$0.180/M#30 / 180Output price$2.10/M#76 / 180
Input price
LMSpeed rank#30
Score$0.180/M
UpdatedAug 23, 2026
Confidence4
Output price
LMSpeed rank#76
Score$2.10/M
UpdatedAug 23, 2026
Confidence4

Agents

V3.0

undefined metric} other undefined metrics}} · No data

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Planning & decompositionPrior only
Tool usePrior only
Environment & long-horizon executionPrior only
Recovery & completion reliabilityPrior only

Coding

V3.0

undefined metric} other undefined metrics}} · Provisional

Score32.680% interval18.7–46.51/4 Measured dimensionsLiveCodeBench40.6%#71 / 115SciCode22.6%#188 / 204
Dimensions and evidence
Code generation32.6
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
livecodebench · livecodebench · z -0.85 · q 1.00
scicode · scicode · z -2.42 · q 1.00
Repository engineeringPrior only
Debugging & testingPrior only
Tool-assisted development & qualityPrior only
LiveCodeBenchV3 evidence
LMSpeed rank#71
Score40.6%
UpdatedAug 23, 2026
Confidence4
SciCodeV3 evidence
LMSpeed rank#188
Score22.6%
UpdatedAug 23, 2026
Confidence4

Reasoning

V3.0

undefined metric} other undefined metrics}} · Estimated

Score42.280% interval31.1–53.32/4 Measured dimensionsMMLU-Pro64.3%#115 / 129GPQA58.9%#165 / 211
Dimensions and evidence
Abstract logicPrior only
Scientific & causal reasoning37.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
gpqa · gpqa · z -1.32 · q 1.00
hle · hle · z -1.38 · q 1.00
Multi-step constraints47.2
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
mmlu_pro · mmlu_pro · z -0.58 · q 1.00
Evidence integration & verificationPrior only
MMLU-ProV3 evidence
LMSpeed rank#115
Score64.3%
UpdatedAug 23, 2026
Confidence4
GPQAV3 evidence
LMSpeed rank#165
Score58.9%
UpdatedAug 23, 2026
Confidence4
HLEV3 evidence
LMSpeed rank#181
Score3.9%
UpdatedAug 23, 2026
Confidence4

Knowledge

V3.0

undefined metric} other undefined metrics}} · No data

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Broad knowledgePrior only
Professional knowledgePrior only
FactualityPrior only
Retrieval & open-book usePrior only

Math

V3.0

undefined metric} other undefined metrics}} · Estimated

Score48.580% interval36.7–60.32/4 Measured dimensionsAIME74.7%#17 / 68MATH-50090.4%#33 / 73
Dimensions and evidence
Foundational math47.9
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
math_500 · math_500 · z -0.24 · q 1.00
Competition math49
undefined family} other undefined families}} · undefined metric} other undefined metrics}}
aime · aime · z -0.15 · q 1.00
Advanced proofsPrior only
Applied & tool-assisted mathPrior only
AIMEV3 evidence
LMSpeed rank#17
Score74.7%
UpdatedAug 23, 2026
Confidence4
MATH-500V3 evidence
LMSpeed rank#33
Score90.4%
UpdatedAug 23, 2026
Confidence4

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

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Perception & OCRPrior only
Document & spatial understandingPrior only
Visual reasoningPrior only
Video & grounded actionPrior only

Instruction following

V3.0

undefined metric} other undefined metrics}} · No data

No data80% interval30.8–69.20/4 Measured dimensions
Dimensions and evidence
Constraint followingPrior only
Structured outputPrior only
Novel-instruction generalizationPrior only
Multi-turn & long instructionsPrior only

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
$0.117/M$0.455/M100%undefined tokens / undefined tokens

Pricing Comparison

Compare Qwen3 8B API pricing across 24 providers. Prices range from $0.027/M to $0.637/M. Zhongzhuan Chat offers the lowest rate at $0.027/M.

ProviderHealthModel VariantGroupInput ($/M)Output ($/M)Speed (t/s)First tokenAudit
L1
99%
qwen3-8b
default
-65%$0.064/M
-88%$0.255/M
L1
99%
qwen3-8b
default
-65%$0.064/M
-88%$0.255/M
L1
100%
qwen3-8b
default
-81%$0.034/M
-93%$0.137/M

Alternatives & Similar Models

Frequently Asked Questions

What benchmark data does Qwen3 8B include?
LMSpeed shows Qwen3 8B benchmark context, API price, output speed, first-token latency, and provider data across 24 providers when those signals are available.
What is the Qwen3 8B API price?
Qwen3 8B has pricing from 24 providers, ranging from $0.027/M to $0.637/M. Zhongzhuan Chat has the lowest listed price.
What does the Qwen3 8B API pricing table include?
The Qwen3 8B API pricing table compares 24 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 8B API pricing?
Zhongzhuan Chat currently has the lowest listed Qwen3 8B price at $0.027/M across 24 providers.
Is Qwen3 8B API free?
Qwen3 8B does not currently have a free API tier on LMSpeed. All 24 providers charge per token.

Also known as

qwen3-8b

Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.Artificial AnalysisStandard 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