Alibaba logo

Qwen3 8B

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 8B is Alibaba's language model with a 131K context window and up to 20K output tokens, available from 6 providers, starting at $0.035 / 1M input and $0.138 / 1M output. An 8B-parameter dense LLM from the Qwen3 series with strong reasoning capabilities and support for hybrid thinking and non-thinking inference modes.
Specifications
Canonical IDalibaba-qwen3-8b
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window131K tokens
Max Output20K tokens
Input ModalitiesText
Output ModalitiesText
Reasoning Effortsdefault
Parameters8B
HuggingFace Likes1,051
HuggingFace Downloads (30d)8,692,944
HuggingFace Downloads (all-time)50,107,992
Release Date · 1 year ago
Knowledge Cutoff · 1 year ago
Benchmarks
Intelligence Index
#392
Coding Index
#187
Math Index
#221
MMLU-Pro
#194
GPQA
#338
HLE
#460
LiveCodeBench
#184
AIME
#37
IFBench
#327
Time to First Token
#516
SciCode
#387
MATH-500
#73
AIME 2025
#221
LCR
#413
TerminalBench Hard
#317
TAU2
#272
Output TPS
#220

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
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
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Input
$ / 1M
Output
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
qwen3-8b
$0.18$0.7$0.09$0.35
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-8b
$0.2$0.2——
Hugging Face logo
Hugging Face
nscale:Qwen/Qwen3-8B
$0.07$0.18——
LlamaGate
llamagate/qwen3-8b
$0.04$0.14——
Novita logo
Novita
novita/qwen/qwen3-8b-fp8
$0.035$0.138——
OpenRouter logo
OpenRouter
qwen/qwen3-8b
$0.117$0.455——

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 8B, ranked by cheapest on-demand price. The model needs about 19 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
g2-standard-4GCPnvidia-l424 GB$0.705/hr
g6.xlargeAWSL422 GB$0.805/hr
g2-standard-8GCPnvidia-l424 GB$0.851/hr
7 more instances can run Qwen3 8B
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Voyage 4 Nano————Available
Qwen3 Embedding 0.6B33K$0.010—Available
Qwen3 Embedding 4B41K$0.020—Available
Qwen3 Embedding 8B41K$0.020—Available
Qwen3 8B131K$0.035$0.138Current
Qwen3 32B131K$0.050$0.100Deprecated
Qwen3 14B131K$0.070$0.200Available
Qwen3 4B Instruct—262K$0.010$0.030Available
Qwen3 1.7B—131K$0.100$0.100Available
Qwen3 0.6B—41K$0.100$0.100Available
KwaiPilot KAT 32B Dev—131K$0.900$0.900Available

Model IDs

accounts/fireworks/models/qwen3-8b
alibaba-qwen3-8b
fireworks_ai/accounts/fireworks/models/qwen3-8b
huggingface-reasoning-qwen3-8b
llamagate/qwen3-8b
novita/qwen/qwen3-8b-fp8
qwen/qwen3-8b
qwen/qwen3-8b-fp8
qwen3-8b
qwen3-8b-instruct
qwen3-8b-instruct-reasoning