Alibaba logo

Qwen3 4B Instruct

Pricing & Specs API
Free REST API for prices, specs and benchmarks
Qwen3 4B Instruct is Alibaba's language model with a 262K context window and up to 33K output tokens, starting at $0.2 / 1M input and $0.2 / 1M output. An instruction-tuned 4B Qwen3 model offering efficient text generation and reasoning in a small parameter footprint.
Specifications
Canonical IDalibaba-qwen3-4b-instruct
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window262K tokens
Max Output33K tokens
Input ModalitiesText
Output ModalitiesText
Parameters4B
Benchmarks
Intelligence Index
#352
Math Index
#74
MMLU-Pro
#192
GPQA
#302
HLE
#329
LiveCodeBench
#124
AIME
#56
IFBench
#186
Time to First Token
#30
SciCode
#388
MATH-500
#59
AIME 2025
#74
LCR
#292
TerminalBench Hard
#275
TAU2
#282
Output TPS
#276

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities2/13
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
Fireworks AI logo
Fireworks AI
fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507
$0.2$0.2

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Qwen3 4B Instruct, ranked by cheapest on-demand price. The model needs about 10 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
Standard_NV4as_v4AzureAMD Radeon Instinct MI2516 GB$0.233/hr
g5g.xlargeAWST4g16 GB$0.420/hr
Standard_NV8as_v4AzureAMD Radeon Instinct MI2516 GB$0.466/hr
7 more instances can run Qwen3 4B Instruct
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$0.010—Available
Qwen3 32B131K$0.050$0.100Deprecated
Qwen3 14B131K$0.120$0.200Deprecated
Qwen3 8B131K$0.035$0.138Deprecated
Qwen3 4B Instruct—262K$0.200$0.200Current
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/qwen3-4b-instruct-2507
alibaba-qwen3-4b-instruct
fireworks_ai/accounts/fireworks/models/qwen3-4b-instruct-2507
huggingface-reasoning-qwen3-4b-instruct-2507
lemonade/Qwen3-4B-Instruct-2507-GGUF
qwen3-4b-2507-instruct
qwen3-4b-2507-instruct-reasoning
qwen3-4b-instruct
qwen3-4b-instruct-reasoning