Qwen3.8-Flash-Next is Alibaba's language model with a 1.0M context window, starting at $0.12 / 1M input and $0.4 / 1M output. A fast, lightweight large language model in the Qwen3 series designed for low-latency next-generation inference.
Specifications
Canonical IDalibaba-qwen3-8-flash-next
TypeLanguage
StatusActive
CreatorAlibabaAlibaba
Providers
Context Window1.0M tokens
Input ModalitiesImageText
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 6 days ago
Benchmarks
Intelligence Index
#15
Coding Index
#12
GPQA
#17
HLE
#36
Time to First Token
#509
SciCode
#55
LCR
#25
Output TPS
#160

Capabilities

Input2/5
Text
Image
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities3/13
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
Cache Read
$ / 1M
Vercel AI Gateway logo
Vercel AI Gateway
alibaba/qwen3.8-flash-next
$0.12$0.4$0.01

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Qwen Audio 3 Flash ASRAvailable
Qwen Audio 3 Flash ASR FiletransAvailable
Qwen Audio 3 Flash ASR StreamingAvailable
Qwen Audio 3 Flash Realtime$0.450$4.50Available
Qwen3.8-Flash-Next1.0M$0.120$0.400Current
Qwen3.5 Omni Flash$0.400$3.00Available
Qwen Flash Character$0.050$0.400Available
Qwen TTS Flash$0.230$1.43Available

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
Qwen3.8 2.4T A95B1.0M$2.00$6.00
Qwen Image 3
Qwen Audio 3 Plus RealtimePlus$0.800$6.40
Qwen Audio 3 Plus TTSPlus
Qwen Image 3.0 ProPro
EAGLE Qwen 2.5 3B Instruct
DeepSeek R1 Qwen3 8B
Qwen3.8 27B1.0M$0.400$2.55
Qwen3.8 MaxMax1.0M$1.65$4.95
Qwen3.7 PlusPlus1.0M$0.320$1.28

Model IDs

accounts/fireworks/models/qwen3p8-flash-next-fp8
accounts/fireworks/models/qwen3p8-flash-next-nvfp4
alibaba-qwen3-8-flash-next
alibaba/qwen3.8-flash-next
qwen3-8-flash-next