Models/Qwen/Qwen3.8 27B

Qwen3.8 27B

Name: Qwen3.8 27B API access
Brand: Qwen

NEW

Qwen · Open weights · Released Aug 14, 2026 · qwen/qwen3.8-27b

Compare Estimate cost

1M contextVisionToolsReasoningStructured outputPrompt cachingOpen weights

Available from 8 providersUSD / MTOK · VERIFIED 12 HOURS AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	SMOKE	UPTIME
CHChutes	$0.35	$2.75	$0.035	262K	fp8	2s	44 tok/s	3/5	99.5%
CWCoreWeave	$0.40	$3.00	$0.15	262K	fp8	1.7s	50 tok/s	3/5	98.5%
AKAkashML	$0.40	$3.00	$0.05	262K	bf16	0.9s	87 tok/s	3/5	99.8%
REReka	$0.45	$3.20	$0.05	262K	fp8	1.7s	77 tok/s	3/5	99.7%
Venice	$0.45	$3.20	—	262K	fp8	1.7s	93 tok/s	3/5	99.2%
Parasail	$0.45	$3.20	—	262K	fp8	1.2s	59 tok/s	3/5	99.8%
INIo Net	$0.48	$3.40	$0.25	66K	fp8	2.2s	19 tok/s	—	99.1%
Alibaba	$0.50	$3.00	$0.10	1M	—	1.9s	64 tok/s	—	100.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · SMOKE: of 5 programmatic capability probes passed (JSON schema, instruction following, tool call, long-context, benign compliance; retry-once) · screened via OpenRouter routing · v0.1 · methodology v1.1 · measured 42 hours ago

Input price history · best listed price, observed

↓ 13% SINCE AUG 24, 2026

$0.40 · AUG 24, 2026$0.35 · TODAY

Pricing variants · USD / MTok in / out

STANDARD

$0.35 / $2.75

per MTok in / out

CACHE READ $0.035

Recent changesRSS ↗

Aug 24, 2026price decreased · input0.4 → 0.35

Aug 24, 2026price decreased · output3 → 2.75

About

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

Specifications

Context window1,000,000

Max output131,072

Modalities intext, image, video

Modalities outtext

LicenseOpen weights

ReleasedAug 14, 2026

TokenizerQwen

WeightsHugging Face ↗

Open weights

Hugging FaceQwen/Qwen3.8-27B ↗

Downloads2.4M

Likes12.3K

Licenseapache-2.0

safetensors

Qwen3.8 2.4T A95B$2.00 / $6.00 Qwen3.8 Max$2.00 / $6.00 Qwen3.7 Flash$0.03 / $0.13 Qwen3.7 Plus$0.32 / $1.28

Embed badge

[![Qwen3.8 27B](https://modelindex.ai/badge/qwen/qwen3.8-27b)](https://modelindex.ai/models/qwen/qwen3.8-27b)

Sources

OpenRouter API12 hours ago

AGGREGATOR

Hugging Face12 hours ago

COMMUNITY

ModelIndex benchmarks42 hours ago

MEASURED

Verified 12 hours ago · list prices, not negotiated rates.