AI TOOLS RADAR
All models / QWEN
qwen logo
qwen

Qwen: Qwen3.8 27B

Source description (English)

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...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
1,000,000 tokens
Maximum output
235,929 tokens
Architecture
text+image+video->text
Tokenizer
Qwen
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.2
per 1M tokens
Output
$2.5
per 1M tokens
Cache read
$0.09
per 1M tokens
API

Model configuration

Default parameters

temperature
1
top_p
0.95
top_k
20

Reasoning

Reasoning required
No
Default parameters
xhigh
Capabilities
xhigh, medium, low, none
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.8-27b","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimagevideo
Output
text
Reasoning

Yes · xhigh · medium · low · none

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p
Available providers

21 providers

Checked: October 23, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

Tenstorrent

fp4
Context
65K
Maximum output
59K
Input
$0.02
Output
$0.5
Cache read
$0.009
Cache write
Not provided

Darkbloom

fp4
Context
262K
Maximum output
33K
Input
$0.035
Output
$2.2
Cache read
$0.0175
Cache write
Not provided

Chutes

fp8
Context
262K
Maximum output
66K
Input
$0.039
Output
$1.25
Cache read
$0.0039
Cache write
Not provided

Near AI

fp8
Context
262K
Maximum output
66K
Input
$0.04
Output
$1.35
Cache read
$0.018
Cache write
Not provided

Ionstream

fp8
Context
262K
Maximum output
66K
Input
$0.04
Output
$1.95
Cache read
$0.02
Cache write
Not provided

Reka

fp8
Context
262K
Maximum output
236K
Input
$0.04
Output
$2.2
Cache read
$0.02
Cache write
Not provided

Modal

Not provided
Context
262K
Maximum output
236K
Input
$0.04
Output
$2.3
Cache read
$0.02
Cache write
Not provided

DekaLLM

Not provided
Context
262K
Maximum output
236K
Input
$0.04
Output
$2.5
Cache read
$0.02
Cache write
Not provided

Wafer

fp8
Context
262K
Maximum output
236K
Input
$0.06
Output
$2.3
Cache read
$0.059
Cache write
Not provided

DeepInfra

bf16
Context
262K
Maximum output
236K
Input
$0.15
Output
$1.875
Cache read
$0.0375
Cache write
Not provided

ModelRun

fp4
Context
262K
Maximum output
236K
Input
$0.2
Output
$2.5
Cache read
$0.09
Cache write
Not provided

Mancer 2

fp8
Context
262K
Maximum output
236K
Input
$0.2
Output
$2.5
Cache read
Not provided
Cache write
Not provided

Phala

Not provided
Context
1M
Maximum output
262K
Input
$0.2
Output
$2.5
Cache read
$0.05
Cache write
Not provided

AkashML

fp8
Context
262K
Maximum output
131K
Input
$0.225
Output
$1.98
Cache read
$0.05
Cache write
Not provided

Parasail

fp8
Context
262K
Maximum output
236K
Input
$0.24
Output
$2.2
Cache read
$0.05
Cache write
Not provided

CoreWeave

fp8
Context
262K
Maximum output
236K
Input
$0.4
Output
$3
Cache read
$0.15
Cache write
Not provided

Novita

Not provided
Context
1M
Maximum output
131K
Input
$0.42
Output
$3
Cache read
$0.085
Cache write
Not provided

Alibaba

Not provided
Context
1M
Maximum output
131K
Input
$0.425
Output
$2.55
Cache read
$0.085
Cache write
$0.5313

Cloudflare

Not provided
Context
262K
Maximum output
236K
Input
$0.45
Output
$3.2
Cache read
$0.05
Cache write
Not provided

Venice

fp8
Context
262K
Maximum output
66K
Input
$0.45
Output
$3.2
Cache read
Not provided
Cache write
Not provided

Cerebras

fp16
Context
66K
Maximum output
33K
Input
$0.99
Output
$1.49
Cache read
$0.99
Cache write
Not provided
qwen

4 models

All models
qwen logoqwen

Qwen: Qwen Image 2.1 Turbo

Qwen Image 2.1 Turbo is the fast, lower-cost tier of the Qwen Image 2.1 series from Qwen, for image generation and editing where throughput and price matter more than peak...

Context
66K
Input
text · image
Output
image
Image input: Free per imageImage output: $0.0184 per image
View model details →
qwen logoqwen

Qwen: Qwen Image 2.1 Pro

Qwen Image 2.1 Pro is an image generation and editing model from Qwen, the higher-quality tier of the Qwen Image 2.1 series. Choose it over Qwen Image 2.1 Turbo when...

Context
66K
Input
text · image
Output
image
Image input: Free per imageImage output: $0.046 per image
View model details →
qwen logoqwen

Qwen: Qwen3.8 Max Prime

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

Context
1M
Input
text · image · video
Output
text
Input: $4Output: $12per 1M tokens
View model details →
qwen logoqwen

Qwen: Qwen3.8 Omni Flash

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

Context
1M
Input
text · image · audio · video
Output
text
Input: $0.15Output: $0.47per 1M tokens
View model details →