GeekRadar / The comparison desk

COMPARE.

AI models

alibaba

Qwen 3.8 27B

AI model Released Aug 14, 2026

Context window: 262,144 tokens^*
Maximum output: 32,768 tokens^*
Open weights: Yes^*

Capability & preference

General capability · ECI

A cross-benchmark capability estimate. Index points, not a percentage; intervals show uncertainty.

Qwen 3.8 27B 152.7^* Qwen 3.8 27B · 95% interval 150.8–154.8

Benchmark results

Run it locally

Inference · memory estimate

Qwen 3.8 27B

51.7^* GiB checkpoint tensor payload · 27.78 B^* stored tensor elements · BF16^*

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

Capabilities

Context window: 262,144 tokens^*
Maximum output: 32,768 tokens^*
Reasoning: Yes^*
Tool calling: Yes^*
Open weights: Yes^*
Model license: apache-2.0^*
Checkpoint tensor payload: 51.75 GiB^*

Input modalities

text^*
image^*
video^*

Output modalities

text^*

Processing & platform

Architecture: qwen3_5^*

System configuration

Detailed specifications

Specifications 1 · 4 fields

Access model: Open weights (unrestricted)^*
Open weights: Yes^*
Organization: Alibaba^*
Organization country: China^*

Specifications 2 · 1 fields

Checkpoint memory architecture

Stored tensor elements: 27,781,427,952^*
Checkpoint tensor bytes: 55,562,855,904^*
Checkpoint data type: BF16^*
Architecture: qwen3_5^*

Specifications 3 · 30 fields

Frontier agentic tasks Agents' Last Exam

suite: Frontier agentic tasks Agents' Last Exam
workload: pass@1
score: 20.4^*

Scope and conditions

Test conditions

Metric: pass@1^*
Checkpoint version: Not specified^*

Visual math problem solving MathVision

suite: Visual math problem solving MathVision
workload: reported score · Code interpreter disabled
score: 90.0^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Code interpreter disabled^*
Annotation set: Corrected ground-truth annotations^*
Prompt: Fixed step-by-step prompt with boxed final answer^*

Visual math problem solving MathVision

suite: Visual math problem solving MathVision
workload: reported score · Code interpreter enabled
score: 94.6^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Code interpreter enabled^*
Annotation set: Corrected ground-truth annotations^*
Prompt: Fixed step-by-step prompt with boxed final answer^*

Frontier agentic tasks Agents' Last Exam

suite: Frontier agentic tasks Agents' Last Exam
workload: score
score: 42.9^*

Scope and conditions

Test conditions

Metric: score^*
Checkpoint version: Not specified^*

General visual reasoning BabyVision

suite: General visual reasoning BabyVision
workload: reported score · Code interpreter disabled
score: 65.7^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Code interpreter disabled^*

General visual reasoning BabyVision

suite: General visual reasoning BabyVision
workload: reported score · Code interpreter enabled
score: 85.6^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Code interpreter enabled^*

Instruction following IFBench

suite: Instruction following IFBench
workload: reported score
score: 79.5^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Scientific chart analysis CharXiv (RQ)

suite: Scientific chart analysis CharXiv (RQ)
workload: reported score · Code interpreter disabled
score: 83.7^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Code interpreter disabled^*
Annotation set: Corrected ground-truth annotations^*

Scientific chart analysis CharXiv (RQ)

suite: Scientific chart analysis CharXiv (RQ)
workload: reported score · Code interpreter enabled
score: 90.2^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Tool access: Code interpreter enabled^*
Annotation set: Corrected ground-truth annotations^*

Scientific reasoning GPQA Diamond

suite: Scientific reasoning GPQA Diamond
workload: reported score
score: 89.2^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Document intelligence OmniDocBench 1.5

suite: Document intelligence OmniDocBench 1.5
version: 1.5
workload: reported score
score: 91.1^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Multidisciplinary reasoning HLE

suite: Multidisciplinary reasoning HLE
workload: reported score
score: 30.8^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Judge: GPT-4o^*

Real-world perception RealWorldQA

suite: Real-world perception RealWorldQA
workload: reported score
score: 85.9^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Competitive coding LiveCodeBench v6

suite: Competitive coding LiveCodeBench v6
version: 6
workload: reported score
score: 90.3^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Embodied intelligence ERQA

suite: Embodied intelligence ERQA
workload: reported score
score: 65.5^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Computer use OSWorld-Verified

suite: Computer use OSWorld-Verified
workload: reported score
score: 84.3^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Agentic terminal coding Terminal Bench 2.1 (Terminus)

suite: Agentic terminal coding Terminal Bench 2.1 (Terminus)
version: 2.1
workload: reported score · Terminus
score: 73.0^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Terminus^*

Agentic coding SWE-bench Pro

suite: Agentic coding SWE-bench Pro
workload: reported score · Claude Code · Refined task set with corrected problematic tasks
score: 61.7^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Task set: Refined task set with corrected problematic tasks^*
Temperature: 1.0^*
Top p: 0.95^*
Context length: 256K tokens^*

Browser use WebArena-Verified

suite: Browser use WebArena-Verified
workload: reported score · OSWorld scaffold; official WebArena-Verified grader
score: 64.8^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: OSWorld scaffold; official WebArena-Verified grader^*

Mobile use AndroidWorld

suite: Mobile use AndroidWorld
workload: reported score
score: 81.9^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Repo-level code generation NL2Repo-Bench

suite: Repo-level code generation NL2Repo-Bench
workload: reported score · Claude Code · Repository acquisition commands disabled
score: 42.3^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Tool access: Repository acquisition commands disabled^*

Application recreation RecreationBench

suite: Application recreation RecreationBench
workload: reported score · Internal
score: 47.1^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Task set: Internal^*
Variant: Application recreation across Ubuntu, macOS, Windows, Android and web^*

Agentic coding DeepSWE 1.1

suite: Agentic coding DeepSWE 1.1
version: 1.1
workload: reported score · Claude Code
score: 42.2^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Temperature: 1.0^*
Top p: 0.95^*
Context length: 256K tokens^*

Software engineering QwenSWEBench

suite: Software engineering QwenSWEBench
workload: reported score · Claude Code · Internal · avg@3
score: 79.0^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Statistic: avg@3^*
Timeout: 8 hours^*
Task set: Internal^*
Maximum output: 32,768^*
Temperature: 1.0^*
Context length: 256K tokens^*

Multimodal tool use ClawEval-MM

suite: Multimodal tool use ClawEval-MM
workload: pass@3 · At least one success in three trials
score: 57.4^*
unit: %

Scope and conditions

Test conditions

Metric: pass@3^*
Checkpoint version: Not specified^*
Statistic: At least one success in three trials^*

Multimodal tool use ClawEval-MM

suite: Multimodal tool use ClawEval-MM
workload: average score · Mean benchmark score over three trials
score: 56.9^*

Scope and conditions

Test conditions

Metric: average score^*
Checkpoint version: Not specified^*
Statistic: Mean benchmark score over three trials^*

Multimodal software engineering SWE-MM

suite: Multimodal software engineering SWE-MM
workload: reported score · Claude Code · Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications
score: 38.6^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Task set: Public SWE-bench Multimodal dev split with Opus 4.7 system-card appendix 8.3 modifications^*

Visual web development Vision2Web

suite: Visual web development Vision2Web
workload: reported score · Claude Code · Category average
score: 62.9^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Claude Code^*
Judge: gpt-5.4-2026-03-05^*
Categories: Frontend, webpage and website^*
Statistic: Category average^*

Long-horizon office work CoWorkBench

suite: Long-horizon office work CoWorkBench
workload: reported score · Internal
score: 70.7^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Task set: Internal^*

Professional job tasks JobBench

suite: Professional job tasks JobBench
workload: reported score
score: 33.4^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*

Specifications 4 · 92 fields

File attachments

Yes^*

Architecture

qwen3_5^*

Attention bias

No^*

Attention dropout

0.0^*

Checkpoint data type

bfloat16^*

Full attention interval

4^*

Attention head dimension

256^*

Activation function

silu^*

Hidden dimension

5,120^*

Feed-forward dimension

17,408^*

Attention layer types

Linear attention key dimension

128^*

Linear attention key heads

16^*

Linear attention value heads

48^*

Linear attention value dimension

128^*

Attention heads

24^*

Transformer layers

64^*

Key/value heads

4^*

Rotary embedding fraction

0.25^*

RMS normalization epsilon

1.0e-6^*

Tied word embeddings

No^*

Vocabulary size

248,320^*

Checkpoint licence

apache-2.0^*

Checkpoint tensor bytes

55,562,855,904^* bytes

Saved tensor elements

27,781,427,952^* elements

Checkpoint tensor payload

51.746942^* GiB

Context window

262,144^* tokens

Model family

qwen^*

Input modalities

text^*
image^*
video^*

Maximum output

32,768^* tokens

Output modalities

text^*

API service · Munito AI (EU) · qwen/qwen3.8-27b

Provider

Munito AI (EU)^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 235,929^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.2^*
output: 2.7^*
cache_read: 0.11^*

API service · Hetzner · Qwen3.8-27B

Provider

Hetzner^*

Model

Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Availability status

beta^*

API service · Ofox · qwen/qwen3.8-27b

Provider

Ofox^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,131,072^*
output: 131,072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.5^*
output: 1.71^*
cache_read: 0.043^*
cache_write: 0.63^*

API service · OVHcloud AI Endpoints · qwen3.8-27b

Provider

OVHcloud AI Endpoints^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- minimal^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.47^*
output: 3.19^*

API service · Groq · qwen/qwen3.8-27b

Provider

Groq^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 131,072^*
output: 16,384^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- default^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Availability status

beta^*

Prices (USD per million tokens)

input: 0.8^*
output: 4^*

API service · Cortecs · qwen3.8-27b

Provider

Cortecs^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 500,000^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.1^*
output: 0.4^*
cache_read: 0.04^*

API service · Opper · qwen3.8-27b

Provider

Opper^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

No^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.5811^*
output: 3^*

API service · LLM Gateway · consensusprotocol/Qwen3.8-27B

Provider

LLM Gateway^*

Model

consensusprotocol/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,000^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.08^*
output: 0.35^*
cache_read: 0.05^*

API service · Vultr · qwen3.8-27b

Provider

Vultr^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.15^*
output: 1^*

API service · NEAR AI Cloud · Qwen/Qwen3.8-27B

Provider

NEAR AI Cloud^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.04^*
output: 1.35^*
cache_read: 0.018^*

API service · Thinking Machines · Qwen/Qwen3.8-27B

Provider

Thinking Machines^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 65,536^*
output: 65,536^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.6975^*
output: 5.595^*
cache_read: 0.1395^*

API service · Standard Compute · qwen/qwen3.8-27b

Provider

Standard Compute^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_details^*

Prices (USD per million tokens)

input: 0.425^*
output: 2.55^*
cache_read: 0.085^*
cache_write: 0.53125^*

API service · Cloudflare Workers AI · @cf/qwen/qwen3.8-27b

Provider

Cloudflare Workers AI^*

Model

@cf/qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.45^*
output: 3.2^*
cache_read: 0.05^*

API service · LLM Tech · nvidia/Qwen3.8-27B-NVFP4

Provider

LLM Tech^*

Model

nvidia/Qwen3.8-27B-NVFP4^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.25^*
output: 2.09^*
cache_read: 0.04^*

API service · OpenRouter · qwen/qwen3.8-27b

Provider

OpenRouter^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 235,929^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.2^*
output: 2.5^*
cache_read: 0.09^*

API service · TensorX · qwen/qwen3.8-27b

Provider

TensorX^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.4^*
output: 2.4^*
cache_read: 0.1^*

API service · NanoGPT · qwen/qwen3.8-27b

Provider

NanoGPT^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,048,576^*
input: 1,048,576^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.15^*
output: 0.7^*
cache_read: 0.04^*

API service · Hugging Face · Qwen/Qwen3.8-27B

Provider

Hugging Face^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.4^*
output: 3^*

API service · Tempr Gateway · groq/qwen/qwen3.8-27b

Provider

Tempr Gateway^*

Model

groq/qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 131,042^*
output: 16,384^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.8^*
output: 4^*
cache_read: 0.4^*

API service · Ambient · qwen/qwen3.8-27b

Provider

Ambient^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 32,768^*
output: 8,192^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.32^*
output: 3.2^*
cache_read: 0.16^*
cache_write: 0^*

API service · LLM Gateway · novita/qwen3.8-27b

Provider

LLM Gateway^*

Model

novita/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 131,072^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.42^*
output: 3^*
cache_read: 0.085^*

API service · Munito AI · qwen/qwen3.8-27b

Provider

Munito AI^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 235,929^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.18^*
output: 2.4^*
cache_read: 0.05^*

API service · Chutes · Qwen/Qwen3.8-27B-TEE

Provider

Chutes^*

Model

Qwen/Qwen3.8-27B-TEE^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 65,536^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.039^*
output: 1.25^*
cache_read: 0.003899999999999999^*

API service · Blue Claw · Qwen3.8-27B

Provider

Blue Claw^*

Model

Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 131,072^*
output: 32,768^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Availability status

beta^*

API service · CommandCode · Qwen/Qwen3.8-27B

Provider

CommandCode^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.4^*
output: 3^*
cache_read: 0.04^*

API service · Ofox · bailian/qwen3.8-27b

Provider

Ofox^*

Model

bailian/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,131,072^*
output: 131,072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.45^*
output: 3.2^*
cache_read: 0.05^*
cache_write: 0.5625^*

API service · Venice AI · qwen-3-8-27b

Provider

Venice AI^*

Model

qwen-3-8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 65,536^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.45^*
output: 3.2^*

API service · Nebius Token Factory · Qwen/Qwen3.8-27B

Provider

Nebius Token Factory^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.45^*
output: 3^*
cache_read: 0.1^*

API service · Kosmik Compute · qwen/qwen3.8-27b

Provider

Kosmik Compute^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.35^*
output: 2.2^*
cache_read: 0.09^*

API service · IteraCompute · qwen/qwen3.8-27b

Provider

IteraCompute^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 131,072^*
output: 8,192^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

API service · Neuralwatt · qwen-3.8-27b-flex

Provider

Neuralwatt^*

Model

qwen-3.8-27b-flex^*

Snapshot

2026-10-26^*

Token limits

context: 262,128^*
output: 131,072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

Yes^*

Prices (USD per million tokens)

input: 0.2925^*
output: 2.08^*
cache_read: 0.1625^*

API service · engy · qwen3.8-27b

Provider

engy^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,001,536^*
input: 936,000^*
output: 65,536^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.045^*
output: 0.32^*
cache_read: 0.015^*

API service · Thinking Machines · Qwen/Qwen3.8-27B:peft:262144

Provider

Thinking Machines^*

Model

Qwen/Qwen3.8-27B:peft:262144^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.6975^*
output: 5.595^*
cache_read: 0.1395^*

API service · Neuralwatt · qwen-3.8-27b

Provider

Neuralwatt^*

Model

qwen-3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,128^*
output: 131,072^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

Yes^*

Prices (USD per million tokens)

input: 0.45^*
output: 3.2^*
cache_read: 0.25^*

API service · Regolo AI · qwen3.8-27b

Provider

Regolo AI^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 120,000^*
output: 120,000^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.58^*
output: 2.42^*

API service · OrcaRouter · qwen/qwen3.8-27b

Provider

OrcaRouter^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.33^*
output: 2.4^*

API service · RunInfra · Qwen/Qwen3.8-27B

Provider

RunInfra^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.1^*
output: 0.4^*
cache_read: 0.01^*

API service · Prime Inference · qwen/qwen3.8-27b

Provider

Prime Inference^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 235,929^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.99^*
output: 3.2^*

API service · Charm Hyper · qwen3.8-27b

Provider

Charm Hyper^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 128,000^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- minimal^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.5^*
output: 3^*
cache_read: 0.1^*

API service · DevPass (LLM Gateway) · Qwen3.8-27B

Provider

DevPass (LLM Gateway)^*

Model

Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,000^*
output: 32,768^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.08^*
output: 0.35^*
cache_read: 0.05^*

API service · Eden AI · qwen/qwen3.8-27b

Provider

Eden AI^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.5^*
output: 3^*
cache_read: 0.1^*
cache_write: 0.625^*

API service · Vercel AI Gateway · alibaba/qwen3.8-27b

Provider

Vercel AI Gateway^*

Model

alibaba/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 131,072^*

Modalities

input: text^*
image^*
pdf^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.5^*
output: 3^*
cache_read: 0.1^*
cache_write: 0.625^*

API service · AI/ML API · alibaba/qwen3.8-27b

Provider

AI/ML API^*

Model

alibaba/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 131,072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_details^*

Prices (USD per million tokens)

input: 0.4761^*
output: 3.3856^*

API service · AMD · Qwen3.8-27B

Provider

AMD^*

Model

Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- low^*
- medium^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

Yes^*

API service · Deep Infra · Qwen/Qwen3.8-27B

Provider

Deep Infra^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.2^*
output: 2.5^*
cache_read: 0.05^*

API service · Scaleway · qwen3.8-27b

Provider

Scaleway^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Availability status

beta^*

Prices (USD per million tokens)

input: 0.684^*
output: 3.762^*
reasoning: 3.762^*
cache_read: 0.137^*

API service · AKI.IO · qwen3.8-27b

Provider

AKI.IO^*

Model

qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.33645^*
output: 2.4673^*
cache_read: 0.11215^*

API service · Tempr Gateway · cerebras/qwen-3.8-27b

Provider

Tempr Gateway^*

Model

cerebras/qwen-3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 131,072^*
output: 40,960^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.99^*
output: 1.49^*

API service · Berget.AI · Qwen/Qwen3.8-27B-FP8

Provider

Berget.AI^*

Model

Qwen/Qwen3.8-27B-FP8^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 65,536^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.46^*
output: 3.48^*

API service · Cerebras · qwen-3.8-27b

Provider

Cerebras^*

Model

qwen-3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 131,072^*
output: 40,960^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.99^*
output: 1.49^*
cache_read: 0.99^*

API service · evroc · Qwen/Qwen3.8-27B

Provider

evroc^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.87^*
output: 3.5^*

API service · EmpirioLabs AI · qwen3-8-27b

Provider

EmpirioLabs AI^*

Model

qwen3-8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.17^*
output: 0.5^*
cache_read: 0.08^*

API service · CoreWeave · Qwen/Qwen3.8-27B

Provider

CoreWeave^*

Model

Qwen/Qwen3.8-27B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.4^*
output: 3^*
cache_read: 0.15^*

API service · Novita AI · qwen/qwen3.8-27b

Provider

Novita AI^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 1,000,000^*
output: 131,072^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*
type
effort^*
values
- low^*
- medium^*
- xhigh^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.42^*
output: 3^*
cache_read: 0.085^*

API service · Kilo Gateway · qwen/qwen3.8-27b

Provider

Kilo Gateway^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 235,929^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.425^*
output: 2.55^*
cache_read: 0.085^*
cache_write: 0.53125^*

API service · NanoGPT · TEE/qwen3.8-27b

Provider

NanoGPT^*

Model

TEE/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
input: 262,144^*
output: 262,144^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.4^*
output: 3^*
cache_read: 0.15^*

API service · NanoGPT · qwen/qwen3.8-27b:thinking

Provider

NanoGPT^*

Model

qwen/qwen3.8-27b:thinking^*

Snapshot

2026-10-26^*

Token limits

context: 1,048,576^*
input: 1,048,576^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.15^*
output: 0.7^*
cache_read: 0.04^*

API service · ai& · qwen/qwen3.8-27b

Provider

ai&^*

Model

qwen/qwen3.8-27b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 32,768^*

Modalities

input: text^*
image^*
video^*
pdf^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- low^*
- medium^*
- xhigh^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.4^*
output: 3^*
cache_read: 0.2^*

Reasoning

Yes^*

Temperature control

Yes^*

Tool calling

Yes^*

* Provisional data