GeekRadar / The comparison desk

COMPARE.

AI models

alibaba

Qwen 3.6 35B-A3B

AI model Released Apr 14, 2026

Context window: 262,144 tokens^*
Maximum output: 65,536 tokens^*
Open weights: Yes^*

Capability & preference

General capability · ECI

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

Qwen 3.6 35B-A3B 144.0^* Qwen 3.6 35B-A3B · 95% interval 142.0–145.9

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

Qwen 3.6 35B-A3B

Tested configuration Radar task score

Unrated

3/4 core tests · not enough evidence

4 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

Qwen 3.6 35B-A3B 84.8^*% Approx. 95% interval: 79.8–89.9% · 2026-08-07

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

Qwen 3.6 35B-A3B 22.0^*% Approx. 95% interval: 13.8–30.2% · 2026-08-27

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

Qwen 3.6 35B-A3B 20.4^*% Approx. 95% interval: 15.7–25.0% · 2026-08-30

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

Qwen 3.6 35B-A3B Not available

Competition mathematics

OTIS Mock AIME 2024-2025 · Separate result

Competition problems with model-extracted answers checked against an exact key. Earlier grading procedures are excluded.

Qwen 3.6 35B-A3B 68.9^*% Approx. 95% interval: 55.2–82.6% · 2026-08-07

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

Benchmark results

Run it locally

Inference · memory estimate

Qwen 3.6 35B-A3B

67.0^* GiB checkpoint tensor payload · 35.95 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: 65,536 tokens^*
Reasoning: Yes^*
Tool calling: Yes^*
Open weights: Yes^*
Model license: apache-2.0^*
Checkpoint tensor payload: 66.97 GiB^*

Input modalities

text^*
image^*
video^*

Output modalities

text^*

Processing & platform

Architecture: qwen3_5_moe^*

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: 35,951,822,704^*
Checkpoint tensor bytes: 71,903,645,408^*
Checkpoint data type: BF16^*
Architecture: qwen3_5_moe^*

Specifications 3 · 51 fields

NL2Repo

suite: NL2Repo
workload: reported score · Not specified
score: 29.4^*

Scope and conditions

Test conditions

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

HallusionBench

suite: HallusionBench
workload: reported score
score: 69.8^*

Scope and conditions

Test conditions

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

QwenWebBench

suite: QwenWebBench
workload: reported score · Internal
score: 1,397.0^*
unit: Elo

Scope and conditions

Test conditions

Metric: BT/Elo rating^*
Checkpoint version: Not specified^*
Languages: English and Chinese^*
Categories: Seven frontend application categories^*
Judge: Multimodal automatic judge^*
Task set: Internal^*

OmniDocBench1.5

suite: OmniDocBench1.5
version: 1.5
workload: reported score
score: 89.9^*

Scope and conditions

Test conditions

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

TAU3-Bench

suite: TAU3-Bench
workload: reported score
score: 67.2^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
User model: gpt-5.2, low reasoning effort^*
Retrieval: Default BM25^*

CharXiv(RQ)

suite: CharXiv(RQ)
workload: reported score
score: 78.0^*

Scope and conditions

Test conditions

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

VITA-Bench

suite: VITA-Bench
workload: reported score · Average subdomain score
score: 35.6^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Judge: claude-4-sonnet^*
Statistic: Average subdomain score^*

CC-OCR

suite: CC-OCR
workload: reported score
score: 81.9^*

Scope and conditions

Test conditions

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

AI2D TEST

suite: AI2D_TEST
workload: reported score
score: 92.7^*

Scope and conditions

Test conditions

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

DeepPlanning

suite: DeepPlanning
workload: reported score
score: 25.9^*

Scope and conditions

Test conditions

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

Tool Decathlon

suite: Tool Decathlon
workload: reported score
score: 26.9^*

Scope and conditions

Test conditions

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

RefCOCO(avg)

suite: RefCOCO(avg)
workload: reported score
score: 92.0^*

Scope and conditions

Test conditions

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

MCPMark

suite: MCPMark
workload: reported score · GitHub MCP v0.30.3
score: 37.0^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: GitHub MCP v0.30.3^*
Truncation: Playwright responses at 32K tokens^*

ODInW13

suite: ODInW13
workload: reported score
score: 50.8^*

Scope and conditions

Test conditions

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

MCP-Atlas

suite: MCP-Atlas
workload: reported score · Public set
score: 62.8^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Judge: gemini-2.5-pro^*
Task set: Public set^*

WideSearch

suite: WideSearch
workload: reported score
score: 60.1^*

Scope and conditions

Test conditions

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

EmbSpatialBench

suite: EmbSpatialBench
workload: reported score
score: 84.3^*

Scope and conditions

Test conditions

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

MMMU

suite: MMMU
workload: reported score
score: 81.7^*

Scope and conditions

Test conditions

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

SWE-bench Verified

suite: SWE-bench Verified
workload: reported score · Internal agent scaffold: bash and file editing · Public benchmark
score: 73.4^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Internal agent scaffold: bash and file editing^*
Temperature: 1.0^*
Top p: 0.95^*
Context length: 200K tokens^*
Task set: Public benchmark^*

RefSpatialBench

suite: RefSpatialBench
workload: reported score
score: 64.3^*

Scope and conditions

Test conditions

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

MMLU-Pro

suite: MMLU-Pro
workload: reported score
score: 85.2^*

Scope and conditions

Test conditions

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

VideoMME (w sub.)

suite: VideoMME (w sub.)
workload: reported score
score: 86.6^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Variant: Subtitles enabled^*

MMLU-Redux

suite: MMLU-Redux
workload: reported score
score: 93.3^*

Scope and conditions

Test conditions

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

VideoMME (w/o sub.)

suite: VideoMME (w/o sub.)
workload: reported score
score: 82.5^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Variant: Subtitles disabled^*

SuperGPQA

suite: SuperGPQA
workload: reported score
score: 64.7^*

Scope and conditions

Test conditions

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

VideoMMMU

suite: VideoMMMU
workload: reported score
score: 83.7^*

Scope and conditions

Test conditions

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

C-Eval

suite: C-Eval
workload: reported score
score: 90.0^*

Scope and conditions

Test conditions

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

MLVU

suite: MLVU
workload: reported score
score: 86.2^*

Scope and conditions

Test conditions

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

MVBench

suite: MVBench
workload: reported score
score: 74.6^*

Scope and conditions

Test conditions

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

GPQA

suite: GPQA
workload: reported score
score: 86.0^*

Scope and conditions

Test conditions

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

LVBench

suite: LVBench
workload: reported score
score: 71.4^*

Scope and conditions

Test conditions

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

HLE

suite: HLE
workload: reported score
score: 21.4^*

Scope and conditions

Test conditions

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

LiveCodeBench v6

suite: LiveCodeBench v6
version: 6
workload: reported score
score: 80.4^*

Scope and conditions

Test conditions

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

HMMT Feb 25

suite: HMMT Feb 25
workload: reported score
score: 90.7^*

Scope and conditions

Test conditions

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

MMMU-Pro

suite: MMMU-Pro
workload: reported score
score: 75.3^*

Scope and conditions

Test conditions

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

SWE-bench Multilingual

suite: SWE-bench Multilingual
workload: reported score · Internal agent scaffold: bash and file editing · Public benchmark
score: 67.2^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Internal agent scaffold: bash and file editing^*
Temperature: 1.0^*
Top p: 0.95^*
Context length: 200K tokens^*
Task set: Public benchmark^*

HMMT Nov 25

suite: HMMT Nov 25
workload: reported score
score: 89.1^*

Scope and conditions

Test conditions

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

HMMT Feb 26

suite: HMMT Feb 26
workload: reported score
score: 83.6^*

Scope and conditions

Test conditions

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

IMOAnswerBench

suite: IMOAnswerBench
workload: reported score
score: 78.9^*

Scope and conditions

Test conditions

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

AIME26

suite: AIME26
workload: reported score · Full AIME 2026 I and II
score: 92.7^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Task set: Full AIME 2026 I and II^*

Mathvista(mini)

suite: Mathvista(mini)
workload: reported score
score: 86.4^*

Scope and conditions

Test conditions

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

SWE-bench Pro

suite: SWE-bench Pro
workload: reported score · Internal agent scaffold: bash and file editing · Corrected public SWE-bench Pro task set
score: 49.5^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Internal agent scaffold: bash and file editing^*
Temperature: 1.0^*
Top p: 0.95^*
Context length: 200K tokens^*
Task set: Corrected public SWE-bench Pro task set^*

ZEROBench sub

suite: ZEROBench_sub
workload: reported score
score: 34.4^*

Scope and conditions

Test conditions

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

Terminal-Bench 2.0

suite: Terminal-Bench 2.0
version: 2.0
workload: reported score · Harbor/Terminus-2 · Mean of five runs
score: 51.5^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: Harbor/Terminus-2^*
Timeout: 3 hours^*
Hardware: 32 CPU / 48 GB RAM^*
Runs: 5^*
Statistic: Mean of five runs^*
Temperature: 1.0^*
Top p: 0.95^*
Top k: 20^*
Maximum output: 80K tokens^*
Context length: 256K tokens^*

Claw-Eval Avg

suite: Claw-Eval Avg
workload: reported score
score: 68.7^*

Scope and conditions

Test conditions

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

Claw-Eval Pass^3

suite: Claw-Eval Pass^3
workload: reported score
score: 50.0^*

Scope and conditions

Test conditions

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

RealWorldQA

suite: RealWorldQA
workload: reported score
score: 85.3^*

Scope and conditions

Test conditions

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

MMBench EN-DEV-v1.1

suite: MMBench EN-DEV-v1.1
version: 1.1
workload: reported score
score: 92.8^*

Scope and conditions

Test conditions

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

SkillsBench Avg5

suite: SkillsBench Avg5
workload: reported score · OpenCode · Self-contained subset, API-dependent tasks excluded · Mean of five runs
score: 28.7^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Harness: OpenCode^*
Tasks: 78^*
Runs: 5^*
Statistic: Mean of five runs^*
Task set: Self-contained subset, API-dependent tasks excluded^*

QwenClawBench

suite: QwenClawBench
workload: reported score · Internal real-user distribution
score: 52.6^*

Scope and conditions

Test conditions

Metric: reported score^*
Checkpoint version: Not specified^*
Task set: Internal real-user distribution^*
Temperature: 0.6^*
Context length: 256K tokens^*

SimpleVQA

suite: SimpleVQA
workload: reported score
score: 58.9^*

Scope and conditions

Test conditions

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

Specifications 4 · 83 fields

File attachments

Yes^*

Architecture

qwen3_5_moe^*

Attention bias

No^*

Attention dropout

0.0^*

Checkpoint data type

bfloat16^*

Full attention interval

4^*

Attention head dimension

256^*

Activation function

silu^*

Hidden dimension

2,048^*

Attention layer types

Linear attention key dimension

128^*

Linear attention key heads

16^*

Linear attention value heads

32^*

Linear attention value dimension

128^*

Expert intermediate dimension

512^*

Attention heads

16^*

Experts

256^*

Active experts per token

8^*

Transformer layers

40^*

Key/value heads

2^*

Rotary embedding fraction

0.25^*

RMS normalization epsilon

1.0e-6^*

Shared expert dimension

512^*

Tied word embeddings

No^*

Vocabulary size

248,320^*

Checkpoint licence

apache-2.0^*

Checkpoint tensor bytes

71,903,645,408^* bytes

Saved tensor elements

35,951,822,704^* elements

Checkpoint tensor payload

66.965488^* GiB

Context window

262,144^* tokens

Model family

qwen^*

Input modalities

text^*
image^*
video^*

Maximum output

65,536^* tokens

Output modalities

text^*

API service · Neuralwatt · qwen3.6-35b

Provider

Neuralwatt^*

Model

qwen3.6-35b^*

Snapshot

2026-10-26^*

Token limits

context: 131,056^*
output: 131,056^*

Modalities

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

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- high^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

Yes^*

Prices (USD per million tokens)

input: 0.29^*
output: 1.15^*
cache_read: 0.029^*

API service · CoreWeave · Qwen/Qwen3.6-35B-A3B

Provider

CoreWeave^*

Model

Qwen/Qwen3.6-35B-A3B^*

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: 0.25^*
output: 1.25^*
cache_read: 0.25^*

API service · InferX · Qwen3.6-35B-A3B-FP8

Provider

InferX^*

Model

Qwen3.6-35B-A3B-FP8^*

Snapshot

2026-10-26^*

Token limits

context: 262,000^*
output: 65,536^*

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^*

API service · Thinking Machines · Qwen/Qwen3.6-35B-A3B:peft:262144

Provider

Thinking Machines^*

Model

Qwen/Qwen3.6-35B-A3B: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: 0.45^*
output: 1.335^*
cache_read: 0.09^*

API service · Ambient · qwen/qwen3.6-35b-a3b

Provider

Ambient^*

Model

qwen/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.15^*
output: 1^*
cache_read: 0.15^*
cache_write: 0^*

API service · Kilo Gateway · qwen/qwen3.6-35b-a3b

Provider

Kilo Gateway^*

Model

qwen/qwen3.6-35b-a3b^*

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^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.1^*
output: 0.95^*
cache_read: 0.05^*

API service · LLMTR · qwen3-6-35b

Provider

LLMTR^*

Model

qwen3-6-35b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

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

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

No^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 5^*
output: 10^*

API service · Hugging Face · Qwen/Qwen3.6-35B-A3B

Provider

Hugging Face^*

Model

Qwen/Qwen3.6-35B-A3B^*

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: 0.15^*
output: 0.95^*

API service · InferX · Qwen3.6-35B-A3B-fp8-no-thinking

Provider

InferX^*

Model

Qwen3.6-35B-A3B-fp8-no-thinking^*

Snapshot

2026-10-26^*

Token limits

context: 262,000^*
output: 65,536^*

Modalities

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

Reasoning

No^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

API service · NanoGPT · qwen/qwen3.6-35b-a3b

Provider

NanoGPT^*

Model

qwen/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

context: 1,048,576^*
input: 1,048,576^*
output: 16,384^*

Modalities

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

Reasoning

No^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.112^*
output: 0.8^*
cache_read: 0.056^*

API service · Umans AI Coding Plan · umans-qwen3.6-35b-a3b

Provider

Umans AI Coding Plan^*

Model

umans-qwen3.6-35b-a3b^*

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^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

No^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

API service · SiliconFlow (China) · Qwen/Qwen3.6-35B-A3B

Provider

SiliconFlow (China)^*

Model

Qwen/Qwen3.6-35B-A3B^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

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

Reasoning

No^*

Tool calling

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input: 0.26900546^*
output: 1.61403276^*

API service · Opper · qwen3.6-35b-a3b

Provider

Opper^*

Model

qwen3.6-35b-a3b^*

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^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.248^*
output: 1.485^*

API service · SaladCloud AI Gateway · qwen3.6-35b-a3b

Provider

SaladCloud AI Gateway^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
input: 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: 0.09^*
output: 0.6^*

API service · QVAC · qwen3.6-35b-a3b

Provider

QVAC^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

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

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

API service · LLM Gateway · alibaba/qwen3.6-35b-a3b

Provider

LLM Gateway^*

Model

alibaba/qwen3.6-35b-a3b^*

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^*
- minimal^*
- low^*
- medium^*
- high^*
- xhigh^*
- max^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.375^*
output: 2.25^*

API service · OrcaRouter · qwen/qwen3.6-35b-a3b

Provider

OrcaRouter^*

Model

qwen/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

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: 0.248^*
output: 1.485^*

API service · Novita AI · qwen/qwen3.6-35b-a3b

Provider

Novita AI^*

Model

qwen/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

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^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.248^*
output: 1.485^*

API service · Boundless · qwen3.6

Provider

Boundless^*

Model

qwen3.6^*

Snapshot

2026-10-26^*

Token limits

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

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: 0.04^*
output: 0.35^*
cache_read: 0.02^*

API service · Thinking Machines · Qwen/Qwen3.6-35B-A3B

Provider

Thinking Machines^*

Model

Qwen/Qwen3.6-35B-A3B^*

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: 0.45^*
output: 1.335^*
cache_read: 0.09^*

API service · AKI.IO · qwen3.6-35b

Provider

AKI.IO^*

Model

qwen3.6-35b^*

Snapshot

2026-10-26^*

Token limits

context: 256,000^*
output: 32,768^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

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

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Availability status

deprecated^*

Prices (USD per million tokens)

input: 0.168225^*
output: 0.56075^*

API service · Scaleway · qwen3.6-35b-a3b

Provider

Scaleway^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

context: 128,000^*
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^*

Availability status

beta^*

Knowledge cutoff

2025-04^*

Prices (USD per million tokens)

input: 0.280375^*
output: 1.68225^*

API service · OpenRouter · qwen/qwen3.6-35b-a3b

Provider

OpenRouter^*

Model

qwen/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

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: 0.1^*
output: 0.95^*
cache_read: 0.05^*

API service · LLM Gateway · novita/qwen3.6-35b-a3b

Provider

LLM Gateway^*

Model

novita/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 64,000^*

Modalities

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

Reasoning

Yes^*

Reasoning controls

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

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.248^*
output: 1.485^*

API service · DevPass (LLM Gateway) · qwen3.6-35b-a3b

Provider

DevPass (LLM Gateway)^*

Model

qwen3.6-35b-a3b^*

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^*
- minimal^*
- low^*
- medium^*
- high^*
- xhigh^*
- max^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.248^*
output: 1.485^*

API service · Merge Gateway · qwen/qwen3.6-35b-a3b

Provider

Merge Gateway^*

Model

qwen/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.248^*
output: 1.485^*
cache_read: 0.0496^*

API service · engy · qwen3.6-35b-a3b

Provider

engy^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

context: 208,192^*
input: 200,000^*
output: 8,192^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.045^*
output: 0.3^*
cache_read: 0.015^*

API service · AIHubMix · qwen3.6-35b-a3b

Provider

AIHubMix^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

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^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.254^*
output: 1.524^*

API service · Neuralwatt · qwen3.6-35b-flex

Provider

Neuralwatt^*

Model

qwen3.6-35b-flex^*

Snapshot

2026-10-26^*

Token limits

context: 131,056^*
output: 131,056^*

Modalities

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

Reasoning

Yes^*

Reasoning controls

type
effort^*
values
- none^*
- high^*
type
budget_tokens^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Interleaved reasoning

Yes^*

Prices (USD per million tokens)

input: 0.1885^*
output: 0.7475^*
cache_read: 0.01885^*

API service · 302.AI · qwen3.6-35b-a3b

Provider

302.AI^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

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: 0.28^*
output: 1.7^*

API service · EmpirioLabs AI · qwen3-6-35b-a3b

Provider

EmpirioLabs AI^*

Model

qwen3-6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

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

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.07^*
output: 0.42^*
cache_read: 0.035^*

API service · Hetzner · Qwen/Qwen3.6-35B-A3B-FP8

Provider

Hetzner^*

Model

Qwen/Qwen3.6-35B-A3B-FP8^*

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 · Cortecs · qwen3.6-35b-a3b

Provider

Cortecs^*

Model

qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

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: 0.167^*
output: 0.557^*

API service · Umans AI · umans-flash

Provider

Umans AI^*

Model

umans-flash^*

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^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

No^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

Prices (USD per million tokens)

input: 0.15^*
output: 1^*
cache_read: 0.05^*

API service · Umans AI Coding Plan · umans-flash

Provider

Umans AI Coding Plan^*

Model

umans-flash^*

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^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

No^*

File attachments

Yes^*

Interleaved reasoning

field: reasoning_content^*

API service · NanoGPT · TEE/qwen3.6-35b-a3b

Provider

NanoGPT^*

Model

TEE/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

input: text^*
output: text^*

Reasoning

No^*

Tool calling

No^*

Structured output

No^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.2^*
output: 1.27^*
cache_read: 0.1^*

API service · NaN · qwen3.6

Provider

NaN^*

Model

qwen3.6^*

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^*
- high^*
- max^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

API service · NanoGPT · qwen/qwen3.6-35b-a3b:thinking

Provider

NanoGPT^*

Model

qwen/qwen3.6-35b-a3b:thinking^*

Snapshot

2026-10-26^*

Token limits

context: 1,048,576^*
input: 1,048,576^*
output: 16,384^*

Modalities

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

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

No^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.112^*
output: 0.8^*
cache_read: 0.056^*

API service · evroc · Qwen/Qwen3.6-35B-A3B

Provider

evroc^*

Model

Qwen/Qwen3.6-35B-A3B^*

Snapshot

2026-10-26^*

Token limits

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

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: 0.345^*
output: 1.38^*

API service · GreenPT · qwen3.6-35b-a3b

Provider

GreenPT^*

Model

qwen3.6-35b-a3b^*

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^*
- minimal^*
- low^*
- medium^*
- high^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.342^*
output: 2.052^*

API service · Deep Infra · Qwen/Qwen3.6-35B-A3B

Provider

Deep Infra^*

Model

Qwen/Qwen3.6-35B-A3B^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 81,920^*

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: 0.1^*
output: 0.95^*
cache_read: 0.1^*

API service · SiliconFlow · Qwen/Qwen3.6-35B-A3B

Provider

SiliconFlow^*

Model

Qwen/Qwen3.6-35B-A3B^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

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

Reasoning

No^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.24^*
output: 1.8^*
cache_read: 0.15^*

API service · NEAR AI Cloud · Qwen/Qwen3.6-35B-A3B-FP8

Provider

NEAR AI Cloud^*

Model

Qwen/Qwen3.6-35B-A3B-FP8^*

Snapshot

2026-10-26^*

Token limits

context: 262,144^*
output: 8,192^*

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Reasoning controls

type
toggle^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.17^*
output: 1.1^*
cache_read: 0.056^*

API service · Venice AI · qwen3-6-35b-a3b

Provider

Venice AI^*

Model

qwen3-6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

context: 256,000^*
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: 0.1^*
output: 1^*

API service · Neuralwatt · qwen3.6-35b-fast

Provider

Neuralwatt^*

Model

qwen3.6-35b-fast^*

Snapshot

2026-10-26^*

Token limits

context: 131,056^*
output: 131,056^*

Modalities

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

Reasoning

No^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

Yes^*

Prices (USD per million tokens)

input: 0.29^*
output: 1.15^*
cache_read: 0.029^*

API service · Zenifra · alibaba/qwen3.6-35b-a3b

Provider

Zenifra^*

Model

alibaba/qwen3.6-35b-a3b^*

Snapshot

2026-10-26^*

Token limits

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

Modalities

input: text^*
output: text^*

Reasoning

Yes^*

Tool calling

Yes^*

Structured output

Yes^*

Temperature control

Yes^*

File attachments

No^*

Prices (USD per million tokens)

input: 0.19^*
output: 0.48^*

Reasoning

Yes^*

Temperature control

Yes^*

Tool calling

Yes^*

* Provisional data