LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3.6 35B-A3B

alibaba·alibaba/qwen3.6-35b-a3b·BETA·Open weights·qwen series
Open multimodal Qwen MoE for local agents that need vision, audio, and code

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.38 / $2.25
Blended $0.84 · Cache read —
Lowest paid·engyGateway
$0.045 / $0.30
Blended $0.11 · 11.3× spread
5 more $0 channels
Context
262,144
Output limit
65,536
Knowledge cutoff
2025-04
Released / updated
2026-04-17 / 2026-04-17
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Weights
Hugging Face

Qwen3.6 35B-A3B by alibaba is offered by 51 providers on this page. Public prices are shown for 44 of them. Its official list price is $0.375 per 1M input tokens and $2.25 per 1M output tokens. The lowest paid channel is engy at $0.045 / $0.30 per 1M, about 7.8× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 5 free ($0) channels and 1 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 110 tokens per second, with 2.07s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 16,384 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-04.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier Non-reasoning

Intelligence—
Value—
Output speed110 tok/s
TTFT2.07 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 51 providers44 with public prices · 5 free · 1 subscription-covered

  • ProviderInput / Output
  • Umans AI Coding PlanGateway
    umans-qwen3.6-35b-a3b
    Subscription
    Cache read $0Context 262,144Output limit 262,144deprecated
  • QVACGateway
    Free
    Context 262,144Output limit 65,536
  • NaNGateway
    qwen3.6
    Free
    Context 262,144Output limit 65,536
  • InferXGateway
    Qwen3.6-35B-A3B-FP8
    Free
    Context 262,000 ⚠Output limit 65,536
  • InferXGateway
    Qwen3.6-35B-A3B-fp8-no-thinking
    Free
    Context 262,000 ⚠Output limit 65,536
  • HetznerCloud
    Qwen/Qwen3.6-35B-A3B-FP8
    Free
    Cache read $0Context 262,144Output limit 262,144beta
  • engyGateway
    $0.045 / $0.30
    Cache read $0.015Context 208,192 ⚠Output limit 8,192
  • BoundlessGateway
    qwen3.6
    $0.04 / $0.35
    Cache read $0.02Context 262,144Output limit 65,536
  • EmpirioLabs AIGateway
    qwen3-6-35b-a3b
    $0.07 / $0.42
    Cache read $0.035Context 131,072 ⚠Output limit 16,384
  • SaladCloud AI GatewayGateway
    $0.09 / $0.60
    Context 262,144Output limit 262,144
  • AlibabaOfficialFirst-party
    $0.38 / $2.25
    Context 262,144Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Umans AI Coding Plan
umans-qwen3.6-35b-a3b
GatewaySubscription$0$0262,144262,144deprecated
QVACGatewayFree——262,14465,536
NaN
qwen3.6
GatewayFree——262,14465,536
InferX
Qwen3.6-35B-A3B-FP8
GatewayFree——262,000 ⚠65,536
InferX
Qwen3.6-35B-A3B-fp8-no-thinking
GatewayFree——262,000 ⚠65,536
Hetzner
Qwen/Qwen3.6-35B-A3B-FP8
CloudFree$0—262,144262,144beta
engyGateway$0.045$0.30$0.015—208,192 ⚠8,192
Boundless
qwen3.6
Gateway$0.04$0.35$0.02—262,14465,536
EmpirioLabs AI
qwen3-6-35b-a3b
Gateway$0.07$0.42$0.035—131,072 ⚠16,384
SaladCloud AI GatewayGateway$0.09$0.60——262,144262,144
AlibabaOfficialFirst-party$0.38$2.25——262,14465,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

Toggle (on / off)effort = loweffort = mediumeffort = higheffort = noneeffort = maxbudget_tokenseffort = minimaleffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 9 of 51 providers.

9 / 51 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1engy$20.40
2Boundless$23.10
3EmpirioLabs AI$30.80
4SaladCloud AI Gateway$48.00
5Neuralwatt$54.72
6NanoGPT$55.68
41Alibaba · Official$187.50

6 more channels offer $0 (Umans AI Coding Plan, QVAC, NaN etc.); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to engy to save $167.10/mo (89%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.25$02026-08-052026-10-20
2026-10-20Input list $0.38Output list $2.25Min blended $0.11

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified—73.4resolvedSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations11 items

GPQA Diamond81.7%
Humanity's Last Exam13.9%
MMMU-Pro71.0%
CritPt0.0%
Terminal-Bench Hard25.8%
Terminal-Bench 2.141.6%
τ²-Bench Telecom85.1%
τ³-Bench Banking5.4%
GDPval-AA854
AA-LCR64.3%
IFBench36.2%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20Claude Haiku 5.5cheaper alternative$0.10 / $0.50Qwen3.6 27Bsame lab$0.60 / $3.60Qwen3.6 Flashsame lab$0.25 / $1.50
Data partly from models.dev (MIT) · Alibaba official docs ↗