LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3.5 397B-A17B

alibaba·alibaba/qwen3.5-397b-a17b·BETA·Open weights·qwen series
Large open Qwen multimodal MoE for visual agents and long technical tasks

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.60 / $3.60
Blended $1.35 · Cache read —
Lowest paid·AIHubMixGateway
$0.16 / $0.99
Blended $0.37 · 10× spread
1 more $0 channels
Context
262,144
Output limit
65,536
Knowledge cutoff
2025-04
Released / updated
2026-02-15 / 2026-02-15
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Weights
Hugging Face

Qwen3.5 397B-A17B by alibaba is offered by 41 providers on this page. Public prices are shown for 40 of them. Its official list price is $0.60 per 1M input tokens and $3.60 per 1M output tokens. The lowest paid channel is AIHubMix at $0.164 / $0.986 per 1M, about 3.6× 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 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 58 tokens per second, with 2.12s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 65,536 to 262,144, 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 Reasoning

Intelligence—
Value—
Output speed58 tok/s
TTFT2.12 s

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

Available at 41 providers40 with public prices · 1 free

  • ProviderInput / Output
  • UnoRouterGateway
    qwen3.5-397b-a17b:free
    Free
    Context 262,144Output limit 65,536deprecated
  • AIHubMixGateway
    $0.16 / $0.99
    tiered >128K: $0.41
    Context 262,144Output limit 65,536
  • Alibaba (China)OfficialFirst-party
    $0.17 / $1.03
    tiered >128K: $0.43
    Context 262,144Output limit 65,536
  • Merge GatewayGateway
    $0.17 / $1.03
    Cache read $0.034Context 131,072 ⚠Output limit 32,768
  • EmpirioLabs AIGateway
    qwen3-5-397b-a17b
    $0.17 / $1.03
    tiered >128K: $0.43
    Cache read $0.17Context 258,048 ⚠Output limit 64,000deprecated
  • OrcaRouterGateway
    $0.17 / $1.03
    tiered >128K: $0.43
    Context 262,144Output limit 65,536
  • QiniuGateway
    $0.17 / $1.04
    tiered >128K: $0.43
    Context 256,000 ⚠Output limit 64,000
  • SiliconFlowCloud
    Qwen/Qwen3.5-397B-A17B
    $0.39 / $2.34
    Context 262,144Output limit 262,144deprecated
  • Kilo GatewayGateway
    $0.39 / $2.34
    Context 262,144Output limit 81,920
  • TokenGoGateway
    $0.40 / $2.65
    Cache read $0.20Context 262,144Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
UnoRouter
qwen3.5-397b-a17b:free
GatewayFree——262,14465,536deprecated
AIHubMixGateway$0.16
tiered >128K: $0.41
$0.99——262,14465,536
Alibaba (China)OfficialFirst-party$0.17
tiered >128K: $0.43
$1.03——262,14465,536
Merge GatewayGateway$0.17$1.03$0.034—131,072 ⚠32,768
EmpirioLabs AI
qwen3-5-397b-a17b
Gateway$0.17
tiered >128K: $0.43
$1.03$0.17—258,048 ⚠64,000deprecated
OrcaRouterGateway$0.17
tiered >128K: $0.43
$1.03——262,14465,536
QiniuGateway$0.17
tiered >128K: $0.43
$1.04——256,000 ⚠64,000
SiliconFlow
Qwen/Qwen3.5-397B-A17B
Cloud$0.39$2.34——262,144262,144deprecated
Kilo GatewayGateway$0.39$2.34——262,14481,920
TokenGoGateway$0.40$2.65$0.20—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)budget_tokenseffort = noneeffort = loweffort = mediumeffort = higheffort = maxeffort = minimaleffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 9 of 41 providers.

4 / 41 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Merge Gateway$69.49
2AIHubMix$82.20
3Alibaba (China) · Official$86.00
4EmpirioLabs AI$86.00
5OrcaRouter$86.00
6Qiniu$86.96

1 more channels offer $0 (UnoRouter); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to Merge Gateway to save $16.51/mo (19%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.60$02026-08-052026-09-28
2026-09-28Input list $0.60Output list $3.60Min blended $0.37

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified—76.4resolvedSource ↗

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

Artificial Analysis evaluations21 items

GPQA Diamond89.3%
Humanity's Last Exam29.0%
HLE-Diamond12.4%
MMMU-Pro77.3%
CritPt1.7%
SciCode44.8%
Terminal-Bench Hard40.9%
Terminal-Bench 2.151.3%
Terminal-Bench 4.00.0%
τ²-Bench Telecom95.6%
τ³-Bench Banking13.4%
AutomationBench-AA6.9%
APEX-Agents-AA15.3%
EnterpriseOps-Gym-AA30.9%
ITBench-AA34.1%
AA-Briefcase563
GDPval-AA801
GDP.pdf12.2%
AA-LCR77.3%
MLCR-AA8.9%
IFBench78.8%

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 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20Qwen3.5 35B-A3Bsame lab$0.25 / $2.00Qwen3.5 4Bsame lab—
Data partly from models.dev (MIT) · Alibaba official docs ↗