LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3.5 122B-A10B

alibaba·alibaba/qwen3.5-122b-a10b·GA·Open weights·qwen series
Qwen vision-language model for visual reasoning, documents, and agent tasks

Specs & pricing

Input / output per 1M tokens
Official price·Alibaba
$0.40 / $3.20
Blended $1.10 · Cache read —
Lowest paid·AIHubMixGateway
$0.11 / $0.90
Blended $0.31 · 10× spread
Context
262,144
Output limit
65,536
Knowledge cutoff
2025-04
Released / updated
2026-02-23 / 2026-02-23
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Weights
Hugging Face

Qwen3.5 122B-A10B by alibaba is offered by 27 providers on this page. Its official list price is $0.40 per 1M input tokens and $3.20 per 1M output tokens. The lowest paid channel is AIHubMix at $0.113 / $0.901 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.

Median output speed is 141 tokens per second, with 2.2s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 131,072 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 Non-reasoning

Intelligence—
Value—
Output speed141 tok/s
TTFT2.2 s

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

Available at 27 providers27 with public prices

  • ProviderInput / Output
  • AIHubMixGateway
    $0.11 / $0.90
    tiered >128K: $0.28
    Context 262,144Output limit 65,536
  • Merge GatewayGateway
    $0.12 / $0.92
    Cache read $0.023Context 131,072 ⚠Output limit 32,768
  • EmpirioLabs AIGateway
    qwen3-5-122b-a10b
    $0.12 / $0.92
    tiered >128K: $0.29
    Cache read $0.12Context 258,048 ⚠Output limit 64,000
  • OrcaRouterGateway
    $0.12 / $0.92
    tiered >128K: $0.29
    Context 262,144Output limit 65,536
  • SiliconFlow (China)Cloud
    Qwen/Qwen3.5-122B-A10B
    $0.12 / $0.96
    tiered >128K: $0.30
    Context 262,144Output limit 65,536
  • NanoGPTGateway
    $0.26 / $2.08
    Cache read $0.13Context 131,072 ⚠Output limit 32,768
  • NanoGPTGateway
    qwen/qwen3.5-122b-a10b:thinking
    $0.26 / $2.08
    Cache read $0.13Context 131,072 ⚠Output limit 32,768
  • SiliconFlowCloud
    Qwen/Qwen3.5-122B-A10B
    $0.26 / $2.08
    Context 262,144Output limit 262,144
  • NeonCloud
    qwen35-122b-a10b
    $0.22 / $2.20
    Context 262,144Output limit 25,000
  • OpenRouterGateway
    $0.26 / $2.08
    Context 262,144Output limit 65,536
  • AlibabaOfficialFirst-party
    $0.40 / $3.20
    Context 262,144Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
AIHubMixGateway$0.11
tiered >128K: $0.28
$0.90——262,14465,536
Merge GatewayGateway$0.12$0.92$0.023—131,072 ⚠32,768
EmpirioLabs AI
qwen3-5-122b-a10b
Gateway$0.12
tiered >128K: $0.29
$0.92$0.12—258,048 ⚠64,000
OrcaRouterGateway$0.12
tiered >128K: $0.29
$0.92——262,14465,536
SiliconFlow (China)
Qwen/Qwen3.5-122B-A10B
Cloud$0.12
tiered >128K: $0.30
$0.96——262,14465,536
NanoGPTGateway$0.26$2.08$0.13—131,072 ⚠32,768
NanoGPT
qwen/qwen3.5-122b-a10b:thinking
Gateway$0.26$2.08$0.13—131,072 ⚠32,768
SiliconFlow
Qwen/Qwen3.5-122B-A10B
Cloud$0.26$2.08——262,144262,144
Neon
qwen35-122b-a10b
Cloud$0.22$2.20——262,14425,000
OpenRouterGateway$0.26$2.08——262,14465,536
AlibabaOfficialFirst-party$0.40$3.20——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 5 of 27 providers.

5 / 27 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Merge Gateway$57.81
2AIHubMix$67.56
3EmpirioLabs AI$68.85
4OrcaRouter$68.85
5SiliconFlow (China)$71.73
6NanoGPT$140.40
16Alibaba · Official$240.00
Switch to Merge Gateway to save $182.19/mo (76%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.20$02026-08-052026-09-28
2026-09-28Input list $0.40Output list $3.20Min blended $0.31

Benchmark1 items

NameConditionsScoreMetricSource
SWE-Bench Verified—72resolvedSource ↗

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

Artificial Analysis evaluations11 items

GPQA Diamond82.7%
Humanity's Last Exam15.9%
MMMU-Pro70.3%
CritPt0.9%
Terminal-Bench Hard29.5%
Terminal-Bench 2.147.2%
τ²-Bench Telecom84.5%
τ³-Bench Banking10.3%
GDPval-AA716
AA-LCR61.3%
IFBench50.8%

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-VL Plussame lab$0.20 / $1.60Qwen3.5 27Bsame lab$0.30 / $2.40
Data partly from models.dev (MIT) · Alibaba official docs ↗