LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 30B-A3B Instruct 2507

alibaba·alibaba/qwen3-30b-a3b-instruct-2507·GA·Open weights·qwen series
Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·SiliconFlowCloud
$0.09 / $0.30
Blended $0.14 · 3.3× spread
2 more $0 channels
Context
262,144
Output limit
262,144
Knowledge cutoff
2025-04
Released / updated
2025-07-28 / 2025-07-28
Capabilities
Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
License
Apache-2.0
Weights
Hugging Face

Qwen3 30B-A3B Instruct 2507 by alibaba is offered by 15 providers on this page. Public prices are shown for 13 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is SiliconFlow at $0.09 / $0.30 per 1M. Prices vary about 3.3× across the providers that host it. It also has 2 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 47 tokens per second, with 1s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. 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

Intelligence—
Value—
Output speed47 tok/s
TTFT1 s

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

Available at 15 providers13 with public prices · 2 free

  • ProviderInput / Output
  • ModelScopeCloud
    Qwen/Qwen3-30B-A3B-Instruct-2507
    Free
    Context 262,144Output limit 16,384
  • LMStudioCloud
    qwen/qwen3-30b-a3b-2507
    Free
    Context 262,144Output limit 16,384
  • SiliconFlowCloud
    Qwen/Qwen3-30B-A3B-Instruct-2507
    $0.09 / $0.30
    Context 262,000 ⚠Output limit 262,000
  • AmbientGateway
    $0.09 / $0.30
    Cache read $0.09Context 131,072 ⚠Output limit 32,768
  • Hugging FaceCloud
    Qwen/Qwen3-30B-A3B-Instruct-2507
    $0.09 / $0.30
    Context 262,144Output limit 16,384
  • CortecsGateway
    $0.099 / $0.30
    Context 262,000 ⚠Output limit 262,000
  • Nebius Token FactoryCloud
    Qwen/Qwen3-30B-A3B-Instruct-2507
    $0.10 / $0.30
    Cache read $0.10Context 262,144Output limit 8,192
  • OpenRouterGateway
    $0.10 / $0.30
    Cache read $0.10Context 262,144Output limit 235,929
  • Eden AIGateway
    nebius/Qwen/Qwen3-30B-A3B-Instruct-2507
    $0.10 / $0.30
    Cache read $0.10Context 262,144Output limit 16,384
  • Kilo GatewayGateway
    $0.10 / $0.30
    Cache read $0.10Context 262,144Output limit 235,929
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
ModelScope
Qwen/Qwen3-30B-A3B-Instruct-2507
CloudFree——262,14416,384
LMStudio
qwen/qwen3-30b-a3b-2507
CloudFree——262,14416,384
SiliconFlow
Qwen/Qwen3-30B-A3B-Instruct-2507
Cloud$0.09$0.30——262,000 ⚠262,000
AmbientGateway$0.09$0.30$0.09$0131,072 ⚠32,768
Hugging Face
Qwen/Qwen3-30B-A3B-Instruct-2507
Cloud$0.09$0.30——262,14416,384
CortecsGateway$0.099$0.30——262,000 ⚠262,000
Nebius Token Factory
Qwen/Qwen3-30B-A3B-Instruct-2507
Cloud$0.10$0.30$0.10—262,1448,192
OpenRouterGateway$0.10$0.30$0.10—262,144235,929
Eden AI
nebius/Qwen/Qwen3-30B-A3B-Instruct-2507
Gateway$0.10$0.30$0.10—262,14416,384
Kilo GatewayGateway$0.10$0.30$0.10—262,144235,929

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.

Your usage cost

Common scenarios
1SiliconFlow$33.00
2Ambient$33.00
3Hugging Face$33.00
4Cortecs$34.75
5Nebius Token Factory$35.00
6OpenRouter$35.00

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

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.14$02026-08-052026-10-09
2026-10-09Input list —Output list —Min blended $0.14

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—Qwen3 30B A3Bsame lab—Qwen3 30B A3B Thinking 2507same lab—
Data partly from models.dev (MIT)