Skip to content

Model

Qwen3-Coder 30B-A3B Instruct

Smaller Qwen coder for efficient local agents and repo-level fixes

23 providers · 23 listingsreleased knowledge cutoff 2025-04open weights
$0.06
lowest input /M · TensorX
$0.245
lowest output /M · Cortecs
262K
context window
262K
max output

Compare providers (sorted by listed input price)

21 of 23 providers publish a price for Qwen3-Coder 30B-A3B Instruct. The cheapest full-context option is TensorX at $0.06/$0.25 per M — 89% below Alibaba's own price. Listed prices span 8.9× for identical weights.

23 listings
Cache read /MCache write /MCapabilitiesStatus
TensorX
qwen/qwen3-coder-30b-a3b-instruct
$0.06$0.25$0.015$0.075262Kno reasoningtoolsno structuredno visionApr 1, 2025
Cortecs
qwen3-coder-30b-a3b-instruct
$0.067$0.245$0.014262Kno reasoningtoolsstructuredno visionApr 1, 2025
SiliconFlow (China)
Qwen/Qwen3-Coder-30B-A3B-Instruct
$0.07$0.28262Kno reasoningtoolsstructuredno visionNov 25, 2025
LLM Gateway
novita/qwen3-coder-30b-a3b-instruct
$0.07$0.27160Kno reasoningtoolsno structuredno visionApr 1, 2025
NovitaAI
qwen/qwen3-coder-30b-a3b-instruct
$0.07$0.27160Kno reasoningtoolsstructuredno visionOct 9, 2025
Hugging Face
Qwen/Qwen3-Coder-30B-A3B-Instruct
$0.07$0.26262Kno reasoningtoolsstructuredno visionApr 1, 2025
OVHcloud AI Endpoints
qwen3-coder-30b-a3b-instruct
$0.07$0.26262Kno reasoningtoolsstructuredno visionOct 28, 2025
DevPass (LLM Gateway)
qwen3-coder-30b-a3b-instruct
$0.07$0.27262Kno reasoningtoolsno structuredno visionApr 1, 2025
OpenRouter
qwen/qwen3-coder-30b-a3b-instruct
$0.07$0.28262Kno reasoningtoolsstructuredno visionApr 1, 2025
SiliconFlow
Qwen/Qwen3-Coder-30B-A3B-Instruct
$0.07$0.28262Kno reasoningtoolsstructuredno visionNov 25, 2025
Helicone
qwen3-coder-30b-a3b-instruct
$0.1$0.3262Kno reasoningtoolsno structuredno visionJul 31, 2025
NanoGPT
qwen3-coder-30b-a3b-instruct
$0.1$0.4$0.05128Kno reasoningtoolsstructuredno visionApr 1, 2025
Clarifai
qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct
$0.115$0.748262Kno reasoningtoolsno structuredno visionFeb 12, 2026
Vercel AI Gateway
alibaba/qwen3-coder-30b-a3b
$0.15$0.6262Kreasoningtoolsno structuredno visionApr 1, 2025
Amazon Bedrock
qwen.qwen3-coder-30b-a3b-v1:0
$0.15$0.6262Kno reasoningtoolsstructuredno visionSep 18, 2025
Scaleway
qwen3-coder-30b-a3b-instruct
$0.2$0.8128Kno reasoningtoolsno structuredno visionMar 17, 2026
Alibaba (China)
qwen3-coder-30b-a3b-instruct
$0.216$0.861262Kno reasoningtoolsno structuredno visionApr 1, 2025
GreenPT
qwen3-coder-30b-a3b-instruct
$0.285$1.08128Kno reasoningtoolsno structuredno visionApr 1, 2025
Kilo Gateway
qwen/qwen3-coder-30b-a3b-instruct
$0.292$1.46262Kno reasoningtoolsstructuredno visionApr 1, 2025
Alibaba
qwen3-coder-30b-a3b-instruct
$0.45$2.25262Kno reasoningtoolsno structuredno visionApr 1, 2025

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M
$0.06unchanged
Best output /M
$0.25unchanged
Provider coverage
23
22 at the start · 24 snapshots

Published best prices are unchanged.

24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

Current price badge for Qwen3-Coder 30B-A3B Instruct
![Qwen3-Coder 30B-A3B Instruct price](https://www.vaanalytics.in/badge/alibaba/qwen3-coder-30b-a3b-instruct.svg)
https://www.vaanalytics.in/badge/alibaba/qwen3-coder-30b-a3b-instruct.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →
  • capabilityvia amazon-bedrock · Sep 13, 2026
    • name: Qwen3 Coder 30B A3B Instruct → Qwen3-Coder 30B-A3B Instruct
    • description: Qwen coding model for software agents, repository edits, and code reasoning → Smaller Qwen coder for efficient local agents and repo-level fixes
    • open_weights: false → true
    • knowledge: 2024-04 → 2025-04
    • +1 more
  • contextvia cortecs · Sep 2, 2026
    • output: 262K → 262K tokens
  • repricedvia alibaba-cn · Aug 27, 2026
    • tiers: → [object Object],[object Object]
  • repricedvia alibaba · Aug 27, 2026
    • tiers: → [object Object],[object Object]
  • contextvia openrouter · Aug 25, 2026
    • output: 262K → 236K tokens
  • new providervia pendra · Aug 25, 2026

Benchmarks

Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.

Weights

Permissiveapache-2.031B params

Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.

licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.