LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3 30B A3B

alibaba·alibaba/qwen3-30b-a3b·GA·Open weights·qwen series
Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·LLM GatewayGateway
$0.076 / $0.23
Blended $0.11 · 2.4× spread
Context
128,000
Output limit
8,192
Knowledge cutoff
2025-04
Released / updated
2025-04-28 / 2025-04-28
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

Qwen3 30B A3B by alibaba is offered by 15 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is LLM Gateway at $0.076 / $0.228 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 2.4× across the providers that host it.

Median output speed is 87 tokens per second, with 0.58s to the first token.

The context window is 128,000 tokens at the reference host, but hosts report different limits, from 8,192 to 131,072, so the usable window depends on the provider you pick. It supports reasoning, 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 · rep. tier Reasoning

Intelligence—
Value—
Output speed87 tok/s
TTFT0.58 s

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

Available at 15 providers15 with public prices

  • ProviderInput / Output
  • LLM GatewayGateway
    $0.076 / $0.23
    Context 8,192 ⚠Output limit 4,096
  • DevPass (LLM Gateway)Gateway
    $0.076 / $0.23
    Context 32,768 ⚠Output limit 16,384
  • Cloudflare Workers AICloud
    @cf/qwen/qwen3-30b-a3b-fp8
    $0.051 / $0.34
    Context 32,768 ⚠Output limit 32,768deprecated
  • HeliconeGateway
    $0.08 / $0.29
    Context 41,000 ⚠Output limit 41,000
  • Jiekou.AIGateway
    qwen/qwen3-30b-a3b-fp8
    $0.09 / $0.45
    Context 40,960 ⚠Output limit 20,000
  • ZeroGPUGateway
    qwen3-30b-a3b-fp8
    $0.10 / $0.45
    Context 32,768 ⚠Output limit 16,384
  • QiniuGateway
    $0.11 / $0.43
    Context 40,000 ⚠Output limit 4,096deprecated
  • NanoGPTGateway
    $0.12 / $0.50
    Cache read $0.12Context 41,000 ⚠Output limit 32,768
  • OpenRouterGateway
    $0.12 / $0.50
    Context 40,960 ⚠Output limit 16,384
  • Kilo GatewayGateway
    $0.12 / $0.50
    Context 40,960 ⚠Output limit 16,384
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
LLM GatewayGateway$0.076$0.23——8,192 ⚠4,096
DevPass (LLM Gateway)Gateway$0.076$0.23——32,768 ⚠16,384
Cloudflare Workers AI
@cf/qwen/qwen3-30b-a3b-fp8
Cloud$0.051$0.34——32,768 ⚠32,768deprecated
HeliconeGateway$0.08$0.29——41,000 ⚠41,000
Jiekou.AI
qwen/qwen3-30b-a3b-fp8
Gateway$0.09$0.45——40,960 ⚠20,000
ZeroGPU
qwen3-30b-a3b-fp8
Gateway$0.10$0.45——32,768 ⚠16,384
QiniuGateway$0.11$0.43——40,000 ⚠4,096deprecated
NanoGPTGateway$0.12$0.50$0.12—41,000 ⚠32,768
OpenRouterGateway$0.12$0.50——40,960 ⚠16,384
Kilo GatewayGateway$0.12$0.50——40,960 ⚠16,384

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 = noneeffort = high

5 / 15 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1LLM Gateway$26.60
2DevPass (LLM Gateway)$26.60
3Cloudflare Workers AI$26.93
4Helicone$30.50
5Jiekou.AI$40.50
6ZeroGPU$42.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.13$02026-08-052026-11-17
2026-11-17Input list —Output list —Min blended $0.11

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—Qwen3 235B-A22B Thinking 2507same lab—Qwen3 30B-A3B Instruct 2507same lab—
Data partly from models.dev (MIT)