InferIndex
Language, English, EN
Account

ModelsQwenQwen3 30B A3B

Qwen3 30B A3B

qwen/qwen3-30b-a3b Compare →
MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.15
Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
$0.215
Offers
18
Providers
11

Cheapest right now

Greenference

via LLM Gateway

$0.114 blended / 1M tokens

No changepromo7D
in
$0.076
out
$0.228
Cached input
–

Promotion announced by LLM Gateway: −20% vs its usual price · Discount shown by the seller, no end date announced, seen on Oct 31, 2026Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.

Usual price at LLM Gateway $0.095 / $0.285

Public leaderboards

  • Text Arena, style controlThe series the source publishes by default for text since 16 May 2025: ranks corrected for the style of the answers (style control). #240 of 419Best rank in the source's rank spread, 240th to 268th, given the confidence intervals of all ranked models. 253rd by score. 1,327 1,322 to 1,331Arena Score · 26,156 votes

Source: Arena (opens in a new tab) · Data under the CC BY 4.0 license (creativecommons.org/licenses/by/4.0) · CC BY 4.0 (opens in a new tab) · scores and ranks as published on 28 Oct 2026; the presentation is ours

Qwen3 30B A3B: the lowest current price is $0.114 per million tokens (at a 3:1 input:output mix), a promotional price at Greenference, checked on ; the median of the 5 comparable offers is $0.15.

Listed offers, by price

Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.

Offers not counted in cheapest, median or most expensive (13)

  • $0.122 · Cloudflare via Eden AI · cannot be designated the cheapest
  • $0.143 · Greenference via Eden AI · cannot be designated the cheapest
  • $0.15 · Nebius via LLM Gateway · cannot be designated the cheapest
  • $0.197 · UCloud · cannot be designated the cheapest
  • $0.215 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.215 · DeepInfra via Hugging Face · another route of the same provider
  • $0.215 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.215 · FastRouter via FastRouter · cannot be designated the cheapest
  • $0.215 · Martian via Martian · cannot be designated the cheapest
  • $0.215 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.215 · DeepInfra via OpenRouter · another route of the same provider
  • $0.228 · Glama via Glama · cannot be designated the cheapest
  • $0.323 · DeepInfra · priority tier

Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.

Cloudflare

directYou buy access straight from the company that runs the model on its servers. · fp8

$0.122 blended / 1M tokens

in
$0.051
out
$0.335
Cached input
–

Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.

Cheapest offer and official list price, by day, 30 days
DayCheapest offerOfficial list price
2026-10-02$0.122, Cloudflare–
2026-10-03$0.122, Cloudflare–
2026-10-04$0.122, Cloudflare–
2026-10-05$0.122, Cloudflare–
2026-10-06$0.122, Cloudflare–
2026-10-07$0.122, Cloudflare–
2026-10-08$0.122, Cloudflare–
2026-10-09$0.122, Cloudflare–
2026-10-10$0.122, Cloudflare–
2026-10-11$0.122, Cloudflare–
2026-10-12$0.122, Cloudflare–
2026-10-13$0.122, Cloudflare–
2026-10-14$0.122, Cloudflare–
2026-10-15$0.122, Cloudflare–
2026-10-16$0.122, Cloudflare–
2026-10-17$0.122, Cloudflare–
2026-10-18$0.122, Cloudflare–
2026-10-19$0.122, Cloudflare–
2026-10-20$0.122, Cloudflare–
2026-10-21$0.122, Cloudflare–
2026-10-22$0.122, Cloudflare–
2026-10-23$0.114, Greenference, Promotional price–
2026-10-24$0.114, Greenference, Promotional price–
2026-10-25$0.114, Greenference, Promotional price–
2026-10-26$0.114, Greenference, Promotional price–
2026-10-27$0.114, Greenference, Promotional price–
2026-10-28$0.114, Greenference, Promotional price–
2026-10-29$0.114, Greenference, Promotional price–
2026-10-30$0.114, Greenference, Promotional price–
2026-10-31$0.114, Greenference, Promotional price–

Cheapest offerPromotional price

Offers

18 of 18 offers

Offers for Qwen3 30B A3B, one row per offer, sorted by blended price.
RankProvider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it.Input $/1MOutput $/1MBlended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.PrecisionHow finely the model's numbers are stored on the provider's servers. Lower precision (fp8, fp4) is cheaper to run and can slightly change answer quality; "unknown" means the provider doesn't say. ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut.ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown.SignalsOffer
1 Greenferencevia LLM Gateway 0.076 0.228 promo: Promotion announced by LLM Gateway · −20% vs its usual price · Discount shown by the seller, no end date announced, seen on Oct 31, 20260.114 – – Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
2 Cloudflarevia Eden AI 0.051 0.335 0.122 fp8 33k Unverified. No public page for this offer: listed, not designated cheapest
3 Cloudflare 0.051 0.335 0.122 fp8 –
4 Greenferencevia Eden AI 0.095 0.285 0.143 – 41k Unverified. No public page for this offer: listed, not designated cheapest
5 NanoGPT 0.10  0.30  0.15  – 41k
6 Nebiusvia LLM Gateway 0.10  0.30  0.15  – – worldwide Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Oct 30). Offers are ranked with the 5% included.
7 UCloud 0.113 0.451 0.197 – – Unverified. No public page for this offer: listed, not designated cheapest
8 DeepInfra 0.12  0.50  0.215 fp8 41k United States
9 InferenceNet 0.12  0.50  0.215 – 41k
10 DeepInfravia Eden AI 0.12  0.50  0.215 fp8 41k United States Unverified. No public page for this offer: listed, not designated cheapest
11 DeepInfravia Hugging Face 0.12  0.50  0.215 fp8 41k United States
12 DeepInfravia Kilo Gateway 0.12  0.50  0.215 fp8 41k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
13 FastRouter 0.12  0.50  0.215 – 41k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
14 Martian 0.12  0.50  0.215 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
15 Nous Portal 0.12  0.50  0.215 – 41k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
16 DeepInfravia OpenRouter 0.12  0.50  0.215 fp8 41k United States Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 30). Offers are ranked with this fee included.
17 Glama 0.13  0.52  0.228 – 131k Unverified. No public page for this offer: listed, not designated cheapest
18 DeepInfra 0.18  0.75  0.323 fp8 41k United States Priority tier: A different service tier, with its own speed and availability conditions.

No training on promptsPrompts may be used for trainingTraining terms not published

backend not named. The router bills this price itself without naming who serves the model.

1 flex or batch offer hidden (lower priority, variable latency).

Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.

Method

Monthly cost for your workload

Computed by the API for the three cheapest offers, per 30-day month.
  1. Cloudflare$8.09per month
  2. Greenference$7.98per month+$-0.11 vs the cheapest
  3. NanoGPT$10.50per month+$2.41 vs the cheapest

Host it yourself instead? See the break-even

Compare Qwen3 30B A3B with

Related models

More from Qwen

All Qwen models

Same index family

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=qwen/qwen3-30b-a3b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

Also works in Cursor and Codex: see the MCP page.