InferIndex
Language, English, EN
Account

ModelsQwenQwen3 VL 30B A3B Instruct

Qwen3 VL 30B A3B Instruct

qwen/qwen3-vl-30b-a3b-instruct131k context 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.
$0.294
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.
$0.468
Offers
22
Providers
10

Cheapest right now

Featherless

directYou buy access straight from the company that runs the model on its servers. · 131k

$0.238 blended / 1M tokens

No change7D
in
$0.15
out
$0.50
Cached input
–
Go to offer Go to offer at Featherless (opens in a new tab)at Featherless

Qwen3 VL 30B A3B Instruct costs from $0.238 per million tokens (at a 3:1 input:output mix): the cheapest of 6 comparable offers, at Featherless, checked on ; 22 offers are listed.

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 (16)

  • $0.197 · Qiniu · cannot be designated the cheapest
  • $0.228 · Glama via Glama · cannot be designated the cheapest
  • $0.263 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.263 · DeepInfra via Hugging Face · another route of the same provider
  • $0.263 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.263 · Martian via Martian · cannot be designated the cheapest
  • $0.263 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.263 · DeepInfra via LLM Gateway · another route of the same provider
  • $0.263 · DeepInfra via OpenRouter · another route of the same provider
  • $0.325 · Novita via Hugging Face · another route of the same provider
  • $0.325 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.325 · Novita via LLM API · cannot be designated the cheapest
  • $0.325 · Novita via LLM Gateway · another route of the same provider
  • $0.325 · Novita via OpenRouter · another route of the same provider
  • $0.394 · DeepInfra · priority tier
  • $0.468 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest

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

NEAR AI

directYou buy access straight from the company that runs the model on its servers. · fp8 · 16k

$0.25 blended / 1M tokens

in
$0.15
out
$0.55
Cached input
$0.03
See pricing See pricing at NEAR AI (opens in a new tab)at NEAR AI

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$0.189, Alibaba–
2026-10-03$0.189, Alibaba–
2026-10-04$0.189, Alibaba–
2026-10-05$0.189, Alibaba–
2026-10-06$0.189, Alibaba–
2026-10-07$0.189, Alibaba–
2026-10-08$0.189, Alibaba–
2026-10-09$0.189, Alibaba–
2026-10-10$0.189, Alibaba–
2026-10-11$0.189, Alibaba–
2026-10-12$0.196, Qiniu–
2026-10-13$0.196, Qiniu–
2026-10-14$0.196, Qiniu–
2026-10-15$0.196, Qiniu–
2026-10-16$0.196, Qiniu–
2026-10-17$0.196, Qiniu–
2026-10-18$0.196, Qiniu–
2026-10-19$0.238, Featherless–
2026-10-20$0.238, Featherless–
2026-10-21$0.238, Featherless–
2026-10-22$0.238, Featherless–
2026-10-23$0.238, Featherless–
2026-10-24$0.238, Featherless–
2026-10-25$0.238, Featherless–
2026-10-26$0.238, Featherless–
2026-10-27$0.238, Featherless–
2026-10-28$0.238, Featherless–
2026-10-29$0.238, Featherless–
2026-10-30$0.238, Featherless–
2026-10-31$0.238, Featherless–

Cheapest offer

Offers

22 of 22 offers

Offers for Qwen3 VL 30B A3B Instruct, 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 Qiniu 0.113 0.451 0.197 – 128k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Qiniu (opens in a new tab)
2 Glama 0.13  0.52  0.228 – 131k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
3 Featherless 0.15  0.50  0.238 – 131k
Go to offer at Featherless (opens in a new tab)
4 NEAR AI 0.15  0.55  0.25  fp8 16k
See pricing at NEAR AI (opens in a new tab)
5 DeepInfra 0.15  0.60  0.263 fp8 262k United States
Go to offer at DeepInfra (opens in a new tab)
6 DeepInfravia Eden AI 0.15  0.60  0.263 fp8 262k United States Unverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab). No public price page for this model
7 DeepInfravia Hugging Face 0.15  0.60  0.263 fp8 262k United States
See pricing at Hugging Face (opens in a new tab)
8 DeepInfravia Kilo Gateway 0.15  0.60  0.263 fp8 262k United States Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
9 Martian 0.15  0.60  0.263 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Martian (opens in a new tab)
10 Nous Portal 0.15  0.60  0.263 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
See pricing at Nous Portal (opens in a new tab)
11 DeepInfravia LLM Gateway 0.15  0.60  0.263 fp8 – United States 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.
Go to offer at LLM Gateway (opens in a new tab)
12 DeepInfravia OpenRouter 0.15  0.60  0.263 fp8 262k 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.
Go to offer at OpenRouter (opens in a new tab)
13 Novita 0.20  0.70  0.325 bf16 131k
See pricing at Novita (opens in a new tab)
14 Novitavia Hugging Face 0.20  0.70  0.325 bf16 131k
See pricing at Hugging Face (opens in a new tab)
15 Novitavia Kilo Gateway 0.20  0.70  0.325 bf16 131k Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
16 Novitavia LLM API 0.20  0.70  0.325 bf16 – Unconfirmed. Last checked 18 October 2026: the last published value, not a confirmed one Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
See pricing at LLM API (opens in a new tab)
17 RedPill 0.20  0.70  0.325 – 128k
Go to offer at RedPill (opens in a new tab)
18 Novitavia LLM Gateway 0.20  0.70  0.325 bf16 – 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.
Go to offer at LLM Gateway (opens in a new tab)
19 Novitavia OpenRouter 0.20  0.70  0.325 bf16 131k 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.
Go to offer at OpenRouter (opens in a new tab)
20 DeepInfra 0.225 0.90  0.394 fp8 262k United States Priority tier: A different service tier, with its own speed and availability conditions.
Go to offer at DeepInfra (opens in a new tab)
21 SiliconFlowvia Kilo Gateway 0.29  1.00  0.468 fp8 262k Unverified. No public page for this offer: listed, not designated cheapest
: Kilo Gateway (opens in a new tab). No public price page for this model
22 SiliconFlowvia OpenRouter 0.29  1.00  0.468 fp8 262k 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.
Go to offer at OpenRouter (opens in a new tab)

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. Featherless$16.50per month
  2. NEAR AI$17.25per month+$0.75 vs the cheapest
  3. DeepInfra$18.00per month+$1.50 vs the cheapest

Host it yourself instead? See the break-even

Compare Qwen3 VL 30B A3B Instruct 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-vl-30b-a3b-instruct
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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