InferIndex
Language, English, EN
Account

ModelsQwenQwen3 235B A22B

Qwen3 235B A22B

qwen/qwen3-235b-a22b262k 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.
$0.30
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.
$0.796
Offers
9
Providers
7

Cheapest right now

NanoGPT

The provider's published policy: prompts are not used for training.

262k

$0.153 blended / 1M tokens

No change7D
in
$0.088
out
$0.35
Cached input
$0.018

Price drop observed: The blended price is 56% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026

Previous price $0.30 / $0.50

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). #187 of 419Best rank in the source's rank spread, 187th to 203rd, given the confidence intervals of all ranked models. 195th by score. 1,375 1,370 to 1,380Arena Score · 25,950 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 235B A22B: the lowest current price is $0.153 per million tokens (at a 3:1 input:output mix), a promotional price at NanoGPT, checked on ; the median of the 5 comparable offers is $0.30.

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 (4)

  • $0.27 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.35 · Novita via LLM API · cannot be designated the cheapest
  • $0.385 · Fireworks via LMRouter · cannot be designated the cheapest
  • $0.796 · Martian via Martian · cannot be designated the cheapest

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$0.27, DeepInfra–
2026-10-03$0.27, DeepInfra–
2026-10-04$0.27, DeepInfra–
2026-10-05$0.27, DeepInfra–
2026-10-06$0.27, DeepInfra–
2026-10-07$0.27, DeepInfra–
2026-10-08$0.27, DeepInfra–
2026-10-09$0.27, DeepInfra–
2026-10-10$0.27, DeepInfra–
2026-10-11$0.27, DeepInfra–
2026-10-12$0.27, DeepInfra–
2026-10-13$0.27, DeepInfra–
2026-10-14$0.27, DeepInfra–
2026-10-15$0.27, DeepInfra–
2026-10-16$0.27, DeepInfra–
2026-10-17$0.27, DeepInfra–
2026-10-18$0.27, DeepInfra–
2026-10-19$0.153, NanoGPT–
2026-10-20$0.153, NanoGPT–
2026-10-21$0.153, NanoGPT–
2026-10-22$0.153, NanoGPT–
2026-10-23$0.153, NanoGPT–
2026-10-24$0.153, NanoGPT–
2026-10-25$0.153, NanoGPT–
2026-10-26$0.153, NanoGPT–
2026-10-27$0.153, NanoGPT–
2026-10-28$0.153, NanoGPT–
2026-10-29$0.153, NanoGPT–
2026-10-30$0.153, NanoGPT–
2026-10-31$0.153, NanoGPT–

Cheapest offer

Offers

9 of 9 offers

Offers for Qwen3 235B A22B, 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 NanoGPT 0.088 0.35 0.153 – 262k Price drop observed: The blended price is 56% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026
2 DeepInfravia Eden AI 0.18  0.54 0.27  – 41k United States Unverified. No public page for this offer: listed, not designated cheapest
3 Nscalevia Hugging Face 0.20  0.60 0.30  – 32k
4 DeepInfravia Requesty 0.20  0.60 0.30  – 41k United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
5 Novitavia LLM API 0.20  0.80 0.35  fp8 – 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
6 Novitavia Requesty 0.20  0.80 0.35  fp8 128k Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
7 Fireworksvia LMRouter 0.22  0.88 0.385 – 128k United States Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
8 Featherless 0.455 1.82 0.796 – 33k
9 Martian 0.455 1.82 0.796 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest

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.

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. NanoGPT$10.50per month
  2. Nscale$21.00per month+$10.50 vs the cheapest
  3. DeepInfra$21.00per month+$10.50 vs the cheapest

Host it yourself instead? See the break-even

Compare Qwen3 235B A22B 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/qwen3-235b-a22b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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