InferIndex
Language, English, EN
Account

ModelsQwenQwen3 235B A22B Instruct 2507

Qwen3 235B A22B Instruct 2507

qwen/qwen3-235b-a22b-2507262k 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.
$1.51
Offers
34
Providers
19

Cheapest right now

DeepInfra

via Requesty

fp8 · 262k

$0.078 blended / 1M tokens

No change7D
in
$0.071
out
$0.10
Cached input
–

Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

Qwen3 235B A22B Instruct 2507 costs from $0.078 per million tokens (at a 3:1 input:output mix): the cheapest of 10 comparable offers, at DeepInfra, checked on ; 34 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 (24)

  • $0.17 · TensorX via Eden AI · cannot be designated the cheapest
  • $0.205 · DeepInfra · another route of the same provider
  • $0.205 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.205 · DeepInfra via Hugging Face · another route of the same provider
  • $0.205 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $0.205 · Glama via Glama · cannot be designated the cheapest
  • $0.205 · Martian via Martian · cannot be designated the cheapest
  • $0.205 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.205 · DeepInfra via OpenRouter · another route of the same provider
  • $0.213 · Novita via LLM API · cannot be designated the cheapest
  • $0.30 · Nebius via Eden AI · cannot be designated the cheapest
  • $0.30 · Nebius via LLM API · cannot be designated the cheapest
  • $0.30 · Venice via Kilo Gateway · cannot be designated the cheapest
  • $0.30 · Cortecs via Cortecs · cannot be designated the cheapest
  • $0.30 · Venice via OpenRouter · another route of the same provider
  • $0.305 · Parasail via Kilo Gateway · cannot be designated the cheapest
  • $0.308 · DeepInfra · priority tier
  • $0.385 · Amazon Bedrock via Eden AI · cannot be designated the cheapest
  • $0.385 · Fireworks via LMRouter · cannot be designated the cheapest
  • $0.438 · Arkanecloud via Eden AI · cannot be designated the cheapest
  • $0.526 · Qiniu · cannot be designated the cheapest
  • $0.613 · GMICloud via Kilo Gateway · cannot be designated the cheapest
  • $1.26 · Scaleway via Eden AI · cannot be designated the cheapest
  • $1.51 · Greenpt via Eden AI · cannot be designated the cheapest

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

$0.153 blended / 1M tokens

in
$0.088
out
$0.35
Cached input
$0.018

Price drop observed: The blended price is 31% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026

Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

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$0.078, DeepInfra–
2026-10-03$0.078, DeepInfra–
2026-10-04$0.078, DeepInfra–
2026-10-05$0.078, DeepInfra–
2026-10-06$0.078, DeepInfra–
2026-10-07$0.078, DeepInfra–
2026-10-08$0.078, DeepInfra–
2026-10-09$0.078, DeepInfra–
2026-10-10$0.078, DeepInfra–
2026-10-11$0.078, DeepInfra–
2026-10-12$0.078, DeepInfra–
2026-10-13$0.078, DeepInfra–
2026-10-14$0.078, DeepInfra–
2026-10-15$0.078, DeepInfra–
2026-10-16$0.078, DeepInfra–
2026-10-17$0.078, DeepInfra–
2026-10-18$0.078, DeepInfra–
2026-10-19$0.078, DeepInfra–
2026-10-20$0.078, DeepInfra–
2026-10-21$0.078, DeepInfra–
2026-10-22$0.078, DeepInfra–
2026-10-23$0.078, DeepInfra–
2026-10-24$0.078, DeepInfra–
2026-10-25$0.078, DeepInfra–
2026-10-26$0.078, DeepInfra–
2026-10-27$0.078, DeepInfra–
2026-10-28$0.078, DeepInfra–
2026-10-29$0.078, DeepInfra–
2026-10-30$0.078, DeepInfra–
2026-10-31$0.078, DeepInfra–

Cheapest offer

Offers

The 25 cheapest of 34 offers

Offers for Qwen3 235B A22B Instruct 2507, 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 DeepInfravia Requesty 0.071 0.10  0.078 fp8 262k United States Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
2 NanoGPT 0.088 0.35  0.153 – 262k Price drop observed: The blended price is 31% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026
Go to offer at NanoGPT (opens in a new tab)
3 GMICloudvia OpenRouter 0.088 0.35  promo: Promotion announced by OpenRouter · −75% vs its usual price · Discount shown by the seller, no end date announced, seen on Oct 30, 20260.153 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)
4 TensorXvia Eden AI 0.072 0.464 0.17  fp8 131k 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
5 DeepInfra 0.09  0.55  0.205 fp8 262k United States
Go to offer at DeepInfra (opens in a new tab)
6 DeepInfravia Eden AI 0.09  0.55  0.205 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 0.09  0.55  0.205 fp8 262k United States
See pricing at Hugging Face (opens in a new tab)
8 DeepInfravia Kilo Gateway 0.09  0.55  0.205 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 Glama 0.09  0.55  0.205 – 262k Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
10 Martian 0.09  0.55  0.205 – – 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)
11 Nous Portal 0.09  0.55  0.205 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 9 price changes in 7 days. Over that period: input $0.088 – $0.09, output $0.35 – $0.55 per million tokens. An offer whose price changes this often is not selected as the cheapest.
See pricing at Nous Portal (opens in a new tab)
12 DeepInfravia OpenRouter 0.09  0.55  0.205 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 Novitavia LLM API 0.09  0.58  0.213 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
See pricing at LLM API (opens in a new tab)
14 Venice 0.15  0.75  0.30  fp8 128k
Go to offer at Venice (opens in a new tab)
15 Nebiusvia Eden AI 0.20  0.60  0.30  fp8 262k worldwide 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
16 Nebiusvia LLM API 0.20  0.60  0.30  fp8 – worldwideUnconfirmed. 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 Nscalevia Hugging Face 0.20  0.60  0.30  – 33k
See pricing at Hugging Face (opens in a new tab)
18 Venicevia Kilo Gateway 0.15  0.75  0.30  fp8 128k 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
19 Cortecs 0.20  0.60  0.30  – 262k worldwide Unverified. No public page for this offer: listed, not designated cheapest
: Cortecs (opens in a new tab). No public price page for this model
20 Nebiusvia Requesty 0.20  0.60  0.30  fp8 128k worldwide Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
21 Venicevia OpenRouter 0.15  0.75  0.30  fp8 128k 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)
22 Parasailvia Kilo Gateway 0.14  0.80  0.305 fp8 131k worldwide 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
23 Parasailvia OpenRouter 0.14  0.80  0.305 fp8 131k worldwide 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)
24 DeepInfra 0.135 0.825 0.308 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)
25 Amazon Bedrockvia Eden AI 0.22  0.88  0.385 – 262k 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

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.

  • DeepInfra

    $0.078

    Requesty

    in
    $0.071
    out
    $0.10 
    Precision
    fp8
    Context
    262k

    Prompts may be used for trainingUnited StatesFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

  • NanoGPT

    $0.153

    NanoGPT

    in
    $0.088
    out
    $0.35 
    Precision
    –
    Context
    262k

    No training on promptsPrice drop observed: The blended price is 31% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026

    Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

  • GMICloud

    promo: Promotion announced by OpenRouter · −75% vs its usual price · Discount shown by the seller, no end date announced, seen on Oct 30, 2026$0.153

    OpenRouter

    in
    $0.088
    out
    $0.35 
    Precision
    fp8
    Context
    262k

    Training terms not publishedFee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • TensorX

    $0.17

    Eden AI

    in
    $0.072
    out
    $0.464
    Precision
    fp8
    Context
    131k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.205

    direct

    in
    $0.09 
    out
    $0.55 
    Precision
    fp8
    Context
    262k

    No training on promptsUnited States

    Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

  • DeepInfra

    $0.205

    Eden AI

    in
    $0.09 
    out
    $0.55 
    Precision
    fp8
    Context
    262k

    Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • DeepInfra

    $0.205

    Hugging Face

    in
    $0.09 
    out
    $0.55 
    Precision
    fp8
    Context
    262k

    No training on promptsUnited States

    See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

  • DeepInfra

    $0.205

    Kilo Gateway

    in
    $0.09 
    out
    $0.55 
    Precision
    fp8
    Context
    262k

    Training terms not publishedUnited StatesUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Glama

    $0.205

    Glama

    in
    $0.09 
    out
    $0.55 
    Precision
    –
    Context
    262k

    No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    Seller's site: Glama (opens in a new tab)No public price page for this model

  • Martian

    $0.205

    Martian

    in
    $0.09 
    out
    $0.55 
    Precision
    –
    Context
    –

    Training terms not publishedworldwideUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Martian (opens in a new tab)via Martian

  • Nous Portal

    $0.205

    Nous Portal

    in
    $0.09 
    out
    $0.55 
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 9 price changes in 7 days. Over that period: input $0.088 – $0.09, output $0.35 – $0.55 per million tokens. An offer whose price changes this often is not selected as the cheapest.backend not named: The router bills this price itself without naming who serves the model.

    See pricing See pricing at Nous Portal (opens in a new tab)via Nous Portal

  • DeepInfra

    $0.205

    OpenRouter

    in
    $0.09 
    out
    $0.55 
    Precision
    fp8
    Context
    262k

    No training on promptsUnited StatesFee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • Novita

    $0.213

    LLM API

    in
    $0.09 
    out
    $0.58 
    Precision
    fp8
    Context
    –

    No training on promptsUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed oneUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • Venice

    $0.30

    direct

    in
    $0.15 
    out
    $0.75 
    Precision
    fp8
    Context
    128k

    No training on prompts

    Go to offer Go to offer at Venice (opens in a new tab)at Venice

  • Nebius

    $0.30

    Eden AI

    in
    $0.20 
    out
    $0.60 
    Precision
    fp8
    Context
    262k

    Prompts may be used for trainingworldwideUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model

  • Nebius

    $0.30

    LLM API

    in
    $0.20 
    out
    $0.60 
    Precision
    fp8
    Context
    –

    Training terms not publishedworldwideUnconfirmed. Last checked 18 October 2026: the last published value, not a confirmed oneUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

    See pricing See pricing at LLM API (opens in a new tab)via LLM API

  • Nscale

    $0.30

    Hugging Face

    in
    $0.20 
    out
    $0.60 
    Precision
    –
    Context
    33k

    Training terms not published

    See pricing See pricing at Hugging Face (opens in a new tab)via Hugging Face

  • Venice

    $0.30

    Kilo Gateway

    in
    $0.15 
    out
    $0.75 
    Precision
    fp8
    Context
    128k

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Cortecs

    $0.30

    Cortecs

    in
    $0.20 
    out
    $0.60 
    Precision
    –
    Context
    262k

    No training on promptsworldwideUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Cortecs (opens in a new tab)No public price page for this model

  • Nebius

    $0.30

    Requesty

    in
    $0.20 
    out
    $0.60 
    Precision
    fp8
    Context
    128k

    Prompts may be used for trainingworldwideFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 30). Offers are ranked with this fee included.

    Go to offer Go to offer at Requesty (opens in a new tab)via Requesty

  • Venice

    $0.30

    OpenRouter

    in
    $0.15 
    out
    $0.75 
    Precision
    fp8
    Context
    128k

    No training on promptsFee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • Parasail

    $0.305

    Kilo Gateway

    in
    $0.14 
    out
    $0.80 
    Precision
    fp8
    Context
    131k

    Training terms not publishedworldwideUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Kilo Gateway (opens in a new tab)No public price page for this model

  • Parasail

    $0.305

    OpenRouter

    in
    $0.14 
    out
    $0.80 
    Precision
    fp8
    Context
    131k

    No training on promptsworldwideFee 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 Go to offer at OpenRouter (opens in a new tab)via OpenRouter

  • DeepInfra

    $0.308

    direct

    in
    $0.135
    out
    $0.825
    Precision
    fp8
    Context
    262k

    No training on promptsUnited StatesPriority tier: A different service tier, with its own speed and availability conditions.

    Go to offer Go to offer at DeepInfra (opens in a new tab)at DeepInfra

  • Amazon Bedrock

    $0.385

    Eden AI

    in
    $0.22 
    out
    $0.88 
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest

    Seller's site: Eden AI (opens in a new tab)No public price page for this model
Show all 34 offers

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. NanoGPT$10.50per month
  2. GMICloud$10.50per month+$0.00 vs the cheapest
  3. Venice$20.25per month+$9.75 vs the cheapest

Host it yourself instead? See the break-even

Compare Qwen3 235B A22B Instruct 2507 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-2507
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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