InferIndex
Language, English, EN
Account

ModelsQwenQwen3.5-122B-A10B

Qwen3.5-122B-A10B

qwen/qwen3.5-122b-a10b 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.
$0.818
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.
$2.01
Offers
28
Providers
15

Cheapest right now

$0.316 blended / 1M tokens

No change7D
in
$0.115
out
$0.917
Cached input
–

prompt up to 128K tokens: up to 128K: $0.115 / $0.917; up to 256K: $0.287 / $2.29 (Input / Output, per million tokens)

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). #122 of 419Best rank in the source's rank spread, 122nd to 155th, given the confidence intervals of all ranked models. 139th by score. 1,416 1,412 to 1,421Arena Score · 29,712 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #112 of 152Best rank in the source's rank spread, 112th to 122nd, given the confidence intervals of all ranked models. 116th by score. 1,360 1,353 to 1,368Arena Score · 8,210 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

Qwen3.5-122B-A10B costs from $0.316 per million tokens (at a 3:1 input:output mix): the cheapest of 9 comparable offers, at Alibaba, checked on ; 28 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.Official list price

Offers not counted in cheapest, median or most expensive (19)

  • $0.316 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.331 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.715 · Alibaba via Eden AI · cannot be designated the cheapest
  • $0.715 · Alibaba via Kilo Gateway · cannot be designated the cheapest
  • $0.715 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
  • $0.715 · Glama via Glama · cannot be designated the cheapest
  • $0.715 · Martian via Martian · cannot be designated the cheapest
  • $0.715 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.818 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.825 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $0.825 · AtlasCloud via OpenRouter · another route of the same provider
  • $1.10 · Alibaba via Alibaba · another route of the same provider
  • $1.10 · Novita via Hugging Face · another route of the same provider
  • $1.10 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $1.10 · Alibaba via LLM Gateway · another route of the same provider
  • $1.10 · Novita via LLM Gateway · another route of the same provider
  • $1.10 · Novita via OpenRouter · another route of the same provider
  • $1.23 · Infomaniak via Eden AI · cannot be designated the cheapest
  • $1.25 · TensorX 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.

Novita

directYou buy access straight from the company that runs the model on its servers. · bf16 · 262k

$1.10 blended / 1M tokens

in
$0.40
out
$3.20
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$0.316, Alibaba$0.316
2026-10-03$0.316, Alibaba$0.316
2026-10-04$0.316, Alibaba$0.316
2026-10-05$0.316, Alibaba$0.316
2026-10-06$0.316, Alibaba$0.316
2026-10-07$0.316, Alibaba$0.316
2026-10-08$0.316, Alibaba$0.316
2026-10-09$0.316, Alibaba$0.316
2026-10-10$0.316, Alibaba$0.316
2026-10-11$0.316, Alibaba$0.316
2026-10-12$0.316, Alibaba$0.316
2026-10-13$0.316, OrcaRouter$0.316
2026-10-14$0.316, Alibaba$0.316
2026-10-15$0.316, Alibaba$0.316
2026-10-16$0.316, Alibaba$0.316
2026-10-17$0.316, Alibaba$0.316
2026-10-18$0.316, Alibaba$0.316
2026-10-19$0.316, Alibaba$0.316
2026-10-20$0.316, Alibaba$0.316
2026-10-21$0.316, Alibaba$0.316
2026-10-22$0.316, Alibaba$0.316
2026-10-23$0.316, Alibaba$0.316
2026-10-24$0.316, Alibaba$0.316
2026-10-25$0.316, Alibaba$0.316
2026-10-26$0.316, Alibaba$0.316
2026-10-27$0.316, Alibaba$0.316
2026-10-28$0.316, Alibaba$0.316
2026-10-29$0.316, Alibaba$0.316
2026-10-30$0.316, Alibaba$0.316
2026-10-31$0.316, Alibaba$0.316

Cheapest offerOfficial list price

Offers

The 25 cheapest of 28 offers

Offers for Qwen3.5-122B-A10B, 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 Alibaba 0.115 0.917 0.316 fp8 – prompt up to 128K tokens: up to 128K: $0.115 / $0.917; up to 256K: $0.287 / $2.29 (Input / Output, per million tokens)
2 OrcaRouter 0.115 0.917 0.316 – 33k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
3 ShengSuanYun 0.12  0.962 0.331 – 256k Unverified. No public page for this offer: listed, not designated cheapest
4 Alibabavia Eden AI 0.26  2.08  0.715 fp8 262k Unverified. No public page for this offer: listed, not designated cheapest
5 Alibabavia Kilo Gateway 0.26  2.08  0.715 fp8 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
6 SiliconFlowvia Kilo Gateway 0.26  2.08  0.715 fp8 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
7 Glama 0.26  2.08  0.715 – 262k Unverified. No public page for this offer: listed, not designated cheapest
8 Martian 0.26  2.08  0.715 – – worldwide Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
9 NanoGPT 0.26  2.08  0.715 – 262k Thinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer existsPrice drop observed: The blended price is 41% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026
10 Nous Portal 0.26  2.08  0.715 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
11 Alibabavia OpenRouter 0.26  2.08  0.715 – 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
12 SiliconFlowvia OpenRouter 0.26  2.08  0.715 fp8 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
13 DeepInfravia Eden AI 0.29  2.40  0.818 fp4 262k United States Unverified. No public page for this offer: listed, not designated cheapest
14 DeepInfravia Hugging Face 0.29  2.40  0.818 fp4 262k United States
15 AtlasCloud 0.30  2.40  0.825 fp8 262k
16 AtlasCloudvia Kilo Gateway 0.30  2.40  0.825 fp8 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
17 AtlasCloudvia OpenRouter 0.30  2.40  0.825 fp8 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.
18 PPIO 0.301 2.41  0.827 – 262k tiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
19 Alibaba 0.40  3.20  1.10  fp8 –
20 Novita 0.40  3.20  1.10  bf16 262k
21 Novitavia Hugging Face 0.40  3.20  1.10  bf16 262k
22 Novitavia Kilo Gateway 0.40  3.20  1.10  bf16 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
23 Alibabavia LLM Gateway 0.40  3.20  1.10  fp8 – 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 31). Offers are ranked with the 5% included.
24 Novitavia LLM Gateway 0.40  3.20  1.10  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 31). Offers are ranked with the 5% included.
25 Novitavia OpenRouter 0.40  3.20  1.10  bf16 262k Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.

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.

  • Alibaba

    $0.316

    Alibaba

    in
    $0.115
    out
    $0.917
    Precision
    fp8
    Context
    –

    Training terms not publishedprompt up to 128K tokens: up to 128K: $0.115 / $0.917; up to 256K: $0.287 / $2.29 (Input / Output, per million tokens)

  • OrcaRouter

    in
    $0.115
    out
    $0.917
    Precision
    –
    Context
    33k

    Training terms not publishedUnverified. 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.

  • ShengSuanYun

    in
    $0.12 
    out
    $0.962
    Precision
    –
    Context
    256k

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

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

    $0.715

    Eden AI

    in
    $0.26 
    out
    $2.08 
    Precision
    fp8
    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
  • Alibaba

    $0.715

    Kilo Gateway

    in
    $0.26 
    out
    $2.08 
    Precision
    fp8
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • Kilo Gateway

    in
    $0.26 
    out
    $2.08 
    Precision
    fp8
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • Glama

    $0.715

    Glama

    in
    $0.26 
    out
    $2.08 
    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

    $0.715

    Martian

    in
    $0.26 
    out
    $2.08 
    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.

  • NanoGPT

    $0.715

    NanoGPT

    in
    $0.26 
    out
    $2.08 
    Precision
    –
    Context
    262k

    No training on promptsThinking: Thinking: a mode of the model, not its standard offer. Never designated cheapest while a standard offer existsPrice drop observed: The blended price is 41% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026

  • Nous Portal

    in
    $0.26 
    out
    $2.08 
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnverified. 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.

  • Alibaba

    $0.715

    OpenRouter

    in
    $0.26 
    out
    $2.08 
    Precision
    –
    Context
    262k

    No training on promptsFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.

  • OpenRouter

    in
    $0.26 
    out
    $2.08 
    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 31). Offers are ranked with this fee included.

  • DeepInfra

    $0.818

    Eden AI

    in
    $0.29 
    out
    $2.40 
    Precision
    fp4
    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

    $0.818

    Hugging Face

    in
    $0.29 
    out
    $2.40 
    Precision
    fp4
    Context
    262k

    No training on promptsUnited States

  • direct

    in
    $0.30 
    out
    $2.40 
    Precision
    fp8
    Context
    262k

    Training terms not published

  • Kilo Gateway

    in
    $0.30 
    out
    $2.40 
    Precision
    fp8
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • OpenRouter

    in
    $0.30 
    out
    $2.40 
    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 31). Offers are ranked with this fee included.

  • PPIO

    $0.827

    direct

    in
    $0.301
    out
    $2.41 
    Precision
    –
    Context
    262k

    Prompts may be used for trainingtiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.

  • Alibaba

    $1.10

    Alibaba

    in
    $0.40 
    out
    $3.20 
    Precision
    fp8
    Context
    –

    Training terms not published

  • Novita

    $1.10

    direct

    in
    $0.40 
    out
    $3.20 
    Precision
    bf16
    Context
    262k

    No training on prompts

  • Novita

    $1.10

    Hugging Face

    in
    $0.40 
    out
    $3.20 
    Precision
    bf16
    Context
    262k

    No training on prompts

  • Novita

    $1.10

    Kilo Gateway

    in
    $0.40 
    out
    $3.20 
    Precision
    bf16
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest

  • Alibaba

    $1.10

    LLM Gateway

    in
    $0.40 
    out
    $3.20 
    Precision
    fp8
    Context
    –

    No training on promptsFee 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 31). Offers are ranked with the 5% included.

  • Novita

    $1.10

    LLM Gateway

    in
    $0.40 
    out
    $3.20 
    Precision
    bf16
    Context
    –

    No training on promptsFee 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 31). Offers are ranked with the 5% included.

  • Novita

    $1.10

    OpenRouter

    in
    $0.40 
    out
    $3.20 
    Precision
    bf16
    Context
    262k

    No training on promptsFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Oct 31). Offers are ranked with this fee included.

Show all 28 offers

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. Alibaba$20.66per month
  2. PPIO$21.64per month+$0.98 vs the cheapest
  3. NanoGPT$46.80per month+$26.14 vs the cheapest

Host it yourself instead? See the break-even

Compare Qwen3.5-122B-A10B 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/qwen3.5-122b-a10b
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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