InferIndex
Language, English, EN
Account

ModelsTencentHy4 preview

Hy4 preview

tencent/hy4-preview1M 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.
$1.25
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.
$1.56
Offers
36
Providers
20

Cheapest right now

AtlasCloud

directYou buy access straight from the company that runs the model on its servers. · fp8 · 1M

$1.25 blended / 1M tokens

No change7D
in
$0.834
out
$2.50
Cached input
$0.042
See pricing See pricing at AtlasCloud (opens in a new tab)at AtlasCloud

Public leaderboards

  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #21 of 152Best rank in the source's rank spread, 21st to 31st, given the confidence intervals of all ranked models. 23rd by score. 1,631 1,621 to 1,641Arena Score · 4,765 votes
  • Agent Arena aggregateThe Agent Arena aggregate score: a score of another kind (not an Arena score), on a scale of its own; it cannot be compared with the other series. #17 of 57Best rank in the source's rank spread, 17th to 32nd, given the confidence intervals of all ranked models. 26th by score. 0.012 0.005 to 0.019IPS score · 10,555,916 observations

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

Hy4 preview costs from $1.25 per million tokens (at a 3:1 input:output mix): the lowest current price, at 8 providers, checked on ; 36 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 (22)

  • $0.625 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $1.25 · io.net · cannot be designated the cheapest
  • $1.25 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · Cohere via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $1.25 · DeepInfra via Hugging Face · not selected as cheapest: its price changes often
  • $1.25 · DeepInfra via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · GMICloud via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · Novita via Hugging Face · another route of the same provider
  • $1.25 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · SiliconFlow via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · Tencent via Eden AI · cannot be designated the cheapest
  • $1.25 · Tencent via Kilo Gateway · cannot be designated the cheapest
  • $1.25 · Glama via Glama · cannot be designated the cheapest
  • $1.25 · Martian via Martian · cannot be designated the cheapest
  • $1.25 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $1.25 · Tencent via Requesty · another route of the same provider
  • $1.25 · AtlasCloud via OpenRouter · another route of the same provider
  • $1.25 · DeepInfra via OpenRouter · not selected as cheapest: its price changes often
  • $1.25 · Novita via OpenRouter · another route of the same provider
  • $1.25 · Tencent via OpenRouter · not selected as cheapest: its price changes often
  • $1.35 · ShengSuanYun via ShengSuanYun · 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. · fp8 · 1M

$1.25 blended / 1M tokens

in
$0.834
out
$2.50
Cached input
$0.042
See pricing See pricing at Novita (opens in a new tab)at Novita

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$0.625, Nous Portal–
2026-10-03$0.625, Nous Portal–
2026-10-04$0.625, Nous Portal–
2026-10-05$0.625, Nous Portal–
2026-10-06$0.625, Nous Portal–
2026-10-07$0.625, Nous Portal–
2026-10-08$0.625, Nous Portal–
2026-10-09$0.625, Nous Portal–
2026-10-10$0.625, Nous Portal–
2026-10-11$0.625, Nous Portal–
2026-10-12$0.625, Nous Portal–
2026-10-13$0.625, Nous Portal–
2026-10-14$0.625, Nous Portal–
2026-10-15$0.625, Nous Portal–
2026-10-16$0.625, Nous Portal–
2026-10-17$0.625, Nous Portal–
2026-10-18$0.625, Nous Portal–
2026-10-19$0.625, Nous Portal–
2026-10-20$0.625, Nous Portal–
2026-10-21$0.625, Nous Portal–
2026-10-22$0.625, Nous Portal–
2026-10-23$0.625, Nous Portal–
2026-10-24$1.25, DeepInfra–
2026-10-25$1.19, DeepInfra, Promotional price–
2026-10-26$1.19, DeepInfra, Promotional price–
2026-10-27$1.19, DeepInfra, Promotional price–
2026-10-28$1.25, AtlasCloud–
2026-10-29$1.25, AtlasCloud–
2026-10-30$1.25, AtlasCloud–
2026-10-31$1.25, AtlasCloud–

Cheapest offerPromotional price

Offers

36 of 36 offers

Offers for Hy4 preview, 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 Nous Portal 0.417 1.25 0.625 – 1M 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)
2 AtlasCloud 0.834 2.50 1.25  fp8 1M
See pricing at AtlasCloud (opens in a new tab)
3 NanoGPT 0.834 2.50 1.25  – 1M Price changes often: 19 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.
Go to offer at NanoGPT (opens in a new tab)
4 DeepInfra 0.834 2.50 1.25  fp4 1M United States Price changes often: 14 price changes in 7 days. Over that period: input $0.792 – $0.834, output $2.38 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.
Go to offer at DeepInfra (opens in a new tab)
5 io.net 0.834 2.50 1.25  fp8 262k Unverified. No public page for this offer: listed, not designated cheapest
: io.net (opens in a new tab). No public price page for this model
6 Novita 0.834 2.50 1.25  fp8 1M
See pricing at Novita (opens in a new tab)
7 AtlasCloudvia Kilo Gateway 0.834 2.50 1.25  fp8 1M 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
8 Coherevia Kilo Gateway 0.834 2.50 1.25  – 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
9 DeepInfravia Eden AI 0.834 2.50 1.25  fp4 1M 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
10 DeepInfravia Hugging Face 0.834 2.50 1.25  fp4 1M United States Price changes often: 14 price changes in 7 days. Over that period: input $0.792 – $0.834, output $2.38 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.
See pricing at Hugging Face (opens in a new tab)
11 DeepInfravia Kilo Gateway 0.834 2.50 1.25  fp4 1M 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
12 GMICloudvia Kilo Gateway 0.834 2.50 1.25  bf16 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
13 Novitavia Hugging Face 0.834 2.50 1.25  fp8 1M
See pricing at Hugging Face (opens in a new tab)
14 Novitavia Kilo Gateway 0.834 2.50 1.25  fp8 1M 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
15 SiliconFlowvia Kilo Gateway 0.834 2.50 1.25  fp8 1M 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 Tencentvia Eden AI 0.834 2.50 1.25  fp8 1M 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
17 Tencentvia Kilo Gateway 0.834 2.50 1.25  fp8 1M Unverified. No public page for this offer: listed, not designated cheapestPrice changes often: 14 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.
: Kilo Gateway (opens in a new tab). No public price page for this model
18 Glama 0.834 2.50 1.25  – 1M Unverified. No public page for this offer: listed, not designated cheapest
: Glama (opens in a new tab). No public price page for this model
19 Martian 0.834 2.50 1.25  – – 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)
20 OrcaRouter 0.834 2.50 1.25  – 1M Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest
Go to offer at OrcaRouter (opens in a new tab)
21 Vercel AI Gateway 0.834 2.50 1.25  – –
Go to offer at Vercel AI Gateway (opens in a new tab)
22 ZenMux 0.834 2.50 1.25  – 1M
Go to offer at ZenMux (opens in a new tab)
23 Tencentvia LLM Gateway 0.834 2.50 1.25  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.
Go to offer at LLM Gateway (opens in a new tab)
24 Tencentvia Requesty 0.834 2.50 1.25  fp8 1M Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.
Go to offer at Requesty (opens in a new tab)
25 AtlasCloudvia OpenRouter 0.834 2.50 1.25  fp8 1M 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.
Go to offer at OpenRouter (opens in a new tab)
26 Coherevia OpenRouter 0.834 2.50 1.25  – 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.
Go to offer at OpenRouter (opens in a new tab)
27 DeepInfravia OpenRouter 0.834 2.50 1.25  fp4 1M United States Price changes often: 14 price changes in 7 days. Over that period: input $0.792 – $0.834, output $2.38 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.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.
Go to offer at OpenRouter (opens in a new tab)
28 GMICloudvia OpenRouter 0.834 2.50 1.25  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.
Go to offer at OpenRouter (opens in a new tab)
29 Novitavia OpenRouter 0.834 2.50 1.25  fp8 1M 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.
Go to offer at OpenRouter (opens in a new tab)
30 SiliconFlowvia OpenRouter 0.834 2.50 1.25  fp8 1M 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.
Go to offer at OpenRouter (opens in a new tab)
31 Tencentvia OpenRouter 0.834 2.50 1.25  fp8 1M Price changes often: 16 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.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.tiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.
Go to offer at OpenRouter (opens in a new tab)
32 Neosantara 0.85  2.55 1.28  – 1M Singapore, Indonesia, United States
See pricing at Neosantara (opens in a new tab)
33 Qiniu 0.902 2.71 1.35  – 1M
See pricing at Qiniu (opens in a new tab)
34 PPIO 0.902 2.71 1.35  – 1M
See pricing at PPIO (opens in a new tab)
35 ShengSuanYun 0.902 2.71 1.35  – 1M Unverified. No public page for this offer: listed, not designated cheapest
: ShengSuanYun (opens in a new tab). No public price page for this model
36 Venice 1.04  3.13 1.56  – 1M
Go to offer at Venice (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.

  • Nous Portal

    $0.625

    Nous Portal

    in
    $0.417
    out
    $1.25
    Precision
    –
    Context
    1M

    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.

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

  • AtlasCloud

    $1.25

    direct

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    Training terms not published

    See pricing See pricing at AtlasCloud (opens in a new tab)at AtlasCloud

  • NanoGPT

    $1.25

    NanoGPT

    in
    $0.834
    out
    $2.50
    Precision
    –
    Context
    1M

    No training on promptsPrice changes often: 19 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.

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

  • DeepInfra

    $1.25

    direct

    in
    $0.834
    out
    $2.50
    Precision
    fp4
    Context
    1M

    No training on promptsUnited StatesPrice changes often: 14 price changes in 7 days. Over that period: input $0.792 – $0.834, output $2.38 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.

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

  • io.net

    $1.25

    direct

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    262k

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

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

  • Novita

    $1.25

    direct

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    No training on prompts

    See pricing See pricing at Novita (opens in a new tab)at Novita

  • AtlasCloud

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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

  • Cohere

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    –
    Context
    262k

    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

  • DeepInfra

    $1.25

    Eden AI

    in
    $0.834
    out
    $2.50
    Precision
    fp4
    Context
    1M

    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

    $1.25

    Hugging Face

    in
    $0.834
    out
    $2.50
    Precision
    fp4
    Context
    1M

    No training on promptsUnited StatesPrice changes often: 14 price changes in 7 days. Over that period: input $0.792 – $0.834, output $2.38 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.

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

  • DeepInfra

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    fp4
    Context
    1M

    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

  • GMICloud

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    bf16
    Context
    262k

    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

  • Novita

    $1.25

    Hugging Face

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    No training on prompts

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

  • Novita

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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

  • SiliconFlow

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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

  • Tencent

    $1.25

    Eden AI

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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

  • Tencent

    $1.25

    Kilo Gateway

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    Training terms not publishedUnverified. No public page for this offer: listed, not designated cheapestPrice changes often: 14 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.

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

  • Glama

    $1.25

    Glama

    in
    $0.834
    out
    $2.50
    Precision
    –
    Context
    1M

    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

    $1.25

    Martian

    in
    $0.834
    out
    $2.50
    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

  • OrcaRouter

    $1.25

    OrcaRouter

    in
    $0.834
    out
    $2.50
    Precision
    –
    Context
    1M

    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.

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

  • Vercel AI Gateway

    $1.25

    Vercel AI Gateway

    in
    $0.834
    out
    $2.50
    Precision
    –
    Context
    –

    No training on prompts

    Go to offer Go to offer at Vercel AI Gateway (opens in a new tab)via Vercel AI Gateway

  • ZenMux

    $1.25

    ZenMux

    in
    $0.834
    out
    $2.50
    Precision
    –
    Context
    1M

    Prompts may be used for training

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

  • Tencent

    $1.25

    LLM Gateway

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    –

    Training terms not publishedFee 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.

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

  • Tencent

    $1.25

    Requesty

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    Prompts may be used for trainingFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Oct 31). Offers are ranked with this fee included.

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

  • AtlasCloud

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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.

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

  • Cohere

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    –
    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.

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

  • DeepInfra

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    fp4
    Context
    1M

    No training on promptsUnited StatesPrice changes often: 14 price changes in 7 days. Over that period: input $0.792 – $0.834, output $2.38 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.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.

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

  • GMICloud

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    bf16
    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.

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

  • Novita

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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.

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

  • SiliconFlow

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    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.

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

  • Tencent

    $1.25

    OpenRouter

    in
    $0.834
    out
    $2.50
    Precision
    fp8
    Context
    1M

    Training terms not publishedPrice changes often: 16 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest.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.tiered pricing: The provider publishes several rates for this model, depending on how long your prompt is. Only one of them is shown here.

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

  • Neosantara

    $1.28

    Neosantara

    in
    $0.85 
    out
    $2.55
    Precision
    –
    Context
    1M

    Training terms not publishedSingapore, Indonesia, United States

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

  • Qiniu

    $1.35

    direct

    in
    $0.902
    out
    $2.71
    Precision
    –
    Context
    1M

    Training terms not published

    See pricing See pricing at Qiniu (opens in a new tab)at Qiniu

  • PPIO

    $1.35

    direct

    in
    $0.902
    out
    $2.71
    Precision
    –
    Context
    1M

    Prompts may be used for training

    See pricing See pricing at PPIO (opens in a new tab)at PPIO

  • ShengSuanYun

    $1.35

    ShengSuanYun

    in
    $0.902
    out
    $2.71
    Precision
    –
    Context
    1M

    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

  • Venice

    $1.56

    direct

    in
    $1.04 
    out
    $3.13
    Precision
    –
    Context
    1M

    No training on prompts

    Go to offer Go to offer at Venice (opens in a new tab)at Venice
Show the 25 cheapest only

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. AtlasCloud$87.56per month
  2. NanoGPT$87.56per month+$0.00 vs the cheapest
  3. DeepInfra$87.56per month+$0.00 vs the cheapest

Host it yourself instead? See the break-even

Compare Hy4 preview with

Related models

More from Tencent

All Tencent 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=tencent/hy4-preview
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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