InferIndex
Language, English, EN
Account

ModelsTencentHy4

Hy4

tencent/hy41M 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.
$0.625
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.
$1.25
Offers
12
Providers
10

Cheapest right now

AtlasCloud

directYou buy access straight from the company that runs the model on its servers. · fp4 · 1M

$0.625 blended / 1M tokens

Not enough history yet · tracking since Nov 4, 2026
in
$0.417
out
$1.25
Cached input
$0.021

Price drop observed: The blended price is 29% lower than before this drop; possibly temporary. · Price drop observed since Nov 6, 2026

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

Previous price $0.584 / $1.75

Public leaderboards

  • 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. #10 of 58Best rank in the source's rank spread, 10th to 17th, given the confidence intervals of all ranked models. 13th by score. 0.054 0.037 to 0.071IPS score · 1,473,452 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 4 Nov 2026

Hy4: the lowest current price is $0.625 per million tokens (at a 3:1 input:output mix), a promotional price at AtlasCloud, checked on ; the median of the 7 comparable offers is $0.625.

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 (5)

  • $0.25 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.625 · Glama via Glama · cannot be designated the cheapest
  • $0.675 · ShengSuanYun via ShengSuanYun · 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

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. · 1M

$0.625 blended / 1M tokens

in
$0.417
out
$1.25
Cached input
$0.021

Promotion announced by Novita: −50% vs its usual price · end date not published

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, 7 days
DayCheapest offerOfficial list price
2026-11-04$0.625, Vercel AI Gateway–
2026-11-06$0.625, AtlasCloud–

Cheapest offer

Offers

12 of 12 offers

Offers for Hy4, 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 0.167 0.50 0.25  – 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 0.417 1.25 0.625 fp4 1M Price drop observed: The blended price is 29% lower than before this drop; possibly temporary. · Price drop observed since Nov 6, 2026
See pricing at AtlasCloud (opens in a new tab)
3 Novita 0.417 1.25 promo: Promotion announced by Novita · −50% vs its usual price · end date not published0.625 – 1M
See pricing at Novita (opens in a new tab)
4 Glama 0.417 1.25 0.625 – 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
5 Vercel AI Gateway 0.417 1.25 0.625 – –
Go to offer at Vercel AI Gateway (opens in a new tab)
6 Tencentvia OpenRouter 0.417 1.25 promo: Promotion announced by OpenRouter · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 6, 20260.625 fp4 1M Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 5). Offers are ranked with this fee included.
Go to offer at OpenRouter (opens in a new tab)
7 PPIO 0.45  1.35 promo: Promotion announced by PPIO · −50% vs its usual price · end date not published0.675 – 1M
See pricing at PPIO (opens in a new tab)
8 ShengSuanYun 0.45  1.35 0.675 – 256k Unverified. No public page for this offer: listed, not designated cheapest
: ShengSuanYun (opens in a new tab). No public price page for this model
9 NanoGPT 0.462 1.39 0.693 – 1M
Go to offer at NanoGPT (opens in a new tab)
10 Tencentvia Eden AI 0.834 2.50 1.25  fp4 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
11 Tencentvia Kilo Gateway 0.834 2.50 1.25  fp4 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
12 ZenMux 0.834 2.50 1.25  – 1M
Go to offer at ZenMux (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.

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$43.78per month
  2. Novita$43.78per month+$0.00 vs the cheapest
  3. Vercel AI Gateway$43.78per month+$0.00 vs the cheapest

Compare Hy4 with

Related models

More from Tencent

All Tencent models

Use this data

The index is queryable. The API is free to use.
Free API
curl https://api.inferindex.dev/cheapest?model=tencent/hy4
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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