InferIndex
Language, English, EN
Account

ModelsTencentHy3

Hy3

tencent/hy3262k 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.
$0.254
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.
$1.75
Offers
34
Providers
16

Cheapest right now

NanoGPT

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

262k

$0.115 blended / 1M tokens

No change7D
in
$0.066
out
$0.26
Cached input
$0.029
Go to offer Go to offer at NanoGPT (opens in a new tab)via NanoGPT

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). #57 of 419Best rank in the source's rank spread, 57th to 88th, given the confidence intervals of all ranked models. 75th by score. 1,454 1,449 to 1,460Arena Score · 13,840 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #57 of 152Best rank in the source's rank spread, 57th to 67th, given the confidence intervals of all ranked models. 64th by score. 1,505 1,497 to 1,514Arena Score · 6,844 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. #42 of 57Best rank in the source's rank spread, 42nd to 50th, given the confidence intervals of all ranked models. 46th by score. −0.073 −0.088 to −0.059IPS score · 1,214,847 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

Hy3 costs from $0.115 per million tokens (at a 3:1 input:output mix): the cheapest of 10 comparable offers, at NanoGPT, 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)

  • $0.23 · DeepInfra via Eden AI · cannot be designated the cheapest
  • $0.23 · DeepInfra via Vercel AI Gateway · another route of the same provider
  • $0.231 · Tencent via Eden AI · cannot be designated the cheapest
  • $0.231 · Tencent via Kilo Gateway · cannot be designated the cheapest
  • $0.231 · Glama via Glama · cannot be designated the cheapest
  • $0.231 · Martian via Martian · cannot be designated the cheapest
  • $0.231 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.231 · Tencent via LLM Gateway · another route of the same provider
  • $0.231 · Tencent via Requesty · another route of the same provider
  • $0.231 · Tencent via OpenRouter · another route of the same provider
  • $0.25 · GMICloud via Kilo Gateway · cannot be designated the cheapest
  • $0.25 · Novita via Kilo Gateway · cannot be designated the cheapest
  • $0.25 · Novita via Vercel AI Gateway · another route of the same provider
  • $0.25 · Novita via LLM Gateway · another route of the same provider
  • $0.25 · DeepInfra via LLM Gateway · cannot be designated the cheapest
  • $0.25 · Novita via Requesty · another route of the same provider
  • $0.25 · GMICloud via OpenRouter · another route of the same provider
  • $0.25 · Novita via OpenRouter · another route of the same provider
  • $0.253 · Poe via Poe · price converted from points
  • $0.263 · ShengSuanYun via ShengSuanYun · cannot be designated the cheapest
  • $0.273 · Phala via Kilo Gateway · cannot be designated the cheapest
  • $0.283 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
  • $0.35 · AtlasCloud via Kilo Gateway · cannot be designated the cheapest
  • $0.35 · AtlasCloud via OpenRouter · another route of the same provider

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$0.115, NanoGPT–
2026-10-03$0.115, NanoGPT–
2026-10-04$0.115, NanoGPT–
2026-10-05$0.115, NanoGPT–
2026-10-06$0.115, NanoGPT–
2026-10-07$0.115, NanoGPT–
2026-10-08$0.115, NanoGPT–
2026-10-09$0.115, NanoGPT–
2026-10-10$0.115, NanoGPT–
2026-10-11$0.115, NanoGPT–
2026-10-12$0.115, NanoGPT–
2026-10-13$0.115, NanoGPT–
2026-10-14$0.115, NanoGPT–
2026-10-15$0.115, NanoGPT–
2026-10-16$0.115, NanoGPT–
2026-10-17$0.115, NanoGPT–
2026-10-18$0.115, NanoGPT–
2026-10-19$0.115, NanoGPT–
2026-10-20$0.115, NanoGPT–
2026-10-21$0.115, NanoGPT–
2026-10-22$0.115, NanoGPT–
2026-10-23$0.115, NanoGPT–
2026-10-24$0.115, NanoGPT–
2026-10-25$0.115, NanoGPT–
2026-10-26$0.115, NanoGPT–
2026-10-27$0.115, NanoGPT–
2026-10-28$0.115, NanoGPT–
2026-10-29$0.115, NanoGPT–
2026-10-30$0.115, NanoGPT–
2026-10-31$0.115, NanoGPT–

Cheapest offer

Offers

The 25 cheapest of 34 offers

Offers for Hy3, 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 0.066 0.26  0.115 – 262k
Go to offer at NanoGPT (opens in a new tab)
2 DeepInfravia Hugging Face 0.13  0.53  0.23  fp4 262k United States
See pricing at Hugging Face (opens in a new tab)
3 DeepInfravia Eden AI 0.13  0.53  0.23  fp4 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
4 DeepInfravia Vercel AI Gateway 0.13  0.53  0.23  fp4 262k United States
Go to offer at Vercel AI Gateway (opens in a new tab)
5 Tencentvia Eden AI 0.132 0.528 0.231 fp8 256k 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
6 Tencentvia Kilo Gateway 0.132 0.528 0.231 fp8 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapestPrice changes often: 14 price changes in 7 days. Over that period: input $0.083 – $0.132, output $0.33 – $0.528 per million tokens. An offer whose price changes this often is not selected as the cheapest.
Go to offer at Kilo Gateway (opens in a new tab)
7 Tencentvia Vercel AI Gateway 0.132 0.528 0.231 fp8 256k
Go to offer at Vercel AI Gateway (opens in a new tab)
8 Glama 0.132 0.528 0.231 – 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
9 Martian 0.132 0.528 0.231 – – 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)
10 Nous Portal 0.132 0.528 0.231 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestPrice changes often: 14 price changes in 7 days. Over that period: input $0.083 – $0.132, output $0.33 – $0.528 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)
11 Tencentvia LLM Gateway 0.132 0.528 0.231 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)
12 Tencentvia Requesty 0.132 0.528 0.231 fp8 262k 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)
13 Tencentvia OpenRouter 0.132 0.528 0.231 fp8 262k Price changes often: 16 price changes in 7 days. Over that period: input $0.083 – $0.132, output $0.33 – $0.528 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)
14 Novita 0.14  0.58  0.25  – 262k
See pricing at Novita (opens in a new tab)
15 GMICloudvia Kilo Gateway 0.14  0.58  0.25  bf16 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
16 GMICloudvia Vercel AI Gateway 0.14  0.58  0.25  bf16 262k
Go to offer at Vercel AI Gateway (opens in a new tab)
17 Novitavia Kilo Gateway 0.14  0.58  0.25  – 262k Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
Go to offer at Kilo Gateway (opens in a new tab)
18 Novitavia Vercel AI Gateway 0.14  0.58  0.25  – 262k
Go to offer at Vercel AI Gateway (opens in a new tab)
19 Novitavia LLM Gateway 0.14  0.58  0.25  – – 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)
20 DeepInfravia LLM Gateway 0.14  0.58  0.25  fp4 – United States 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)
21 Novitavia Requesty 0.14  0.58  0.25  – 262k 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)
22 GMICloudvia OpenRouter 0.14  0.58  0.25  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)
23 Novitavia OpenRouter 0.14  0.58  0.25  – 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)
24 Poe 0.141 0.586 0.253 – 262k Unverified. No public page for this offer: listed, not designated cheapestpriced in points: Converted from points or credits: the amount paid depends on how points are bought.
No public offer page
25 ZenMux 0.147 0.589 0.258 – 262k
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.

  • NanoGPT

    $0.115

    NanoGPT

    in
    $0.066
    out
    $0.26 
    Precision
    –
    Context
    262k

    No training on prompts

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

  • DeepInfra

    $0.23

    Hugging Face

    in
    $0.13 
    out
    $0.53 
    Precision
    fp4
    Context
    262k

    No training on promptsUnited States

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

  • DeepInfra

    $0.23

    Eden AI

    in
    $0.13 
    out
    $0.53 
    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

    $0.23

    Vercel AI Gateway

    in
    $0.13 
    out
    $0.53 
    Precision
    fp4
    Context
    262k

    No training on promptsUnited States

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

  • Tencent

    $0.231

    Eden AI

    in
    $0.132
    out
    $0.528
    Precision
    fp8
    Context
    256k

    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

    $0.231

    Kilo Gateway

    in
    $0.132
    out
    $0.528
    Precision
    fp8
    Context
    262k

    Training terms not publishedUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapestPrice changes often: 14 price changes in 7 days. Over that period: input $0.083 – $0.132, output $0.33 – $0.528 per million tokens. An offer whose price changes this often is not selected as the cheapest.

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

  • Tencent

    $0.231

    Vercel AI Gateway

    in
    $0.132
    out
    $0.528
    Precision
    fp8
    Context
    256k

    Training terms not published

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

  • Glama

    $0.231

    Glama

    in
    $0.132
    out
    $0.528
    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

    $0.231

    Martian

    in
    $0.132
    out
    $0.528
    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

    $0.231

    Nous Portal

    in
    $0.132
    out
    $0.528
    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: 14 price changes in 7 days. Over that period: input $0.083 – $0.132, output $0.33 – $0.528 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

  • Tencent

    $0.231

    LLM Gateway

    in
    $0.132
    out
    $0.528
    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

    $0.231

    Requesty

    in
    $0.132
    out
    $0.528
    Precision
    fp8
    Context
    262k

    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

  • Tencent

    $0.231

    OpenRouter

    in
    $0.132
    out
    $0.528
    Precision
    fp8
    Context
    262k

    Training terms not publishedPrice changes often: 16 price changes in 7 days. Over that period: input $0.083 – $0.132, output $0.33 – $0.528 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

  • Novita

    $0.25

    direct

    in
    $0.14 
    out
    $0.58 
    Precision
    –
    Context
    262k

    No training on prompts

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

  • GMICloud

    $0.25

    Kilo Gateway

    in
    $0.14 
    out
    $0.58 
    Precision
    bf16
    Context
    262k

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

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

  • GMICloud

    $0.25

    Vercel AI Gateway

    in
    $0.14 
    out
    $0.58 
    Precision
    bf16
    Context
    262k

    Training terms not published

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

  • Novita

    $0.25

    Kilo Gateway

    in
    $0.14 
    out
    $0.58 
    Precision
    –
    Context
    262k

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

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

  • Novita

    $0.25

    Vercel AI Gateway

    in
    $0.14 
    out
    $0.58 
    Precision
    –
    Context
    262k

    No training on prompts

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

  • Novita

    $0.25

    LLM Gateway

    in
    $0.14 
    out
    $0.58 
    Precision
    –
    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.

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

  • DeepInfra

    $0.25

    LLM Gateway

    in
    $0.14 
    out
    $0.58 
    Precision
    fp4
    Context
    –

    No training on promptsUnited StatesFee 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

  • Novita

    $0.25

    Requesty

    in
    $0.14 
    out
    $0.58 
    Precision
    –
    Context
    262k

    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

  • GMICloud

    $0.25

    OpenRouter

    in
    $0.14 
    out
    $0.58 
    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

    $0.25

    OpenRouter

    in
    $0.14 
    out
    $0.58 
    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.

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

  • Poe

    $0.253

    Poe

    in
    $0.141
    out
    $0.586
    Precision
    –
    Context
    262k

    Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapestpriced in points: Converted from points or credits: the amount paid depends on how points are bought.

    No public offer page

  • ZenMux

    $0.258

    ZenMux

    in
    $0.147
    out
    $0.589
    Precision
    –
    Context
    262k

    Prompts may be used for training

    Go to offer Go to offer at ZenMux (opens in a new tab)via ZenMux
Show all 34 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. NanoGPT$7.86per month
  2. DeepInfra$15.75per month+$7.89 vs the cheapest
  3. Tencent$15.84per month+$7.98 vs the cheapest

Host it yourself instead? See the break-even

Compare Hy3 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/hy3
MCP server
claude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp

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