InferIndex
Language, English, EN
Account

ModelsTencentHy3 preview

Hy3 preview

tencent/hy3-preview262k context Compare →
Offers
6
Providers
5

Cheapest right now

GMICloud

via OpenRouter

bf16 · 262k

$0.285 blended / 1M tokens

No change7D
in
$0.18
out
$0.60
Cached input
$0.06

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

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). #131 of 419Best rank in the source's rank spread, 131st to 171st, given the confidence intervals of all ranked models. 156th by score. 1,409 1,401 to 1,416Arena Score · 6,869 votes
  • Code Arena (WebDev)The Code Arena ranking (WebDev). The source publishes no style-corrected series (as read on 9 October 2026). #111 of 152Best rank in the source's rank spread, 111th to 127th, given the confidence intervals of all ranked models. 120th by score. 1,357 1,340 to 1,374Arena Score · 1,444 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

Hy3 preview costs from $0.285 per million tokens (at a 3:1 input:output mix): the cheapest current offer, at GMICloud, checked on ; 6 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 (5)

  • $0.285 · GMICloud via Kilo Gateway · cannot be designated the cheapest
  • $0.285 · Glama via Glama · cannot be designated the cheapest
  • $0.285 · Martian via Martian · cannot be designated the cheapest
  • $0.285 · Nous Portal via Nous Portal · cannot be designated the cheapest
  • $0.286 · Qiniu · cannot be designated the cheapest

Cheapest, no training on prompts

No offer with a published no-training policy for this model.

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$0.283, Qiniu–
2026-10-03$0.283, Qiniu–
2026-10-04$0.283, Qiniu–
2026-10-05$0.283, Qiniu–
2026-10-06$0.283, Qiniu–
2026-10-07$0.283, Qiniu–
2026-10-08$0.283, Qiniu–
2026-10-09$0.283, Qiniu–
2026-10-10$0.284, Qiniu–
2026-10-11$0.284, Qiniu–
2026-10-12$0.284, Qiniu–
2026-10-13$0.284, Qiniu–
2026-10-14$0.284, Qiniu–
2026-10-15$0.284, Qiniu–
2026-10-16$0.284, Qiniu–
2026-10-17$0.284, Qiniu–
2026-10-18$0.284, Qiniu–
2026-10-19$0.285, GMICloud–
2026-10-20$0.285, GMICloud–
2026-10-21$0.285, GMICloud–
2026-10-22$0.285, GMICloud–
2026-10-23$0.285, GMICloud–
2026-10-24$0.285, GMICloud–
2026-10-25$0.285, GMICloud–
2026-10-26$0.285, GMICloud–
2026-10-27$0.285, GMICloud–
2026-10-28$0.285, GMICloud–
2026-10-29$0.285, GMICloud–
2026-10-30$0.285, GMICloud–
2026-10-31$0.285, GMICloud–

Cheapest offer

Offers

6 of 6 offers

Offers for Hy3 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 GMICloudvia Kilo Gateway 0.18 0.60  0.285 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
2 Glama 0.18 0.60  0.285 – 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
3 Martian 0.18 0.60  0.285 – – 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)
4 Nous Portal 0.18 0.60  0.285 – 262k 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)
5 GMICloudvia OpenRouter 0.18 0.60  0.285 bf16 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)
6 Qiniu 0.18 0.601 0.286 – 262k Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestprompt up to 16K tokens: up to 16K: $0.18 / $0.601; up to 32K: $0.241 / $0.962; above that: $0.301 / $1.20 (Input / Output, per million tokens)
See pricing at Qiniu (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.

  • GMICloud

    $0.285

    Kilo Gateway

    in
    $0.18
    out
    $0.60 
    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

  • Glama

    $0.285

    Glama

    in
    $0.18
    out
    $0.60 
    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

    $0.285

    Martian

    in
    $0.18
    out
    $0.60 
    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

    $0.285

    Nous Portal

    in
    $0.18
    out
    $0.60 
    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.

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

  • GMICloud

    $0.285

    OpenRouter

    in
    $0.18
    out
    $0.60 
    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 30). Offers are ranked with this fee included.

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

  • Qiniu

    $0.286

    direct

    in
    $0.18
    out
    $0.601
    Precision
    –
    Context
    262k

    Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestprompt up to 16K tokens: up to 16K: $0.18 / $0.601; up to 32K: $0.241 / $0.962; above that: $0.301 / $1.20 (Input / Output, per million tokens)

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

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. GMICloud$19.80per month

Host it yourself instead? See the break-even

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

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