Models

Hy3

tencent ↗ · 262K ctx · 5 providers · updated 2026-08-04 22:15 UTC

Cheapest
$0.231 via OpenRouter
Avg price
$0.242 /1M
providers
5
Tokens (24h)
880B
Volume (24h)
$203.3K est.
(3 × $0.132 + $0.528) ÷ 4 = $0.231/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.132, 3:1 $0.231, 1:1 $0.330, output only $0.528 per 1M.

The board shows this model's cheapest measured offer ($0.231/1M); the smaller figure under it is the mean of the 5 offers listed below ($0.242/1M). Add those up and divide — it matches. 24h token volume (880B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $0.132$0.528 API-measured
0g-teetls 0G Router $0.132$0.528 API-measured
deepinfra HuggingFace Router $0.140$0.580 268ms 26 API-measured
novita-ai Novita AI $0.140$0.580 API-measured
requesty Requesty $0.140$0.580 API-measured

Volume trend

1.9T 30d d-29 · 283B tokensd-28 · 327B tokensd-27 · 970B tokensd-26 · 1.0T tokensd-25 · 964B tokensd-24 · 1.1T tokensd-23 · 1.1T tokensd-22 · 1.1T tokensd-21 · 1.4T tokensd-20 · 1.6T tokensd-19 · 1.7T tokensd-18 · 1.7T tokensd-17 · 1.9T tokensd-16 · 1.6T tokensd-15 · 1.6T tokensd-14 · 1.8T tokensd-13 · 597B tokensd-12 · 713B tokensd-11 · 723B tokensd-10 · 717B tokensd-9 · 590B tokensd-8 · 597B tokensd-7 · 820B tokensd-6 · 842B tokensd-5 · 614B tokensd-4 · 612B tokensd-3 · 725B tokensd-2 · 580B tokensd-1 · 631B tokensd-0 · 880B tokens

Last 30 days: 283B → 880B (+211%); range 283B–1.9T tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/hy3.json. Free reuse requires attribution to tkx.org.

About

Hy3 is an AI model served by multiple inference providers on AI model marketplaces, specializing in natural language processing tasks. It is listed under the organization tag "Tencent".

AI-generated summary from public information — is this yours?

FAQ

How much does Hy3 cost?

Cheapest measured offer right now: $0.132/1M input, $0.528/1M output via openrouter-best — across 5 tracked providers, refreshed hourly.

Who serves Hy3?

5 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is Hy3 used?

Hy3 routed 880B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings