Models

hy3

openrouter · 262K ctx · 7 providers · updated 2026-09-19 01:15 UTC

Cheapest
$0.144 Official list · OpenRouter
Avg price
$0.249 /1M
providers
7
Tokens (24h)
728B
Volume (24h)
$168.3K est.
(3 × $0.083 + $0.330) ÷ 4 = $0.144/1M — 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 $0.083, 3:1 $0.144, 1:1 $0.206, output only $0.330 per 1M.

The board shows this model's cheapest measured offer ($0.144/1M); the smaller figure under it is the mean of the 9 offers listed below ($0.249/1M). Add those up and divide — it matches. 24h token volume (728B) 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 Pricebook (LiteLLM) $0.083$0.330 Official list
openrouter-best OpenRouter $0.132$0.528 API-measured
novita Pricebook (LiteLLM) $0.140$0.580 Official list
deepinfra Pricebook (LiteLLM) $0.140$0.580 Official list
deepinfra HuggingFace Router $0.140$0.580 415ms 57 API-measured
novita-ai Novita AI $0.140$0.580 API-measured
requesty Requesty $0.140$0.580 API-measured
aihubmix Pricebook (LiteLLM) $0.156$0.625 Official list
0g-teetls 0G Router $0.198$0.792 API-measured

Volume trend

1.3T 30d d-29 · 1.3T tokensd-28 · 1.1T tokensd-27 · 754B tokensd-26 · 707B tokensd-25 · 1.1T tokensd-24 · 1.0T tokensd-23 · 1.0T tokensd-22 · 1.1T tokensd-21 · 963B tokensd-20 · 699B tokensd-19 · 748B tokensd-18 · 825B tokensd-17 · 515B tokensd-16 · 730B tokensd-15 · 768B tokensd-14 · 510B tokensd-13 · 343B tokensd-12 · 301B tokensd-11 · 495B tokensd-10 · 575B tokensd-9 · 571B tokensd-8 · 547B tokensd-7 · 678B tokensd-6 · 473B tokensd-5 · 458B tokensd-4 · 776B tokensd-3 · 782B tokensd-2 · 756B tokensd-1 · 766B tokensd-0 · 728B tokens

Last 30 days: 1.3T → 728B (-42%); range 301B–1.3T 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: $0.0825/1M input, $0.33/1M output via openrouter — across 7 tracked providers, refreshed hourly.

Who serves hy3?

7 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 728B 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