Models

Hy4

tencent ↗ · 1049K ctx · 2 providers · updated 2026-11-04 07:16 UTC

Cheapest
$0.625 via OpenRouter
Avg price
$0.938 /1M
providers
2
Tokens (24h)
1.6T
Volume (24h)
$989.7K est.
(3 × $0.417 + $1.25) ÷ 4 = $0.625/1M — 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 $0.417, 3:1 $0.625, 1:1 $0.834, output only $1.25 per 1M.

The board shows this model's cheapest measured offer ($0.625/1M); the smaller figure under it is the mean of the 2 offers listed below ($0.938/1M). Add those up and divide — it matches. 24h token volume (1.6T) 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 ↗ $0.417$1.25 — — — API-measured
novita-ai Novita AI ↗ $0.834$2.50 — — — API-measured

Who burns this model

Top apps routing traffic to this model over the last 30 days, via OpenRouter's public stats. Only apps that opted into tracking appear, and only the top few are published — this is not the full demand picture. These figures are a 30-day window and are NOT comparable with the cumulative totals on the Apps board.

AppTokens (30d)Requests
SimWorld SceneBenchmark 25M 428
omp 14M 153
Beast 13M 154
DeepSeek Harness 12M 92
pi 8M 80

Volume trend

1.7T 30d d-29 · 1.1T tokensd-28 · 1.2T tokensd-27 · 1.4T tokensd-26 · 1.3T tokensd-25 · 1.3T tokensd-24 · 1.2T tokensd-23 · 841B tokensd-22 · 1.1T tokensd-21 · 1.0T tokensd-20 · 1.1T tokensd-19 · 1.3T tokensd-18 · 1.2T tokensd-17 · 907B tokensd-16 · 846B tokensd-15 · 1.4T tokensd-14 · 1.4T tokensd-13 · 1.5T tokensd-12 · 1.5T tokensd-11 · 1.3T tokensd-10 · 978B tokensd-9 · 974B tokensd-8 · 1.4T tokensd-7 · 1.4T tokensd-6 · 1.5T tokensd-5 · 1.7T tokensd-4 · 1.5T tokensd-3 · 959B tokensd-2 · 735B tokensd-1 · 1.6T tokensd-0 · 1.6T tokens

Last 30 days: 1.1T → 1.6T (+49%); range 735B–1.7T 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/hy4.json. Free reuse requires attribution to tkx.org.

FAQ

How much does Hy4 cost?

Cheapest measured offer right now: $0.417/1M input, $1.2505/1M output via openrouter-best — across 2 tracked providers, refreshed hourly.

Who serves Hy4?

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

How heavily is Hy4 used?

Hy4 routed 1.6T 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