LLM API pricing

Hy4 API pricing: cheapest provider

3 providers sell Hy4. GMI Cloud is cheapest; the most expensive charges 1.3× as much for the same model.

  • Cheapest$0.6254per 1M · GMI Cloud
  • Input · output$0.417 / $1.25per 1M tokens
  • Price gap1.3×across 3 providers
  • Context1Mmax tokens
$0.6254 GMI Cloud1.3× spread$0.7844 Chutes
Already paying for Hy4? Check if you overpay →

Standard list prices in USD from each provider's pricing page · last price change Nov 14, 2026 · How we collect and rank prices

Ranked for your volume

Hy4 monthly cost by provider

Change the monthly tokens and the ranking updates instantly, using each provider's standard list price.

More requirements: caching, context, features, provider

Share this page URL to keep your scenario. 3 of 3 providers meet these assumptions.

Cheapest provider for your volume

GMI Cloud

3 options · most expensive $31.38, 1.3× this price

$25.02estimated / month
ProviderEstimated / monthInput / 1MOutput / 1MCached input / 1MContext
1
GMI CloudInference providerCheapestPricing page
$25.02$0.417$1.25$0.0211M
2
Novita AIInference providerPricing page
$25.02$0.417$1.25$0.0211M
3
ChutesInference providerPricing page
$31.38$0.525$1.56$0.0251M

Order depends on listed price for your volume only. No provider pays for its position.

What this estimate leaves out

Input volume includes the cached share, not an additional token volume. This is a list-price estimate, not a quote: cache-write charges, cache eligibility/TTL, batch discounts, long-context surcharges, regional pricing and taxes are excluded. Check the provider's terms for your workload before switching.

Price history

The cheapest price has not changed since tracking started on Nov 8, 2026: $0.6254 per 1M tokens at GMI Cloud. All price changes

Switch to the cheapest provider

Switch to Novita AI

Already using the OpenAI SDK? Change the base URL, key and model name.

Show the code
from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.novita.ai/openai",
    api_key=os.environ["NOVITA_API_KEY"],
)
response = client.chat.completions.create(
    model="tencent/hy4",
    messages=[{"role": "user", "content": "Hello"}],
)
Base URL from Novita AI's API docs, model name from the open pricing datasets. Check the model page in Novita AI's docs before you switch production traffic.

Compare Hy4 with another model

Or pick any model

Before you pick a provider

Context windows differ by provider, from 1M to 1M tokens. A cheaper host may not accept your longest prompts.

3 of 3 providers list a cached-input price. Repeated system prompts or documents can cost much less there than the standard input rate shown above.