LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Hy4 flash

tencent·tencent/hy4-flash·GA·Closed·Hy series·NEW
Tencent's lower-cost Hy4 tier for everyday agent and productivity tasks, with image understanding and a 1M-token context window.

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·OpenRouterGateway
$0.035 / $0.14
Blended $0.061 · 2.3× spread
3 more $0 channels
Context
1,048,576
Output limit
65,536
Knowledge cutoff
—
Released / updated
2026-11-16 / 2026-11-16
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImage

Hy4 flash by tencent is offered by 11 providers on this page. Public prices are shown for 8 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is OpenRouter at $0.035 / $0.141 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 2.3× across the providers that host it. It also has 3 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image.

Available at 11 providers8 with public prices · 3 free

  • ProviderInput / Output
  • KenariGateway
    hy4-flash:free
    Free
    Context 1,048,576Output limit 65,536
  • OpenCodeGateway
    hy4-flash-free
    Free
    Cache read $0Context 1,048,576Output limit 65,536
  • OpenCode GoGateway
    hy4-flash-free
    Free
    Cache read $0Context 1,048,576Output limit 65,536
  • OpenRouterGateway
    $0.035 / $0.14
    Cache read $0.0015Context 1,048,576Output limit 65,536
  • Vercel AI GatewayCloud
    $0.035 / $0.14
    Cache read $0.0015Context 1,024,000 ⚠Output limit 64,000
  • Kilo GatewayGateway
    $0.07 / $0.28
    Cache read $0.003Context 1,048,576Output limit 65,536
  • DevPass (LLM Gateway)Gateway
    $0.07 / $0.28
    Cache read $0.003Context 1,000,000 ⚠Output limit 65,536
  • LLM GatewayGateway
    $0.07 / $0.28
    Cache read $0.003Context 1,000,000 ⚠Output limit 65,536
  • Novita AIGateway
    $0.07 / $0.28
    Cache read $0.003Context 1,000,000 ⚠Output limit 64,000
  • KenariGateway
    $0.071 / $0.29
    Cache read $0.0043Context 1,048,576Output limit 65,536
  • CrossModelGateway
    $0.08 / $0.32
    Cache read $0.0032Context 1,048,576Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
hy4-flash:free
GatewayFree——1,048,57665,536
OpenCode
hy4-flash-free
GatewayFree$0—1,048,57665,536
OpenCode Go
hy4-flash-free
GatewayFree$0—1,048,57665,536
OpenRouterGateway$0.035$0.14$0.0015—1,048,57665,536
Vercel AI GatewayCloud$0.035$0.14$0.0015—1,024,000 ⚠64,000
Kilo GatewayGateway$0.07$0.28$0.003—1,048,57665,536
DevPass (LLM Gateway)Gateway$0.07$0.28$0.003—1,000,000 ⚠65,536
LLM GatewayGateway$0.07$0.28$0.003—1,000,000 ⚠65,536
Novita AIGateway$0.07$0.28$0.003—1,000,000 ⚠64,000
KenariGateway$0.071$0.29$0.0043—1,048,57665,536
CrossModelGateway$0.08$0.32$0.0032$0.081,048,57665,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = highToggle (on / off)effort = minimaleffort = loweffort = mediumeffort = xhigheffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 11 providers.

Your usage cost

Common scenarios
1OpenRouter$10.01
2Vercel AI Gateway$10.01
3Kilo Gateway$20.01
4DevPass (LLM Gateway)$20.01
5LLM Gateway$20.01
6Novita AI$20.01

3 more channels offer $0 (Kenari, OpenCode, OpenCode Go); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.061$02026-11-162026-11-17
2026-11-17Input list —Output list —Min blended $0.061

Related models

Hy4same series$0.83 / $2.50Hy4 previewsame series$0.83 / $2.50Hy3same series$0 / $0
Data partly from models.dev (MIT)