LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Hy3

tencent·tencent/hy3·GA·Open weights·Hy series
Tencent Hy reasoning model for coding, instruction following, and agent tasks

Specs & pricing

Input / output per 1M tokens
Official price·Tencent TokenHub
$0 / $0
Blended $0 · Cache read $0
Lowest paid·NanoGPTGateway
$0.066 / $0.26
Blended $0.11 · 3.2× spread
2 more $0 channels
Context
256,000
Output limit
128,000
Knowledge cutoff
—
Released / updated
2026-07-06 / 2026-07-06
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Weights
Hugging Face

Hy3 by tencent is offered by 26 providers on this page. Public prices are shown for 22 of them. Its official list price is $0 per 1M tokens. No paid channel is priced below the official list price. Prices vary about 3.2× across the providers that host it. It also has 2 free ($0) channels and 2 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 79 tokens per second, with 3.07s to the first token.

The context window is 256,000 tokens at the reference host, but hosts report different limits, from 190,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed79 tok/s
TTFT3.07 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 26 providers22 with public prices · 2 free · 2 subscription-covered

  • ProviderInput / Output
  • Tencent TokenHubOfficialFirst-party
    Subscription
    Cache read $0Context 256,000Output limit 128,000
  • Tencent Token PlanGateway
    Subscription
    Cache read $0Context 256,000Output limit 128,000
  • OrcaRouterGateway
    tencent/hy3-free
    Free
    Context 256,000Output limit 128,000
  • OpenCodeGateway
    hy3-free
    Free
    Cache read $0Context 190,000 ⚠Output limit 64,000deprecated
  • NanoGPTGateway
    $0.066 / $0.26
    Cache read $0.029Context 262,144 ⚠Output limit 128,000
  • Eden AIGateway
    deepinfra/tencent/Hy3
    $0.13 / $0.53
    Cache read $0.033Context 262,144 ⚠Output limit 128,000
  • Deep InfraCloud
    tencent/Hy3
    $0.13 / $0.53
    Cache read $0.033Context 262,144 ⚠Output limit 128,000deprecated
  • LLM GatewayGateway
    $0.13 / $0.53
    Cache read $0.033Context 262,144 ⚠Output limit 131,072
  • DevPass (LLM Gateway)Gateway
    $0.13 / $0.53
    Cache read $0.033Context 262,144 ⚠Output limit 128,000
  • SiliconFlowCloud
    tencent/Hy3
    $0.13 / $0.53
    Cache read $0.033Context 262,144 ⚠Output limit 262,144
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Tencent TokenHubOfficialFirst-partySubscription$0$0256,000128,000
Tencent Token PlanGatewaySubscription$0$0256,000128,000
OrcaRouter
tencent/hy3-free
GatewayFree——256,000128,000
OpenCode
hy3-free
GatewayFree$0—190,000 ⚠64,000deprecated
NanoGPTGateway$0.066$0.26$0.029—262,144 ⚠128,000
Eden AI
deepinfra/tencent/Hy3
Gateway$0.13$0.53$0.033—262,144 ⚠128,000
Deep Infra
tencent/Hy3
Cloud$0.13$0.53$0.033—262,144 ⚠128,000deprecated
LLM GatewayGateway$0.13$0.53$0.033—262,144 ⚠131,072
DevPass (LLM Gateway)Gateway$0.13$0.53$0.033—262,144 ⚠128,000
SiliconFlow
tencent/Hy3
Cloud$0.13$0.53$0.033—262,144 ⚠262,144

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

Toggle (on / off)effort = noneeffort = higheffort = loweffort = mediumeffort = minimaleffort = xhighbudget_tokens ≥ 128 ≤ 32,768effort = max

Interleaved thinking (reasoning between tool calls) is declared by 5 of 26 providers.

1 / 26 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1NanoGPT$21.76
2Eden AI$40.86
3Deep Infra$40.86
4LLM Gateway$40.92
5DevPass (LLM Gateway)$40.92
6SiliconFlow$40.92

4 more channels offer $0 (Tencent TokenHub, Tencent Token Plan, OrcaRouter etc.); 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
$0.23$02026-08-052026-09-03
2026-09-03Input list $0Output list $0Min blended $0.11

Benchmark31 items

NameConditionsScoreMetricSource
SWE-Bench Verified—78resolvedSource ↗
SWE-Bench Multilingualharness: SWE-agent · variant: highest reasoning effort75.8scoreSource ↗
SWE-Bench Proharness: SWE-agent · variant: highest reasoning effort57.9scoreSource ↗
Terminal-Benchharness: Terminus 2 · variant: highest reasoning effort; 4h timeout; 500 episodes · v2.171.7scoreSource ↗
NL2Repoharness: Claude Code · variant: highest reasoning effort; 250 turns; 12000s timeout45.6scoreSource ↗
DeepSWEharness: mini-swe-agent · variant: highest reasoning effort; 2h timeout28scoreSource ↗
BrowseCompharness: Tencent internal search harness · variant: highest reasoning effort84.2scoreSource ↗
WideSearchharness: Tencent internal search harness · variant: highest reasoning effort76.4scoreSource ↗
DeepSearchQAharness: Tencent internal search harness · variant: highest reasoning effort91scoreSource ↗
MCP Atlasharness: Scale AI · variant: highest reasoning effort; April 2026; 100 tool calls · dataset: 500 public tasks79.1scoreSource ↗
Toolathlonvariant: highest reasoning effort48.5scoreSource ↗
APEX-Agentsvariant: highest reasoning effort25.6pass@1Source ↗
ClawEvalharness: Tencent internal harness · variant: highest reasoning effort · dataset: 105 queries · v2026032568.5pass@3Source ↗
WildClawBenchharness: OpenClaw · variant: highest reasoning effort · dataset: 35 text-only tasks53.6scoreSource ↗
SkillsBenchharness: Claude Code · variant: highest reasoning effort · dataset: 79 text-only tasks55.3average over 3 runsSource ↗
Humanity's Last Examvariant: highest reasoning effort; with tools · dataset: text-only53.2scoreSource ↗
Humanity's Last Examvariant: highest reasoning effort; without tools · dataset: text-only37scoreSource ↗
GPQA Diamondvariant: highest reasoning effort90.4scoreSource ↗
FrontierSciencevariant: highest reasoning effort; research21.3scoreSource ↗
FrontierSciencevariant: highest reasoning effort; olympiad74.8scoreSource ↗
USAMOvariant: highest reasoning effort · v202672scoreSource ↗
MathArena Apexvariant: highest reasoning effort38.7scoreSource ↗
ArxivMathvariant: highest reasoning effort52.2scoreSource ↗
HorizonMathvariant: highest reasoning effort7.1pass@12Source ↗
PHYBenchvariant: highest reasoning effort77.4scoreSource ↗
CMT Benchmarkvariant: highest reasoning effort37.8scoreSource ↗
IMOAnswerBenchvariant: highest reasoning effort90scoreSource ↗
SuperChemvariant: highest reasoning effort54.9scoreSource ↗
CL-benchvariant: highest reasoning effort23.8scoreSource ↗
CL-bench-lifevariant: highest reasoning effort17scoreSource ↗
AA-LCRvariant: highest reasoning effort73.4scoreSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations13 items

GPQA Diamond89.7%
Humanity's Last Exam33.5%
HLE-Diamond11.6%
CritPt4.9%
SciCode48.6%
Terminal-Bench 2.164.4%
Terminal-Bench 4.00.5%
τ³-Bench Banking22.9%
AutomationBench-AA18.4%
AA-Briefcase947
GDPval-AA1071
GDP.pdf11.2%
AA-LCR79.0%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Hy4 flashsame series—Hy4same series$0.83 / $2.50Hy4 previewsame series$0.83 / $2.50Hy-MT2 Plussame lab—Hy3 previewsame lab$0 / $0
Data partly from models.dev (MIT) · Tencent TokenHub official docs ↗