Stable Diffusion 3.5 Large vs Hy4 preview

At a Glance

Compare
Pricing and Limits
Input priceFrom · USD / 1M tokensNot reported$0.834Openrouter · Sep 22, 2026
Output priceFrom · USD / 1M tokensNot reported$2.501Openrouter · Sep 22, 2026
Context windowMaximum documented tokens0K1,000K
Model facts checkedAug 28, 2026View model evidence →Sep 2, 2026View model evidence →

Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →

Different Model RolesThese models do not share a sourced market category. Their primary-source facts remain comparable below, while performance claims require matched evidence.

Available Benchmarks

All benchmark results →
No Protocol-Matched Benchmark Yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

Side-by-Side Facts

Fieldstable-diffusion-3.5-largeHy4 preview
DeveloperStability AITencent
FamilyStable Diffusion 3 5 LargeHy4
Modelstable-diffusion-3.5-largeHy4 preview
Versionstable-diffusion-3.5-largeHy4 preview
Lifecycleactivepreview
Released2024-10-222026-08-28
Knowledge cutoffUnknownUnknown
Input modalitiesTextText
Output modalitiesImageText
Context window0K1,000K
Total parameters8.1B770B
Active parametersUnknown49B
Licenseotherapache-2.0
Open weightsYesYes
API availableYesYes
Self-hostableYesYes
Provider accessHugging Face (Standard), Stability AI (Pay as you go)Openrouter (Standard)
Capabilitiesgenerationchat, generation, reasoning, tools

Stable Diffusion 3.5 Large Capabilities

generation
Serving providers2
Canonical IDstabilityai/stable-diffusion-3.5-large

Hy4 preview Capabilities

chatgenerationreasoningtools
Serving providers1
Canonical IDtencent/Hy4-preview

Primary Evidence

Sources and Freshness

Questions

Stable Diffusion 3.5 Large vs Hy4 preview FAQs

Is Stable Diffusion 3.5 Large or Hy4 preview better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Stable Diffusion 3.5 Large and Hy4 preview, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Stable Diffusion 3.5 Large or Hy4 preview?+

Only Hy4 preview has a directly sourced input price: $0.834 per million tokens. Only Hy4 preview has a directly sourced output price: $2.501 per million tokens.

Which has a larger context window, Stable Diffusion 3.5 Large or Hy4 preview?+

Hy4 preview has the larger sourced context window. Stable Diffusion 3.5 Large supports 0K and Hy4 preview supports 1,000K.

Which performs better in benchmarks, Stable Diffusion 3.5 Large or Hy4 preview?+

There is no overall benchmark winner: At least two independently verified, protocol-matched benchmarks are required for an overall winner.

Can Stable Diffusion 3.5 Large or Hy4 preview be self-hosted?+

Both models have the same recorded self-hosting status: supported. Stable Diffusion 3.5 Large is open weight; Hy4 preview is open weight.

Can Stable Diffusion 3.5 Large and Hy4 preview understand images?+

Stable Diffusion 3.5 Large is not documented with image input; Hy4 preview is not documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Stable Diffusion 3.5 Large or Hy4 preview?+

Neither has a larger sourced maximum output. Stable Diffusion 3.5 Large is — and Hy4 preview is —.

Do Stable Diffusion 3.5 Large and Hy4 preview support reasoning and tool use?+

Stable Diffusion 3.5 Large: none of these features are definitively sourced. Hy4 preview: reasoning and tool calling. Feature support does not establish relative quality.

Which is available from more inference providers, Stable Diffusion 3.5 Large or Hy4 preview?+

Stable Diffusion 3.5 Large has 2 sourced provider routes; Hy4 preview has 1, so Stable Diffusion 3.5 Large has broader tracked availability.

Which offers better value, Stable Diffusion 3.5 Large or Hy4 preview?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback