Stable Diffusion 3.5 Large API
undefineds max · 1MP · Released Oct 22, 2024 · By Stability AI · Stability Community
Stable Diffusion 3.5 Large costs $0.021 per image, against an official rate of $0.035 — 40% below official pricing. It is a Stability AI model under the Stability Community licence, callable through an OpenAI-compatible endpoint with the model id `stabilityai/sd-3.5-large`. This model is listed for reference and is not currently served by an upstream provider, so requests for it return no available channel.
Not currently available. No configured upstream serves this model, so a request for it returns no available channel. The rate below is what it will cost when it is enabled.
Input
$0.0210/img
$0.0350/img
Billing
per image
no per-job minimum
Savings
40%
off official
- No markup
- OpenAI SDK compatible
- No minimum spend
- Stability Community
Deep ecosystem of LoRAs and ControlNets. The pick when you need fine-grained control rather than raw one-shot quality.
Copy this and go
The model id is already filled in. Nothing in this snippet needs editing except your key.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://router.xark.io/api/v1" # ← the only line that changes
)
response = client.chat.completions.create(
model="stabilityai/sd-3.5-large",
messages=[{"role": "user", "content": "Hello"}]
)
Stable Diffusion 3.5 Large pricing across providers
Rates as published by each provider. We update these when they change; if you spot one that's stale, tell us and we'll fix it.
| Provider | Input | Output |
|---|---|---|
| AI Token Router | $0.0210/img | — |
| Official (Stability AI) | $0.0350/img | — |
| Replicate | $0.0400/img | — |
| fal.ai | $0.0380/img | — |
| OpenRouter | Not offered | — |
What it's good at
- ControlNet and LoRA-driven pipelines
- Style-consistent brand asset generation
- Existing SD-based workflows
Other image models
Stable Diffusion 3.5 Large questions
Every figure below is read from the same catalogue entry as the table above, so the two cannot disagree.
What does Stable Diffusion 3.5 Large cost on AI Token Router, and what is the official rate?
Stable Diffusion 3.5 Large is billed at $0.0210 per image here, against Stability AI's official $0.0350 — 40% below, or $0.0140 per image back. There is no platform fee, no minimum spend and no per-job surcharge on top of that rate, and failed requests are not billed. The official figure is published next to ours because a discount with no stated benchmark is not a claim anyone can check.
Can I call Stable Diffusion 3.5 Large right now?
No. Stable Diffusion 3.5 Large is catalogued but not currently servable — no configured upstream provider carries it, so a request naming `stabilityai/sd-3.5-large` returns `no available channel` instead of a result. The rate on this page is what it will cost once an upstream serves it, not something you can spend today. The image models you can call today are Qwen-Image. 7 of the 24 catalogued models are callable, and every page says which it is.
How do I generate an image with Stable Diffusion 3.5 Large?
POST to `https://router.xark.io/api/v1/images/generations` with `"model": "stabilityai/sd-3.5-large"` and a prompt, or call `images.generate` on an OpenAI SDK pointed at `https://router.xark.io/api/v1`. The request and response shapes follow the OpenAI images API, so an existing integration needs the base URL and the model id changed and nothing else. The bare name `sd-3.5-large` and the URL slug `sd-3-5-large` resolve to the same model.
What resolution does Stable Diffusion 3.5 Large output, and what counts as one billable image?
Stable Diffusion 3.5 Large outputs at 1MP. Billing is per generated image at $0.0210/img — one rate, so resolution, prompt length and the number of denoising steps do not change what you are charged, and a request that fails is not billed at all. Asking for several images in one call bills as that many images, which is the same as making the calls separately.
What licence is Stable Diffusion 3.5 Large under, and can I use it commercially?
Stable Diffusion 3.5 Large is published by Stability AI under the Stability Community licence. That is Stability AI's own licence rather than a standard open-source text, so what it permits is set by the document and not by anything inferable from its name. What we can state: it allows third-party hosting, which is the condition for a model appearing in this catalogue at all — we do not resell access to closed-weight models. Conditions such as user thresholds, attribution requirements or acceptable-use terms are common in licences of this kind, so read Stability AI's text before you ship.
How does Stable Diffusion 3.5 Large pricing here compare with other providers carrying it?
Of the 2 other providers we track carrying Stable Diffusion 3.5 Large, the lowest is fal.ai at $0.0380/img, against our $0.0210/img. That is where the rates stood when we last reconciled them, and it can change without notice — we are not claiming to be the cheapest source for this model, only that our rate sits below Stability AI's official $0.0350/img. If you find one of these figures stale, tell us and we will correct it.
What is Stable Diffusion 3.5 Large actually good at?
Deep ecosystem of LoRAs and ControlNets. The pick when you need fine-grained control rather than raw one-shot quality. In practice that points at controlNet and LoRA-driven pipelines, style-consistent brand asset generation and existing SD-based workflows. The specifics that actually decide a fit — the rate, the licence and what it will and will not serve today — are all on this page rather than behind a sales conversation.