Hosted multimodal model APIs
How to use
SiliconCloud.
Testing and integrating hosted open models for chat, embeddings, reranking, image, audio, and video workloads through a common API surface.
SiliconCloud is a SiliconFlow generative AI cloud for hosted language, image, audio, video, embedding, and reranking model APIs. Testing and integrating hosted open models for chat, embeddings, reranking, image, audio, and video workloads through a common API surface. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to SiliconCloud
Get into the official SiliconCloud experience with the right account and a setup you understand.
- 01
Start at https://siliconflow.com/ and confirm the domain before entering account or payment information.
- 02
Availability: SiliconCloud is a browser-managed service accessed through the SiliconFlow console, REST API, and OpenAI-compatible clients rather than a standalone desktop app.
- 03
A SiliconFlow account and funded balance, a server-side API key, an approved service region and data path, licensed inputs and models, representative evaluation data, moderation, and rate, retention, and cost controls.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful SiliconCloud session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define the task, modality, users, data class, model license, quality, safety, context, latency, throughput, retention, region, cost, and fallback requirements.
- 02
Inspect the current model catalog and terms, shortlist exact model IDs by capability and license, and separate synchronous text calls from asynchronous or media workflows.
- 03
Keep the API key server-side and run a frozen benchmark with pinned model and parameters, representative inputs, bounded outputs, captured usage, errors, latency, and retries.
- 04
Review correctness, safety, privacy path, rights, model variability, failure behavior, and task cost, then canary an allowlisted integration with monitoring and a tested fallback.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of SiliconCloud output
Turn a promising generation into an asset you can legally and safely ship.
- 01
Restate the brief, the deliverable format, and where the asset will appear before judging any output.
- 02
Inspect at full resolution: generated media hides its errors at thumbnail size.
- 03
Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.
- 04
Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.
- 05
Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.
- Inspect at full resolution before approving anything.
- Confirm commercial-use rights before an asset reaches a client.
- Keep the prompt and settings with the asset so it can be reproduced.
Privacy & permissions
Use SiliconCloud safely
Use the platform without surrendering rights, likenesses, or client material you do not control.
- 01
Confirm you hold the rights to every reference image, voice, or clip before uploading it.
- 02
Check whether your plan trains on submitted content, and opt out before uploading client work.
- 03
Never upload a real person's likeness or voice without their explicit, documented consent.
- 04
Review the output for marks, styles, or likenesses you have no licence to reproduce.
- 05
Label synthetic media where your client, platform, or jurisdiction requires disclosure.
- OpenAI compatibility describes request shape, not equivalent model behavior, moderation, context, licensing, or reliability. SiliconFlow's terms and privacy policy place substantial responsibility on users for Interaction Data and restrict some uses. Verify current commercial and model terms, avoid sensitive or unauthorized data, keep keys private, pin model IDs, moderate output, cap spend and retries, and independently authorize every tool action.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use SiliconCloud for the work it does best.
Each workflow below has its own outcome, steps and review checkpoints.
Select an exact hosted model through task evidence, current terms, and operating measurements rather than catalog popularity.
↓ 02 WorkflowIntegrate SiliconCloud tools without unsafe actionsSeparate model-generated tool proposals from authentication, authorization, validation, execution, and human approval.
↓Workflow 01
Benchmark a SiliconCloud model for production
Select an exact hosted model through task evidence, current terms, and operating measurements rather than catalog popularity.
Outcome: Pin a model and fallback that meet documented quality, safety, privacy, latency, and cost limits.
- 01
Define task, users, languages, modality, data class, quality, safety, schema, context, latency, throughput, region, retention, commercial use, cost, and rollback thresholds.
- 02
Query the current catalog and record exact model IDs, providers, capabilities, licenses and terms, context, prices, limits, supported parameters, and lifecycle state.
- 03
Run a frozen representative set with a server-side key, identical prompts and settings, bounded output, captured usage, errors, latency, and repeated trials where variance matters.
- 04
Score correctness, grounding, safety, refusals, bias, schema validity, hallucination, tail latency, failure rate, privacy path, and total task cost.
- 05
Pin the winner and an evaluated fallback, enforce allowlists, rate and budget limits, canary it, monitor model changes, and rerun tests before migration.
What good use looks like
- Record exact model IDs and terms.
- Measure tail latency and task cost.
- Retest before every model change.
Workflow 02
Integrate SiliconCloud tools without unsafe actions
Separate model-generated tool proposals from authentication, authorization, validation, execution, and human approval.
Outcome: Use function calling while preventing prompt injection, cross-tenant access, forged arguments, and autonomous consequential actions.
- 01
Define an allowlist of narrow tools, user roles, tenant boundaries, argument schemas, data classifications, approval thresholds, side effects, budgets, timeouts, and audit requirements.
- 02
Keep keys server-side, minimize prompts, quote untrusted content as data, use a pinned model, disable arbitrary URLs or code, and never put credentials in tool descriptions or context.
- 03
Parse tool calls as untrusted proposals, reject unknown names and fields, canonicalize and validate arguments, reauthorize against current user state, and request confirmation for side effects.
- 04
Execute through isolated service accounts with idempotency, least privilege, rate and spend limits, then return bounded results without internal secrets or excessive records.
- 05
Test prompt injection, confused deputy, tenant crossover, replay, duplicate calls, malformed JSON, data exfiltration, timeout, provider failure, key rotation, denial, and rollback.
What good use looks like
- Treat every tool call as untrusted.
- Authorize outside the model.
- Require confirmation for side effects.
Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.
- SiliconCloud quick start ↗
- SiliconFlow API specification ↗
- SiliconFlow privacy policy ↗
- SiliconFlow terms of use ↗