Integration

SiliconFlow integration

SiliconFlow serverless inference for open-source models. Run chat and text completions, an Anthropic-compatible messages call, embeddings and reranking, generate images, submit and poll video generation jobs, synthesise speech from a stock or uploaded voice and transcribe audio, list the served models and read the account balance. The text surface is OpenAI-compatible, so only the model id usually changes. Authentication is a bearer API key.

Connect SiliconFlow How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in SiliconFlow.Built from the 15 SiliconFlow tools below, on the connection you add once.

What you can do with SiliconFlow

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Completion, 2 operations

create_chat_completionCreate chat completionPOSTChat Completions.
create_completionCreate completionPOSTCreate completion.

Deletion, 1 operation

delete_voiceDelete voicePOSTDelete User Voice.

Embedding, 1 operation

create_embeddingCreate embeddingPOSTCreate Embeddings.

Generation, 1 operation

generate_imageGenerate imagePOSTImage Generation.

Info, 1 operation

get_user_infoGet user infoGETGet user information.

List, 1 operation

list_voicesList voicesGETGet Voice List.

Message, 1 operation

create_anthropic_messageCreate anthropic messagePOSTChat Completions.

Model, 1 operation

list_modelsList modelsGETGet Model List.

Rerank, 1 operation

rerank_documentsRerank documentsPOSTCreate Rerank.

Speech, 1 operation

create_speechCreate speechPOSTCreate Speech.

Statu, 1 operation

get_video_job_statusGet video job statusPOSTget video.

Submit, 1 operation

submit_video_jobSubmit video jobPOSTSubmit video.

Transcription, 1 operation

create_transcriptionCreate transcriptionPOSTCreate Audio Transcriptions.

Voice, 1 operation

upload_voiceUpload voicePOSTUpload Voice.

Use SiliconFlow from Claude Code, Cursor or Codex

Connect SiliconFlow in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its SiliconFlow operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect SiliconFlow

Create your workspace
Sign up free. Nothing to install.
Connect SiliconFlow once
Add your SiliconFlow connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.