Integration

SambaNova Cloud integration

SambaNova Cloud (SambaCloud) runs open models such as gpt-oss, DeepSeek, Llama, Gemma and MiniMax on SambaNova hardware. Generate replies in three compatible formats (OpenAI Chat Completions, OpenAI Responses, Anthropic Messages), continue a raw text prompt, count a Messages prompt's input tokens, and list the available models with their context length and per-token price. Every generation is billed per token; the Free Tier (no payment method) allows 20 requests per minute and per day and 200,000 tokens a day per model. Streaming is not exposed, and the embeddings and audio transcription and translation routes are left out because SambaNova serves their models (E5-Mistral-7B-Instruct, Whisper-Large-v3) on SambaStack only, not on SambaCloud. Authentication is an API key from the SambaCloud portal (API section) sent as a Bearer token in the Authorization header.

Connect SambaNova Cloud How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in SambaNova Cloud.Built from the 7 SambaNova Cloud tools below, on the connection you add once.

What you can do with SambaNova Cloud

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

Model, 2 operations

get_modelGet modelGETAgents: ask firstReturns one model available on SambaCloud: id, context_length, max_completion_tokens and per-token pricing in USD. An unknown id is refused as not found.
list_modelsList modelsGETAgents: ask firstLists the models available on SambaCloud: id, context_length, max_completion_tokens and per-token pricing in USD (prompt, completion and, where offered, cache read and write). Use an id as model in the generation tools.

Chat completion, 1 operation

create_chat_completionCreate chat completionPOSTAgents: ask firstGenerates the next assistant message for a conversation (system, user, assistant and tool roles) with the chosen model, with optional function tools, JSON output and reasoning effort. Returns choices[0].message and token usage. Billed per token.

Completion, 1 operation

create_completionCreate completionPOSTAgents: ask firstContinues a raw text prompt (no chat roles) with the chosen model. Returns the generated text in choices[0].text and token usage. Billed per token. For conversations use create_chat_completion.

Message, 1 operation

create_messageCreate messagePOSTAgents: ask firstGenerates a reply in the Anthropic Messages format (top-level system prompt, content blocks, tool_use) with the chosen model; max_tokens is required. Returns content[] blocks, stop_reason and usage. Billed per token.

Message token count, 1 operation

count_message_tokensCount message tokensPOSTAgents: ask firstCounts the input tokens a create_message call with the same model, system, messages, tools and tool_choice would use, without generating a reply. Returns input_tokens.

Model response, 1 operation

create_responseCreate responsePOSTAgents: ask firstGenerates a reply in the OpenAI Responses format from a text input or a list of input items. Stateless: send the full history each call. Returns output[] items (message, reasoning, function_call) and usage. Billed per token.

Use SambaNova Cloud from Claude Code, Cursor or Codex

Connect SambaNova Cloud in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its SambaNova Cloud 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 SambaNova Cloud

Create your workspace
Sign up free. Nothing to install.
Connect SambaNova Cloud once
Add your SambaNova Cloud 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.