Guide d'installation pour frameworks d'agents

Quel endpoint utiliser ?

Deux endpoints — choisir le bon

Tokonomix expose deux endpoints de passerelle. Le choix dépend de si votre agent utilise des appels d'outils.

Quand utiliser quel endpoint

OpenClaw

OpenClaw se connecte à Tokonomix via l'URL de base Anthropic. Les appels d'outils et le streaming fonctionnent immédiatement.

# OpenClaw config (config.toml or .openclaw)
[api]
base_url = "https://tokonomix.ai/api/anthropic"
api_key  = "tok-your-key"

# For consensus (single-model passthrough via OpenAI endpoint):
# base_url = "https://tokonomix.ai/api/v1"
# model    = "tokonomix-consensus"

# Tool-calling agents: use the Anthropic base URL (Mode B).
# Consensus sessions: switch to the OpenAI-compat base URL above.

LangChain

Utilisez la classe ChatOpenAI avec une URL de base personnalisée. Pour les agents utilisant des outils, basculez sur l'endpoint Anthropic Messages.

# Python — plain chat or consensus
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="tokonomix-consensus",          # or any model slug
    base_url="https://tokonomix.ai/api/v1",
    api_key="tok-your-key",
)

# Tool-calling agents: switch to the Anthropic endpoint
from langchain_anthropic import ChatAnthropic

tool_llm = ChatAnthropic(
    model="claude-sonnet-4-6",
    base_url="https://tokonomix.ai/api/anthropic",
    api_key="tok-your-key",
)
# Bind tools as usual:
# agent_llm = tool_llm.bind_tools([my_tool])

AutoGen

Le OpenAIChatCompletionClient d'AutoGen accepte une URL de base personnalisée. Définissez-la sur l'endpoint compatible OpenAI de Tokonomix pour le chat et le consensus.

# Python — AutoGen 0.4+ (autogen-agentchat)
from autogen_ext.models.openai import OpenAIChatCompletionClient

# Plain chat or consensus
client = OpenAIChatCompletionClient(
    model="tokonomix-consensus",          # or any model slug
    base_url="https://tokonomix.ai/api/v1",
    api_key="tok-your-key",
)

# Tool-calling agents: use OpenAI client pointed at the OpenAI-compat endpoint.
# Consensus: pass model="tokonomix-consensus"; remove any tools= argument.
# Note: do NOT pass tools= when using tokonomix-consensus — that model does not
# accept tool definitions and will return a 400 error.

Claude Code MCP

Claude Code récupère Tokonomix via le serveur MCP. Une fois configuré, Claude Code peut appeler directement tokonomix_consensus_ask et tokonomix_single_ask.

// ~/.claude/settings.json  (or project .claude/settings.json)
{
  "mcpServers": {
    "tokonomix": {
      "command": "npx",
      "args": ["-y", "tokonomix-mcp"],
      "env": {
        "TOKONOMIX_API_KEY": "tok-your-key"
      }
    }
  }
}

// Available MCP tools after setup:
//   tokonomix_consensus_ask   — ask a question across multiple models at once
//   tokonomix_single_ask      — single-model call with full token accounting
//   tokonomix_get_balance     — check remaining token balance
//   tokonomix_list_models     — enumerate available models and capabilities
//
// Example usage in Claude Code:
//   tokonomix_consensus_ask({ prompt: "Review this function for edge cases", ... })
//
// Note: the MCP tools use the gateway internally — no separate endpoint config needed.

Erreurs courantes et solutions