MiniMax M3

from openai import OpenAI

client = OpenAI(
    base_url="https://api.batchin.tech/v1",
    api_key="BATCHIN_API_KEY",
    default_headers={"X-BatchIn-Lane": "turbo"}  # "turbo" | "pro" | "economy" | "failover"
)

resp = client.chat.completions.create(
    model="minimax-m3",
    messages=[{"role": "user", "content": "Benchmark system architecture performance and cost profile."}],
    extra_body={"route_policy": "lowest_latency"}  # Turbo low-latency lane
)

print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.batchin.tech/v1",
  apiKey: process.env.BATCHIN_API_KEY,
  defaultHeaders: { "X-BatchIn-Lane": "turbo" }, // "turbo" | "pro" | "economy" | "failover"
});

const resp = await client.chat.completions.create({
  model: "minimax-m3",
  messages: [{ role: "user", content: "Benchmark system architecture performance and cost profile." }],
});

console.log(resp.choices[0]?.message?.content);

curl https://api.batchin.tech/v1/chat/completions \
  -H "Authorization: Bearer $BATCHIN_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-BatchIn-Lane: turbo" \
  -d '{
    "model": "minimax-m3",
    "messages": [{"role":"user","content":"Benchmark system architecture performance and cost profile."}]
  }' -i
# Inspect response headers:
# X-BatchIn-Lane: speed_optimized
# X-BatchIn-Latency-Ms: 138
# X-BatchIn-Route-Decision: primary_lane