One Endpoint.
Every Frontier Model.
Mimo is the enterprise AI API gateway for production teams. Drop-in OpenAI compatibility, an interactive playground, per-key rate limits, streaming, and transparent analytics.
Built for production teams
Everything you need to ship AI features — gateway, playground, keys, billing and observability in one place.
Drop-in OpenAI Compatibility
Change the base URL to https://mimo.lokerin.net/v1 and your key. Zero code changes across SDKs and agents.
Interactive Playground
Try every model in the browser before writing code. Compare outputs, tune temperature, export snippets. Open playground →
Frontier Models
General agents, reasoning flagships and long-context models behind one key — chat and responses APIs supported.
Streaming & Responses API
Real-time SSE streaming plus /v1/responses for reasoning models. Token params auto-normalized.
Keys, Plans & Limits
Per-key rate limits with Retry-After headers, expirations, plan tiers and fair-use enforcement.
Usage Analytics
Dashboard with daily requests, token usage, 7-day charts, logs and a public status page.
cutad-agent
General-purpose agent. Fast responses for everyday tasks, chat and content generation.
model: "cutad-agent"
Try in playground →cutad-agent-pro
Enhanced reasoning for complex tasks. Longer context, better accuracy, production-grade output.
model: "cutad-agent-pro"
Try in playground →muse-spark
Reasoning flagship via the Responses API. Deep analysis, tool-style structured output.
model: "muse-spark-1.3-contributor-free"
Try in playground →deepseek-bitdeer
DeepSeek V4 Flash at scale through high-throughput inference. Great quality per token.
model: "deepseek-bitdeer"
Try in playground →deepseek-opencode
DeepSeek Flash via the reasoning gateway. For experiments and evaluation workloads.
model: "deepseek-opencode"
Try in playground →Try before you code
No SDK required. Pick a model, type a prompt, compare results — then export the code.
Up and running in 3 steps
Pick a model
Choose cutad-agent for general tasks, muse-spark-1.3-contributor-free for reasoning.
Make your first call
Use any OpenAI-compatible SDK or plain HTTP. That's it.
curl https://mimo.lokerin.net/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "cutad-agent",
"messages": [{"role": "user", "content": "Hello!"}],
"stream": true
}'from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://mimo.lokerin.net/v1")
resp = client.chat.completions.create(
model="cutad-agent",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in resp:
print(chunk.choices[0].delta.content or "", end="")const res = await fetch("https://mimo.lokerin.net/v1/chat/completions", {
method: "POST",
headers: { "Content-Type": "application/json", "Authorization": "Bearer YOUR_API_KEY" },
body: JSON.stringify({ model: "cutad-agent", messages: [{ role: "user", content: "Hello!" }], stream: true }),
});Endpoints
| Endpoint | Method | Description |
|---|---|---|
/v1/chat/completions | POST | Chat completions (streaming or non-streaming) |
/v1/responses | POST | Responses API for reasoning models (e.g. muse-spark) |
/v1/models | GET | List available models |