FAQ

Account & API Keys

How do I get an API Key?

Register on our platform and navigate to the API Keys section in your dashboard. You can generate a new key from there.

How many API Keys can I create?

Each account can create multiple API Keys. All keys under the same account share the same rate limits.

What should I do if my API Key is leaked?

Immediately revoke the compromised key in your dashboard and create a new one. Any requests made with the old key after revocation will be rejected.

Billing & Usage

How is usage calculated?

Usage is calculated based on the number of input and output tokens processed. Cached input tokens are billed at a reduced rate. See the Pricing & Rate Limits page for detailed per-model pricing.

Is there a free tier?

MiMo-V2-TTS is currently free for a limited time. Other models are billed per token usage.

How can I check my usage?

Visit the Usage section in your dashboard to view detailed token consumption and request statistics.

Models & Capabilities

Which model should I choose?

• MiMo-V2-Pro — Best for complex reasoning and coding tasks. Supports up to 1M context length.
• MiMo-V2-Flash — Fast and cost-effective for general tasks. Great for high-throughput use cases.
• MiMo-V2-Omni — Designed for multimodal tasks including image, audio, and video understanding.
• MiMo-V2-TTS — Purpose-built for speech synthesis.

What API formats are supported?

We support both OpenAI-compatible and Anthropic-compatible API formats. You can use existing SDKs and tools with minimal configuration changes.

Do the models support function calling / tool use?

Yes, MiMo-V2-Pro, MiMo-V2-Omni, and MiMo-V2-Flash all support function calling.

Technical Issues

I'm getting 429 errors. What should I do?

A 429 error means you have hit the rate limit. Implement exponential backoff in your retry logic and consider spreading requests over time. Check the Pricing & Rate Limits page for your model's RPM and TPM limits.

Can I use the OpenAI Python SDK?

Yes. Simply set the base_url to https://api.mimo-v2.com/v1 and use your Mimo API Key:

from openai import OpenAI

client = OpenAI(
    api_key="your-mimo-api-key",
    base_url="https://api.mimo-v2.com/v1",
)

Is streaming supported?

Yes, all text generation models support streaming output via the stream: true parameter.