MiMo V2.6 Flash
MiMo V2.6 Flash is Xiaomi's open-weight model for agentic work. We serve the official MOPD weights — an update of Flash-RL made to repeat tool calls less often in agent loops. It reads images as well as text, returns its reasoning separately from the answer and calls tools, with a context of up to a million tokens. We serve it on hardware we operate inside the EEA; prompts and completions are not stored.
model id: mimo-v26-flash
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="mimo-v26-flash", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "mimo-v26-flash", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "mimo-v26-flash", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
export ANTHROPIC_BASE_URL=https://api.heabsy.comexport ANTHROPIC_AUTH_TOKEN="$HEABSY_API_KEY"export ANTHROPIC_MODEL=mimo-v26-flashexport ANTHROPIC_DEFAULT_OPUS_MODEL=mimo-v26-flashexport ANTHROPIC_DEFAULT_SONNET_MODEL=mimo-v26-flashexport ANTHROPIC_DEFAULT_HAIKU_MODEL=mimo-v26-flashexport CLAUDE_CODE_MAX_CONTEXT_TOKENS=1048576claude
Use it in Claude Code · OpenCode · Cline · Kilo Code · SillyTavern · n8n
Price list, updated 21 October 2026. No minimum spend, no subscription.
Which MiMo V2.6 is this?
MiMo V2.6 Flash runs on our own hardware in three variants: the official Xiaomi weights, Uncensored (dealignai's refusal removal carried into the weights) and Abliterated (refusal direction ablated with the Heretic method, applied as an adapter). The two uncensored variants are for research and red-teaming and need your own moderation in front of end users.
MiMo V2.6 Pro is a separate model of the same generation and is served by a partner provider, without zero data retention.
Technical details
- Context window
- 1M tokens
- Max output
- 65,536 tokens
- Throughput limit
- 2M tok/min
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- XiaomiMiMo/MiMo-V2.6-Flash-MOPD
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model runs on GPUs we operate inside the European Economic Area. Prompts and completions are not written to our logs or durable storage, nothing is used for training, and request content is processed in the EEA. How we serve our own models is described on the inference page.
Questions about this model
›Where is MiMo V2.6 Flash computed?
Inside the European Economic Area, on hardware we operate. The catalog reports the processing region per model, so you can answer a supervisory authority without asking us.
›Does MiMo V2.6 Flash store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the MiMo V2.6 Flash context window?
1M tokens, with up to 65,536 tokens of output.
›What does MiMo V2.6 Flash cost?
$0.4762 per million input tokens and $1.4286 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on MiMo V2.6 Flash?
Yes, 2M tokens per minute. Higher limits are a question of volume, not of principle.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| MiMo V2.6 Flash | Xiaomi | — | 1M | — | $0.4762 |
| MiMo V2.6 Flash Uncensored | Xiaomi | — | 1M | — | $0.4404 |
| MiMo V2.6 Flash Abliterated | Xiaomi | — | 1M | — | $0.4762 |
| MiMo V2.6 Pro | Xiaomi | — | 1M | — | $0.87 |
35 more models behind the same key and the same invoice.
Browse the catalog