xiaomiCertifiedReleased 09/21/2026

MiMo V2.6 Flash

MiMo V2.6 Flash is Xiaomi's efficient multimodal reasoning model for coding, automation, and everyday agent workflows. Hosted on Boundless with a 1,048,576-token context window, it accepts text, images, audio, and video. It supports reasoning, tool calling, structured output, and prompt caching.

View API reference ↓
Input / output priceFrom$0.11 / $0.22per 1M
24h uptime99.80%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "xiaomi/mimo-v2.6-flash",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

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

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
boundless1.05M1.05M6.5 s252 tps$0.14$0.28Read $0.0028Write —8 featuresNoNoGlobalCertified
DeepInfra1.05M1.05M3.3 s87 tps$0.14$0.28Read $0.0028Write —6 featuresNoYesGlobalCertified
gmicloud1.05M1.05M4.2 s38 tps$0.11$0.22Read $0.0024Write —8 featuresNoNoGlobalCertified
inference-net1.05M1.05M——$0.14$0.28Read $0.0028Write —6 featuresNoNoGlobalListed
novita1.05M131K4.5 s42 tps$0.14$0.28Read $0.0028Write —8 featuresNoNoGlobalCertified
tencent1M128K1.6 s—$0.14$0.28Read $0.0028Write —6 featuresNoNoGlobalListed
xiaomi1.05M131K3.3 s44 tps$0.14$0.28Read $0.0028Write —8 featuresNoNoGlobalCertified

Uptime

24 hours

Request success rate per provider.

boundless99.50%
DeepInfra99.98%
gmicloud99.56%
inference-net—
novita99.97%
tencent100.00%
xiaomi99.75%

Throughput

last hour

P50 output tokens per second.

boundless252 tps
DeepInfra87 tps
xiaomi44 tps
novita42 tps
gmicloud38 tps
inference-net—
tencent—

Latency

last hour

P50 time to first token.

tencent1.6 s
xiaomi3.3 s
DeepInfra3.3 s
gmicloud4.2 s
novita4.5 s
boundless6.5 s
inference-net—

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "xiaomi/mimo-v2.6-flash",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

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

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. xiaomi/mimo-v2.6-flash. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. MiMo V2.6 Flash supports up to 131,072 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1.05M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens

More models by xiaomi

ModelContextInputOutputCacheRelease
xiaomi/mimo-v2.6-pro1.05M$0.44$0.87Read $0.0036Write —09/21/2026
xiaomi/mimo-v2.6-pro-ultraspeed1.05M$4.35$8.70Read $0.036Write —09/21/2026