mlx-optiq
← Models

MiMo V2.6 Flash

MiMo V2.6 Flash on OptiQ Cloud, billed per token.

cloud

MiMo V2.6 Flash is a fast model from Xiaomi with a context window of 256K tokens. It is served by OptiQ Cloud, billed per token, and is the cheapest OptiQ Cloud model on cached input. All OptiQ Cloud models are served at full precision, and your requests are never used for training.

Input$0.22 / M
Cached input$0.01 / M
Output$0.65 / M
Context256K tokens
Typical speed—

Next to the other OptiQ Cloud models

Scores are from each maker's model card, for benchmarks that more than one card reports; OptiQ did not run them. Prices are what OptiQ Cloud charges.

Output price, $ per million tokens

Output price, $ per million tokensDeepSeek V4.1 Flash $0.50; GLM 5.3 Flash $0.50; MiniMax M3.1 Flash $0.60; Qwen3.8 27B $2.00; MiMo V2.6 Flash $0.65; MiniMax M3 $2.00; GLM 5.3 $4.40; DeepSeek V4 Pro $6.60DeepSeek V4.1 Flash$0.50GLM 5.3 Flash$0.50MiniMax M3.1 Flash$0.60Qwen3.8 27B$2.00MiMo V2.6 Flash$0.65MiniMax M3$2.00GLM 5.3$4.40DeepSeek V4 Pro$6.60

Input price, $ per million tokens

Input price, $ per million tokensDeepSeek V4.1 Flash $0.10; GLM 5.3 Flash $0.15; MiniMax M3.1 Flash $0.15; Qwen3.8 27B $0.15; MiMo V2.6 Flash $0.22; MiniMax M3 $0.50; GLM 5.3 $1.40; DeepSeek V4 Pro $2.20DeepSeek V4.1 Flash$0.10GLM 5.3 Flash$0.15MiniMax M3.1 Flash$0.15Qwen3.8 27B$0.15MiMo V2.6 Flash$0.22MiniMax M3$0.50GLM 5.3$1.40DeepSeek V4 Pro$2.20

Use it

Connect this Mac

Sign in once. New accounts get $2 of credit. See OptiQ Cloud.

pip install mlx-optiq
optiq cloud login

Claude Code

optiq run claude --cloud mimo-v2.6-flash

Codex

optiq run codex --cloud mimo-v2.6-flash

OpenCode

optiq run opencode --cloud mimo-v2.6-flash

Mistral Vibe

optiq run vibe --cloud mimo-v2.6-flash

Hermes Agent

optiq run hermes --cloud mimo-v2.6-flash

OpenClaw

optiq run openclaw --cloud mimo-v2.6-flash

No local model is loaded. optiq run starts optiq serve --cloud-only, sets the agent up for this session only, and stops the server when the agent exits.

OptiQ Code

Boost: this model leads the task and your local model is its helper.

/boost mimo-v2.6-flash

OptiQ Lab, and any app that talks to optiq serve

Pick optiq-cloud/mimo-v2.6-flash in the model list. With no local model:

optiq serve --cloud-only

The API, from anywhere

Create a key on the dashboard.

curl https://cloud.mlx-optiq.com/api/v1/chat/completions \
  -H "Authorization: Bearer $OPTIQ_CLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mimo-v2.6-flash",
       "messages": [{"role": "user", "content": "Hello"}]}'
from openai import OpenAI

client = OpenAI(
    base_url="https://cloud.mlx-optiq.com/api/v1",
    api_key="<your key>")
reply = client.chat.completions.create(
    model="mimo-v2.6-flash",
    messages=[{"role": "user", "content": "Hello"}])
print(reply.choices[0].message.content)

Details

Input$0.22 per million tokens
Cached input$0.01 per million tokens
Output, including reasoning$0.65 per million tokens
Context window256K tokens
Longest reply131,072 tokens
Model idmimo-v2.6-flash on the API, optiq-cloud/mimo-v2.6-flash in optiq serve