TokenReply

Loading…

Reload
Availability99.0%
Available

Samples: 16

Latency7.4 s
Output speed92.2 tok/s

Xiaomi MiMo V2.6 Flash, a fast low-cost chat and agent model with a 1M-token context window.

Input / 1M tokens
$0.14
Output / 1M tokens
$0.28
Context window
1,050,000
Route
Default
Roleplay

No matching public benchmark is available for this model.

Not measured

Routes

Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.

Use this model
forge$0.07$0.14$0.0014Not measuredNot measuredPlans and tiers
mimo_official$0.07$0.14$0.0014Not measuredNot measuredPlans and tiers
Default$0.14$0.28$0.0028Not measuredNot measuredUse this model
opencode_plus$0.14$0.28$0.0028Not measuredNot measuredPlans and tiers
curl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
  -H "Authorization: Bearer $TOKENREPLY_API_KEY" \
  -H 'Content-Type: application/json' \
  --data '{
  "model": "mimo-v2.6-flash",
  "messages": [
    {
      "role": "user",
      "content": "Reply with hello."
    }
  ]
}'

More XiaomiMiMo models