Submit
XiaomiOpen-weight·1000K context·— params·MIT

MiMo-V2.6-Flashxiaomi/mimo-v2-6-flash

MiMo-V2.6-Flash is Xiaomi's lower-priced multimodal API option in the September 22 release. Its downloadable MOPD checkpoint has an MIT license. The published token rate is useful for screening high-volume workflows; it does not establish cost per successful task or a latency guarantee.

Cheapest blended:$0.17 / 1M tokenson Xiaomi MiMo · 1 provider listed

Official sources checked October 2, 2026. Evaluation suggestions below are not benchmark results.

Where Flash's price helps—and where it does not

For 7.5M uncached input and 2.5M output tokens, the displayed standard rates produce a $1.75 estimate. This is arithmetic, not an invoice. A workflow that needs twice as many attempts can erase a token-price advantage, so compare total spend per acceptable result rather than input price alone.

The published batch schedule is $0.07 input, $0.0014 cached input and $0.14 output per million tokens. Batch changes the cost and completion pattern; use it only for work whose deadline tolerates asynchronous processing. Keep interactive and queued usage separate in budgets.

Multimodal inputs need a task-specific check

The official checkpoint supports text, image, video and audio input with text output. This does not establish that every wrapper exposes every modality. Confirm the exact endpoint payload before evaluating screenshots, recordings or clips.

For an extraction workload, score missed fields, invented fields and unusable formatting separately. For a clip or audio task, test whether the answer cites the correct event or time interval. Save the input and generation settings so a failed task can be reproduced.

Weights, tool loops and migration

The linked MOPD weights are MIT-licensed. The provider describes a tool-repetition improvement; this page does not claim a tested fix. Put a cap on tool steps and retries, and count repeated calls even when the final answer eventually succeeds.

Xiaomi has scheduled the older V2.5 APIs for October 21 retirement. Before changing a production alias, test Flash on the jobs you currently send to V2.5, retain rollback settings and check the latest notice. A release date alone is not sufficient evidence of a safe replacement.

Official source 1 →Official source 2 →Official source 3 →Official source 4 →

Pricing across providers

Sort by:
ProviderInput /1MOutput /1MBlended /1MLatency p50FormatFreshnessAction
Xiaomi MiMo
mimo-v2.6-flash

Standard USD pay-as-you-go rate; batch pricing differs. Account and region eligibility must be checked.

$0.14
Cached $0.0028
$0.28$0.175—OpenAI-compatibleNeeds 24d agoTry →

Affiliate disclosure: We may earn a commission from qualified signups. Pricing independence is enforced at the data layer — see our Editorial Independence Policy.

Works with

Point any of these clients at a hosting's base URL — they all speak at least one of this model's endpoint protocols (OPENAI_COMPATIBLE).

Capabilities

  • reasoning
  • coding
  • tool_use
  • multimodal_input

Code samples

Example using Xiaomi MiMo — the cheapest hosting for this model as of last verification. Swap base_url and model to use a different provider from the matrix above.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.xiaomimimo.com/v1",
)

response = client.chat.completions.create(
    model="mimo-v2.6-flash",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

Technical specs

Context
1000K
Max output
128K
Parameters
—
Release
2026-09-22
Training cutoff
—
License
MIT
Hugging Face →Official documentation →

Similar models

Compare with

  • MiMo-V2.6-Flash vs DeepSeek V4.1 Flash
    Comparison planned — not yet published
  • MiMo-V2.6-Flash vs GLM 5.3 Flash
    Comparison planned — not yet published
  • MiMo-V2.6-Flash vs Kimi K2.5
    Comparison planned — not yet published

Frequently asked

How much does MiMo-V2.6-Flash cost?+
The cheapest public hosting is $0.17 per 1M blended tokens on Xiaomi MiMo. 1 total providers are listed above with per-input / per-output / cached pricing.
Is MiMo-V2.6-Flash open-source? Can I fine-tune it?+
MiMo-V2.6-Flash has published weights. License: MIT. Review the linked repository and license for deployment, fine-tuning and commercial-use conditions.
Is MiMo-V2.6-Flash OpenAI-compatible?+
At least one listed hosting exposes an OpenAI-compatible API, so you can point an existing openai SDK client at the Provider's base_url and use the Provider's model name. See the Code Samples above for a copy-pasteable example.
What's the maximum context window for MiMo-V2.6-Flash?+
The model supports up to 1,000,000 tokens of context (input + output). Some hosted versions may impose a smaller limit — check the "Context" column in the pricing matrix for each provider.