ZMIME
Comparison · 3 models · Updated Nov 18, 2026

MiMo-V2.6-Pro-UltraSpeed vs Fugu Max vs Ember-1

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Xiaomi

    MiMo-V2.6-Pro-UltraSpeed

    Released Sep 21, 2026New

    47/100
    • ECI—
    • Price$4.35 / $8.70
    • Context1.05M
  2. Sakana AI

    Fugu Max

    Released Sep 11, 2026

    47/100
    • ECI—
    • Price$2.00 / $6.00
    • Context1M
  3. Fireworks AI

    Ember-1

    Released Sep 22, 2026New

    37/100
    • ECI—
    • Price$3.00 / $15.00
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.6-Pro-UltraSpeed 47/100, Fugu Max 47/100, Ember-1 37/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceFugu MaxFugu Max $3.00 · MiMo-V2.6-Pro-UltraSpeed $5.44 · Ember-1 $6.00 per 1M tokens (3:1 blend)
  • Longest contextMiMo-V2.6-Pro-UltraSpeed and Ember-1MiMo-V2.6-Pro-UltraSpeed 1,048,576 · Ember-1 1,048,576 · Fugu Max 1,000,000 tokens
  • Widest inputsMiMo-V2.6-Pro-UltraSpeedMiMo-V2.6-Pro-UltraSpeed: Text, Images, Audio, Video · Fugu Max: Text, Images, PDFs · Ember-1: Text, Images
  • Self-hostingMiMo-V2.6-Pro-UltraSpeedPublishes downloadable weights
How the score is built
MeasureWeightMiMo-V2.6-Pro-UltraSpeedFugu MaxEmber-1
Price50%142612
Inputs & features30%907060
Context window20%656465
Specs & price only100%47/10047/10037/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

MiMo-V2.6-Pro-UltraSpeed vs Fugu Max vs Ember-1 specifications side by side
SpecificationMiMo-V2.6-Pro-UltraSpeedXiaomiFugu MaxSakana AIEmber-1Fireworks AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$4.35$2.00 (best)$3.00
Output$8.70$6.00 (best)$15.00
Cached input$0.036——
Blended (3:1)$5.44$3.00 (best)$6.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Xiaomi APIMedian of 9 providersMedian of 8 providers
Limits
Context window1,048,576 tokens (best)1,000,000 tokens1,048,576 tokens (best)
Max output131,072 tokens (best)128,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenProprietaryProprietary
API model IDmimo-v2.6-pro-ultraspeed——
API providers11 (best)98
ReleasedSep 21, 2026Sep 11, 2026Sep 22, 2026
Knowledge cutoff———
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • MiMo-V2.6-Pro-UltraSpeed$60.90
  • Fugu Max$32.00
  • Ember-1$60.00
04 — Questions

Which should you choose?

Which is better: MiMo-V2.6-Pro-UltraSpeed, Fugu Max or Ember-1?

There is not enough shared capability evidence to name an overall winner. The scores (MiMo-V2.6-Pro-UltraSpeed 47/100, Fugu Max 47/100, Ember-1 37/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, MiMo-V2.6-Pro-UltraSpeed, Fugu Max or Ember-1?

Fugu Max is cheaper at $2.00 input / $6.00 output per million tokens (median across 9 API providers). MiMo-V2.6-Pro-UltraSpeed costs $4.35 input / $8.70 output per million tokens (official Xiaomi API price); Ember-1 costs $3.00 input / $15.00 output per million tokens (median across 8 API providers). At a typical mix of three input tokens to one output token, that is $3.00 per million tokens for Fugu Max versus $5.44 for MiMo-V2.6-Pro-UltraSpeed (1.8× as much) and $6.00 for Ember-1 (2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. MiMo-V2.6-Pro-UltraSpeed has not been scored yet, Fugu Max has not been scored yet and Ember-1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for MiMo-V2.6-Pro-UltraSpeed, Fugu Max and Ember-1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

MiMo-V2.6-Pro-UltraSpeed and Ember-1 have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for Fugu Max. Maximum output per response: MiMo-V2.6-Pro-UltraSpeed up to 131,072, Fugu Max up to 128,000, Ember-1 up to 131,072 tokens.

Which can read images, PDFs, audio or video?

MiMo-V2.6-Pro-UltraSpeed accepts text, images, audio and video; Fugu Max accepts text, images and PDFs; Ember-1 accepts text and images. MiMo-V2.6-Pro-UltraSpeed handles the widest range of inputs.

Are any of these open source?

MiMo-V2.6-Pro-UltraSpeed publishes its weights and can be self-hosted; Fugu Max and Ember-1 is proprietary.

Which is newer?

Ember-1 is the newest, released Sep 22, 2026. MiMo-V2.6-Pro-UltraSpeed came out Sep 21, 2026; Fugu Max came out Sep 11, 2026.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.