ZMIME
Comparison · 3 models · Updated Nov 18, 2026

MiMo-V2.6-Pro-UltraSpeed vs Solar Mini 4 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. Upstage

    Solar Mini 4

    Released Sep 22, 2026New

    65/100
    • ECI—
    • Price$0.10 / $0.40
    • Context524K
  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 (Solar Mini 4 65/100, MiMo-V2.6-Pro-UltraSpeed 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 priceSolar Mini 4Solar Mini 4 $0.175 · 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 · Solar Mini 4 524,288 tokens
  • Widest inputsMiMo-V2.6-Pro-UltraSpeedMiMo-V2.6-Pro-UltraSpeed: Text, Images, Audio, Video · Solar Mini 4: Text · Ember-1: Text, Images
  • Self-hostingMiMo-V2.6-Pro-UltraSpeedPublishes downloadable weights
How the score is built
MeasureWeightMiMo-V2.6-Pro-UltraSpeedSolar Mini 4Ember-1
Price50%148212
Inputs & features30%904560
Context window20%655465
Specs & price only100%47/10065/10037/100

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 Solar Mini 4 vs Ember-1 specifications side by side
SpecificationMiMo-V2.6-Pro-UltraSpeedXiaomiSolar Mini 4UpstageEmber-1Fireworks AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$4.35$0.10 (best)$3.00
Output$8.70$0.40 (best)$15.00
Cached input$0.036$0.01 (best)—
Blended (3:1)$5.44$0.175 (best)$6.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Xiaomi APIOfficial Upstage APIMedian of 8 providers
Limits
Context window1,048,576 tokens (best)524,288 tokens1,048,576 tokens (best)
Max output131,072 tokens131,072 tokens131,072 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesYesminimal · low · medium · high · xhigh · maxYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsOpenProprietaryProprietary
API model IDmimo-v2.6-pro-ultraspeedsolar-mini4—
API providers11 (best)58
ReleasedSep 21, 2026Sep 22, 2026Sep 22, 2026
Knowledge cutoff—Feb 2026—
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
  • Solar Mini 4$1.80
  • Ember-1$60.00
04 — Questions

Which should you choose?

Which is better: MiMo-V2.6-Pro-UltraSpeed, Solar Mini 4 or Ember-1?

There is not enough shared capability evidence to name an overall winner. The scores (Solar Mini 4 65/100, MiMo-V2.6-Pro-UltraSpeed 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, Solar Mini 4 or Ember-1?

Solar Mini 4 is cheaper at $0.10 input / $0.40 output per million tokens (official Upstage API price). 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 $0.175 per million tokens for Solar Mini 4 versus $5.44 for MiMo-V2.6-Pro-UltraSpeed (31× as much) and $6.00 for Ember-1 (34× 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, Solar Mini 4 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, Solar Mini 4 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 524,288 for Solar Mini 4. Maximum output per response: MiMo-V2.6-Pro-UltraSpeed up to 131,072, Solar Mini 4 up to 131,072, 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; Solar Mini 4 accepts text; 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; Solar Mini 4 and Ember-1 is proprietary.

Which is newer?

Solar Mini 4 is the newest, released Sep 22, 2026. Ember-1 came out Sep 22, 2026; MiMo-V2.6-Pro-UltraSpeed came out Sep 21, 2026. Knowledge cutoff: Solar Mini 4 Feb 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.