ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Kimi K2.8 Preview vs GPT-5.4 mini

Kimi K2.8 Preview comes out ahead, 66 to 60 on our weighted score.

  1. Our pick

    Moonshot AI

    Kimi K2.8 Preview

    Released Sep 11, 2026

    66/100
    • ECI—
    • Price—
    • Context1.05M
    Full specs Remove Kimi K2.8 Preview

  2. OpenAI

    GPT-5.4 mini

    Released Mar 17, 2026

    60/100
    • ECI148.8
    • Price$0.75 / $4.50
    • Context400K
    Full specs Remove GPT-5.4 mini

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Kimi K2.8 Preview is our pick

Kimi K2.8 Preview is the better all-round choice, scoring 66/100 against GPT-5.4 mini (60). It leads on context window. The score weighs inputs & features 60%, context window 40%. 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 priceGPT-5.4 miniGPT-5.4 mini $1.69 per 1M tokens (3:1 blend) · Kimi K2.8 Preview unpriced
  • Longest contextKimi K2.8 PreviewKimi K2.8 Preview 1,048,576 · GPT-5.4 mini 400,000 tokens
  • Widest inputsKimi K2.8 PreviewKimi K2.8 Preview: Text, Images, Video · GPT-5.4 mini: Text, Images
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightKimi K2.8 PreviewGPT-5.4 mini
Inputs & features60%7070
Context window40%6144
Overall100%66/10060/100

Left out because at least one model lacks the data: capability and price. 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.

Kimi K2.8 Preview vs GPT-5.4 mini specifications side by side
SpecificationKimi K2.8 PreviewMoonshot AIGPT-5.4 miniOpenAI
Capability
Capabilities Index (ECI)—148.8
ECI rank—#56 of 148
GPQA DiamondGraduate-level science questions—86.9%
FrontierMath Tiers 1–3Research-level mathematics—51.2%
OTIS Mock AIME 2024–2025Competition mathematics—88.9%
SimpleQA VerifiedShort factual questions—29.4%
Price per million tokens
Input—$0.75
Output—$4.50
Cached input—$0.075
Blended (3:1)—$1.69
Long-context rate—Same rate
Price source—Official OpenAI API
Limits
Context window1,048,576 tokens (best)400,000 tokens
Max output—128,000 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsNoNo
AudioNoNo
VideoYesNo
ReasoningYesYeslow · medium · high · xhigh
Tool callingYesYes
Structured outputNoYes
Availability
WeightsProprietaryProprietary
API model ID—gpt-5.4-mini
API providers—29
ReleasedSep 11, 2026Mar 17, 2026
Knowledge cutoff—Aug 31, 2025
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.

  • Kimi K2.8 Preview—
  • GPT-5.4 mini$16.50
04 — Questions

Which should you choose?

Which is better: Kimi K2.8 Preview or GPT-5.4 mini?

Kimi K2.8 Preview is the better all-round choice, scoring 66/100 against GPT-5.4 mini (60). It leads on context window. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Kimi K2.8 Preview or GPT-5.4 mini?

GPT-5.4 mini is cheaper at $0.75 input / $4.50 output per million tokens (official OpenAI API price). . At a typical mix of three input tokens to one output token, that is $1.69 per million tokens for GPT-5.4 mini versus . Kimi K2.8 Preview has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Kimi K2.8 Preview has not been scored yet and GPT-5.4 mini has an ECI of 148.8.

Which is better for coding?

There are no published SWE-bench Verified results for Kimi K2.8 Preview and GPT-5.4 mini yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.

Which has the bigger context window?

Kimi K2.8 Preview has the largest context window at 1,048,576 tokens, against 400,000 for GPT-5.4 mini. Maximum output per response: GPT-5.4 mini up to 128,000 tokens.

Which can read images, PDFs, audio or video?

Kimi K2.8 Preview accepts text, images and video; GPT-5.4 mini accepts text and images. Kimi K2.8 Preview handles the widest range of inputs.

Are any of these open source?

No. Kimi K2.8 Preview and GPT-5.4 mini are proprietary and only available through APIs and apps.

Which is newer?

Kimi K2.8 Preview is the newest, released Sep 11, 2026. GPT-5.4 mini came out Mar 17, 2026. Knowledge cutoff: GPT-5.4 mini Aug 31, 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons