ZMIME
Comparison · 3 models · Updated Nov 22, 2026

GLM-4.5-Air vs Gemma-SEA-LION-v4-27B-IT vs Codestral 25.08

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

  1. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    55/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  2. AI Singapore

    Gemma-SEA-LION-v4-27B-IT

    Released Sep 23, 2025

    56/100
    • ECI—
    • Price$0.351 / $0.555
    • Context128K
  3. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025Latest

    54/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  4. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    32/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  5. AI Singapore

    Gemma-SEA-LION-v4-27B-IT

    Released Sep 23, 2025

    32/100
    • ECI—
    • Price$0.351 / $0.555
    • Context128K
  6. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025Latest

    32/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemma-SEA-LION-v4-27B-IT 56/100, GLM-4.5-Air 55/100, Codestral 25.08 54/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (GLM-4.5-Air 32/100, Gemma-SEA-LION-v4-27B-IT 32/100, Codestral 25.08 32/100) compare the available specifications only. The score weighs context window 100%. 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 priceGemma-SEA-LION-v4-27B-ITGemma-SEA-LION-v4-27B-IT $0.402 · GLM-4.5-Air $0.425 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextGLM-4.5-AirGLM-4.5-Air 131,072 · Gemma-SEA-LION-v4-27B-IT 128,000 · Codestral 25.08 128,000 tokens
  • Widest inputsGemma-SEA-LION-v4-27B-ITGLM-4.5-Air: Text · Gemma-SEA-LION-v4-27B-IT: Text, Images · Codestral 25.08: Text
  • Self-hostingGLM-4.5-Air and Gemma-SEA-LION-v4-27B-ITPublishes downloadable weights
How the score is built
MeasureWeightGLM-4.5-AirGemma-SEA-LION-v4-27B-ITCodestral 25.08
Price71%656663
Context window29%323232
Specs & price only100%55/10056/10054/100

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

How the score is built
MeasureWeightGLM-4.5-AirGemma-SEA-LION-v4-27B-ITCodestral 25.08
Context window100%323232
Specs only100%32/10032/10032/100

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

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

GLM-4.5-Air vs Gemma-SEA-LION-v4-27B-IT vs Codestral 25.08 specifications side by side
SpecificationGLM-4.5-AirZ.ai (Zhipu)Gemma-SEA-LION-v4-27B-ITAI SingaporeCodestral 25.08Mistral AI
Capability
Capabilities Index (ECI)Not publishedNot publishedNot published
ECI rankNot publishedNot publishedNot published
ECI confidence intervalNot publishedNot publishedNot published
ECI evaluation dateNot publishedNot publishedNot published
Documented capabilitiesLighter GLM-4.5 variant for fast coding assistance and cheaper agentsGemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction followingMistral code model for low-latency completion, fill-in-the-middle, and code generation
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
Publisher-reported benchmarks
Artificial Analysis Coding IndexPublisher-reported result23.8indexReported resultMay 30, 2026Not publishedNot published
SciCodePublisher-reported result30.6percent correctReported resultMay 30, 2026Not publishedNot published
Terminal-Bench HardPublisher-reported result20.5success rateReported resultMay 30, 2026Not publishedNot published
Price per million tokens
Input$0.20 (best)$0.351$0.30
Output$1.10$0.555 (best)$0.90
Cached input$0.03Not published$0.03
Blended (3:1)$0.425$0.402 (best)$0.45
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIMedian of 3 providersOfficial Mistral API
Limits
Context window131,072 tokens (best)128,000 tokens128,000 tokens
Max inputNot publishedNot publishedNot published
Max output98,304 tokens128,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesNoYes
Structured outputNot publishedNot publishedYes
File attachmentsNoYesYes
Temperature controlYesYesYes
Reasoning controltoggleNot publishedNot published
Availability
WeightsOpenOpenProprietary
API model IDglm-4.5-airNot publishedcodestral-2508
API providers18 (best)311
ReleasedJul 28, 2025Sep 23, 2025Jul 30, 2025
Knowledge cutoffApr 2025Not publishedNot published
Publisher documentationPublisher documentation · Model weightsModel weightsPublisher documentation
Source metadata updatedJul 28, 2025Sep 23, 2025Jul 30, 2025
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 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.

  • GLM-4.5-Air$4.20
  • Gemma-SEA-LION-v4-27B-IT$4.62
  • Codestral 25.08$4.80
04 — Questions

Which should you choose?

Which is better: GLM-4.5-Air, Gemma-SEA-LION-v4-27B-IT or Codestral 25.08?

There is not enough shared capability evidence to name an overall winner. The scores (Gemma-SEA-LION-v4-27B-IT 56/100, GLM-4.5-Air 55/100, Codestral 25.08 54/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (GLM-4.5-Air 32/100, Gemma-SEA-LION-v4-27B-IT 32/100, Codestral 25.08 32/100) compare the available specifications only. The score weighs context window 100%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, GLM-4.5-Air, Gemma-SEA-LION-v4-27B-IT or Codestral 25.08?

Gemma-SEA-LION-v4-27B-IT is cheaper at $0.351 input / $0.555 output per million tokens (median across 3 API providers). GLM-4.5-Air costs $0.20 input / $1.10 output per million tokens (official Z.AI API price); Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.402 per million tokens for Gemma-SEA-LION-v4-27B-IT versus $0.425 for GLM-4.5-Air (1.1× as much) and $0.45 for Codestral 25.08 (1.1× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GLM-4.5-Air has not been scored yet, Gemma-SEA-LION-v4-27B-IT has not been scored yet and Codestral 25.08 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GLM-4.5-Air, Gemma-SEA-LION-v4-27B-IT and Codestral 25.08 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Gemma-SEA-LION-v4-27B-IT has no confirmed tool-calling support in this comparison.

Which has the bigger context window?

GLM-4.5-Air has the largest context window at 131,072 tokens, against 128,000 for Gemma-SEA-LION-v4-27B-IT and 128,000 for Codestral 25.08. Maximum output per response: GLM-4.5-Air up to 98,304, Gemma-SEA-LION-v4-27B-IT up to 128,000, Codestral 25.08 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

GLM-4.5-Air accepts text; Gemma-SEA-LION-v4-27B-IT accepts text and images; Codestral 25.08 accepts text. Gemma-SEA-LION-v4-27B-IT handles the widest range of inputs.

Are any of these open source?

GLM-4.5-Air and Gemma-SEA-LION-v4-27B-IT publishes its weights and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Gemma-SEA-LION-v4-27B-IT is the newest, released Sep 23, 2025. Codestral 25.08 came out Jul 30, 2025; GLM-4.5-Air came out Jul 28, 2025. Knowledge cutoff: GLM-4.5-Air Apr 2025.

How do you decide the winner?

This rating uses price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.