ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GLM-4.5-Air vs o4-mini-deep-research vs Codestral 25.08

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. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    49/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  2. OpenAI

    o4-mini-deep-research

    Released Jun 26, 2025

    38/100
    • ECI—
    • Price$1.80 / $7.20
    • Context200K
  3. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • 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 (GLM-4.5-Air 49/100, Codestral 25.08 49/100, o4-mini-deep-research 38/100) 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 priceGLM-4.5-AirGLM-4.5-Air $0.425 · Codestral 25.08 $0.45 · o4-mini-deep-research $3.15 per 1M tokens (3:1 blend)
  • Longest contexto4-mini-deep-researcho4-mini-deep-research 200,000 · GLM-4.5-Air 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputso4-mini-deep-researchGLM-4.5-Air: Text · o4-mini-deep-research: Text, Images · Codestral 25.08: Text
  • Self-hostingGLM-4.5-AirPublishes downloadable weights
How the score is built
MeasureWeightGLM-4.5-Airo4-mini-deep-researchCodestral 25.08
Price50%652563
Inputs & features30%356035
Context window20%323932
Specs & price only100%49/10038/10049/100

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.

GLM-4.5-Air vs o4-mini-deep-research vs Codestral 25.08 specifications side by side
SpecificationGLM-4.5-AirZ.ai (Zhipu)o4-mini-deep-researchOpenAICodestral 25.08Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.20 (best)$1.80$0.30
Output$1.10$7.20$0.90 (best)
Cached input$0.03—$0.03
Blended (3:1)$0.425 (best)$3.15$0.45
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Z.AI APIMedian of 1 providersOfficial Mistral API
Limits
Context window131,072 tokens200,000 tokens (best)128,000 tokens
Max output98,304 tokens100,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsOpenProprietaryProprietary
API model IDglm-4.5-air—codestral-2508
API providers18 (best)111
ReleasedJul 28, 2025Jun 26, 2025Jul 30, 2025
Knowledge cutoffApr 2025May 2024—
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
  • o4-mini-deep-research$32.40
  • Codestral 25.08$4.80
04 — Questions

Which should you choose?

Which is better: GLM-4.5-Air, o4-mini-deep-research or Codestral 25.08?

There is not enough shared capability evidence to name an overall winner. The scores (GLM-4.5-Air 49/100, Codestral 25.08 49/100, o4-mini-deep-research 38/100) 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, GLM-4.5-Air, o4-mini-deep-research or Codestral 25.08?

GLM-4.5-Air is cheaper at $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); o4-mini-deep-research costs $1.80 input / $7.20 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.425 per million tokens for GLM-4.5-Air versus $0.45 for Codestral 25.08 (1.1× as much) and $3.15 for o4-mini-deep-research (7.4× 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, o4-mini-deep-research 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, o4-mini-deep-research and Codestral 25.08 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?

o4-mini-deep-research has the largest context window at 200,000 tokens, against 131,072 for GLM-4.5-Air and 128,000 for Codestral 25.08. Maximum output per response: GLM-4.5-Air up to 98,304, o4-mini-deep-research up to 100,000, Codestral 25.08 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

GLM-4.5-Air accepts text; o4-mini-deep-research accepts text and images; Codestral 25.08 accepts text. o4-mini-deep-research handles the widest range of inputs.

Are any of these open source?

GLM-4.5-Air publishes its weights and can be self-hosted; o4-mini-deep-research and Codestral 25.08 is proprietary.

Which is newer?

Codestral 25.08 is the newest, released Jul 30, 2025. GLM-4.5-Air came out Jul 28, 2025; o4-mini-deep-research came out Jun 26, 2025. Knowledge cutoff: GLM-4.5-Air Apr 2025, o4-mini-deep-research May 2024.

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.