ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral 25.08 vs GLM-4.5-Air vs Qwen3 VL Flash (Alibaba Cloud)

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

Price in rating: Excluded · Include price

  1. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    34/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  2. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    34/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  3. Alibaba (Qwen)

    Qwen3 VL Flash (Alibaba Cloud)

    Released Oct 15, 2025

    47/100
    • ECI—
    • Price$0.022 / $0.215
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 VL Flash (Alibaba Cloud) 47/100, GLM-4.5-Air 34/100, Codestral 25.08 34/100) compare the available specifications only. 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 priceQwen3 VL Flash (Alibaba Cloud)Qwen3 VL Flash (Alibaba Cloud) $0.07 · GLM-4.5-Air $0.425 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextQwen3 VL Flash (Alibaba Cloud)Qwen3 VL Flash (Alibaba Cloud) 262,144 · GLM-4.5-Air 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputsQwen3 VL Flash (Alibaba Cloud)Codestral 25.08: Text · GLM-4.5-Air: Text · Qwen3 VL Flash (Alibaba Cloud): Text, Images
  • Self-hostingGLM-4.5-AirPublishes downloadable weights
How the score is built
MeasureWeightCodestral 25.08GLM-4.5-AirQwen3 VL Flash (Alibaba Cloud)
Inputs & features60%353550
Context window40%323243
Specs only100%34/10034/10047/100

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.

Codestral 25.08 vs GLM-4.5-Air vs Qwen3 VL Flash (Alibaba Cloud) specifications side by side
SpecificationCodestral 25.08Mistral AIGLM-4.5-AirZ.ai (Zhipu)Qwen3 VL Flash (Alibaba Cloud)Alibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.20$0.022 (best)
Output$0.90$1.10$0.215 (best)
Cached input$0.03$0.03—
Blended (3:1)$0.45$0.425$0.07 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Z.AI APIMedian of 1 providers
Limits
Context window128,000 tokens131,072 tokens262,144 tokens (best)
Max output8,192 tokens98,304 tokens (best)32,768 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenProprietary
API model IDcodestral-2508glm-4.5-air—
API providers1118 (best)1
ReleasedJul 30, 2025Jul 28, 2025Oct 15, 2025
Knowledge cutoff—Apr 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.

  • Codestral 25.08$4.80
  • GLM-4.5-Air$4.20
  • Qwen3 VL Flash (Alibaba Cloud)$0.65
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, GLM-4.5-Air or Qwen3 VL Flash (Alibaba Cloud)?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3 VL Flash (Alibaba Cloud) 47/100, GLM-4.5-Air 34/100, Codestral 25.08 34/100) compare the available specifications only. 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, Codestral 25.08, GLM-4.5-Air or Qwen3 VL Flash (Alibaba Cloud)?

Qwen3 VL Flash (Alibaba Cloud) is cheaper at $0.022 input / $0.215 output per million tokens (median across 1 API provider). 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 $0.07 per million tokens for Qwen3 VL Flash (Alibaba Cloud) versus $0.425 for GLM-4.5-Air (6× as much) and $0.45 for Codestral 25.08 (6.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, GLM-4.5-Air has not been scored yet and Qwen3 VL Flash (Alibaba Cloud) has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral 25.08, GLM-4.5-Air and Qwen3 VL Flash (Alibaba Cloud) 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?

Qwen3 VL Flash (Alibaba Cloud) has the largest context window at 262,144 tokens, against 131,072 for GLM-4.5-Air and 128,000 for Codestral 25.08. Maximum output per response: Codestral 25.08 up to 8,192, GLM-4.5-Air up to 98,304, Qwen3 VL Flash (Alibaba Cloud) up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; GLM-4.5-Air accepts text; Qwen3 VL Flash (Alibaba Cloud) accepts text and images. Qwen3 VL Flash (Alibaba Cloud) handles the widest range of inputs.

Are any of these open source?

GLM-4.5-Air publishes its weights and can be self-hosted; Codestral 25.08 and Qwen3 VL Flash (Alibaba Cloud) is proprietary.

Which is newer?

Qwen3 VL Flash (Alibaba Cloud) is the newest, released Oct 15, 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 inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.