ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral vs GLM-4.5-Air vs Qwen2.5-VL 7B Instruct

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

Price in rating: Included · Exclude price

Retired Qwen2.5-VL 7B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.

  1. Mistral AI

    Codestral

    Released May 29, 2024

    51/100
    • ECI—
    • Price$0.30 / $0.90
    • Context256K
  2. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    49/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  3. Alibaba (Qwen)

    Qwen2.5-VL 7B Instruct

    Released Sep 2024Retired

    51/100
    • ECI—
    • Price$0.35 / $1.05
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 7B Instruct 51/100, Codestral 51/100, GLM-4.5-Air 49/100) 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 $0.45 · Qwen2.5-VL 7B Instruct $0.525 per 1M tokens (3:1 blend)
  • Longest contextCodestralCodestral 256,000 · GLM-4.5-Air 131,072 · Qwen2.5-VL 7B Instruct 131,072 tokens
  • Widest inputsQwen2.5-VL 7B InstructCodestral: Text · GLM-4.5-Air: Text · Qwen2.5-VL 7B Instruct: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightCodestralGLM-4.5-AirQwen2.5-VL 7B Instruct
Price50%636563
Inputs & features30%353550
Context window20%433224
Specs & price only100%51/10049/10051/100

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 vs GLM-4.5-Air vs Qwen2.5-VL 7B Instruct specifications side by side
SpecificationCodestralMistral AIGLM-4.5-AirZ.ai (Zhipu)Qwen2.5-VL 7B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.20 (best)$0.35
Output$0.90 (best)$1.10$1.05
Cached input$0.03$0.03—
Blended (3:1)$0.45$0.425 (best)$0.525
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Z.AI APIOfficial Alibaba API
Limits
Context window256,000 tokens (best)131,072 tokens131,072 tokens
Max output4,096 tokens98,304 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenOpenOpen
API model IDcodestral-latestglm-4.5-airqwen2-5-vl-7b-instruct
API providers418 (best)1
ReleasedMay 29, 2024Jul 28, 2025Sep 2024
Knowledge cutoffOct 2024Apr 2025Apr 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.

  • Codestral$4.80
  • GLM-4.5-Air$4.20
  • Qwen2.5-VL 7B Instruct$5.60
04 — Questions

Which should you choose?

Which is better: Codestral, GLM-4.5-Air or Qwen2.5-VL 7B Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen2.5-VL 7B Instruct 51/100, Codestral 51/100, GLM-4.5-Air 49/100) 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, Codestral, GLM-4.5-Air or Qwen2.5-VL 7B Instruct?

GLM-4.5-Air is cheaper at $0.20 input / $1.10 output per million tokens (official Z.AI API price). Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price). 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 (1.1× as much) and $0.525 for Qwen2.5-VL 7B Instruct (1.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, GLM-4.5-Air has not been scored yet and Qwen2.5-VL 7B Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral, GLM-4.5-Air and Qwen2.5-VL 7B Instruct 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?

Codestral has the largest context window at 256,000 tokens, against 131,072 for GLM-4.5-Air and 131,072 for Qwen2.5-VL 7B Instruct. Maximum output per response: Codestral up to 4,096, GLM-4.5-Air up to 98,304, Qwen2.5-VL 7B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Codestral accepts text; GLM-4.5-Air accepts text; Qwen2.5-VL 7B Instruct accepts text and images. Qwen2.5-VL 7B Instruct handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights, so you can self-host them.

Which is newer?

GLM-4.5-Air is the newest, released Jul 28, 2025. Qwen2.5-VL 7B Instruct came out Sep 2024; Codestral came out May 29, 2024. Knowledge cutoff: Codestral Oct 2024, GLM-4.5-Air Apr 2025, Qwen2.5-VL 7B Instruct Apr 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.