ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Codestral 25.08 vs Qwen3 Omni 30B A3B Thinking vs GLM-4.5-Air

Qwen3 Omni 30B A3B Thinking comes out ahead, 59 to 48 and 47 on our weighted score.

  1. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    47/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
    Full specs Remove Codestral 25.08
  2. Our pick

    Alibaba (Qwen)

    Qwen3 Omni 30B A3B Thinking

    Released Sep 22, 2025

    59/100
    • ECI—
    • Price$0.25 / $0.97
    • Context66K
    Full specs Remove Qwen3 Omni 30B A3B Thinking

  3. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    48/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
    Full specs Remove GLM-4.5-Air
01 — Verdict

Qwen3 Omni 30B A3B Thinking is our pick

Qwen3 Omni 30B A3B Thinking is the better all-round choice, scoring 59/100 against GLM-4.5-Air (48) and Codestral 25.08 (47). It leads on inputs & features. 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 · Qwen3 Omni 30B A3B Thinking $0.43 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextGLM-4.5-AirGLM-4.5-Air 131,072 · Codestral 25.08 128,000 · Qwen3 Omni 30B A3B Thinking 65,536 tokens
  • Widest inputsQwen3 Omni 30B A3B ThinkingCodestral 25.08: Text · Qwen3 Omni 30B A3B Thinking: Text, Images, Audio, Video · GLM-4.5-Air: Text
  • Self-hostingQwen3 Omni 30B A3B Thinking and GLM-4.5-AirPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightCodestral 25.08Qwen3 Omni 30B A3B ThinkingGLM-4.5-Air
Price50%646465
Inputs & features30%358035
Context window20%241225
Overall100%47/10059/10048/100

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 Qwen3 Omni 30B A3B Thinking vs GLM-4.5-Air specifications side by side
SpecificationCodestral 25.08Mistral AIQwen3 Omni 30B A3B ThinkingAlibaba (Qwen)GLM-4.5-AirZ.ai (Zhipu)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.25$0.20 (best)
Output$0.90 (best)$0.97$1.10
Cached input$0.03—$0.03
Blended (3:1)$0.45$0.43$0.425 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 1 providersOfficial Z.AI API
Limits
Context window128,000 tokens65,536 tokens131,072 tokens (best)
Max output8,192 tokens16,384 tokens98,304 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoYesNo
VideoNoYesNo
ReasoningNoYesYes
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenApache-2.0Open
API model IDcodestral-2508—glm-4.5-air
API providers11119 (best)
ReleasedJul 30, 2025Sep 22, 2025Jul 28, 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
  • Qwen3 Omni 30B A3B Thinking$4.44
  • GLM-4.5-Air$4.20
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, Qwen3 Omni 30B A3B Thinking or GLM-4.5-Air?

Qwen3 Omni 30B A3B Thinking is the better all-round choice, scoring 59/100 against GLM-4.5-Air (48) and Codestral 25.08 (47). It leads on inputs & features. 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 25.08, Qwen3 Omni 30B A3B Thinking or GLM-4.5-Air?

GLM-4.5-Air is cheaper at $0.20 input / $1.10 output per million tokens (official Z.AI API price). Qwen3 Omni 30B A3B Thinking costs $0.25 input / $0.97 output per million tokens (median across 1 API provider); 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 $0.425 per million tokens for GLM-4.5-Air versus $0.43 for Qwen3 Omni 30B A3B Thinking (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. Codestral 25.08 has not been scored yet, Qwen3 Omni 30B A3B Thinking has not been scored yet and GLM-4.5-Air has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral 25.08, Qwen3 Omni 30B A3B Thinking and GLM-4.5-Air 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?

GLM-4.5-Air has the largest context window at 131,072 tokens, against 128,000 for Codestral 25.08 and 65,536 for Qwen3 Omni 30B A3B Thinking. Maximum output per response: Codestral 25.08 up to 8,192, Qwen3 Omni 30B A3B Thinking up to 16,384, GLM-4.5-Air up to 98,304 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; Qwen3 Omni 30B A3B Thinking accepts text, images, audio and video; GLM-4.5-Air accepts text. Qwen3 Omni 30B A3B Thinking handles the widest range of inputs.

Are any of these open source?

Qwen3 Omni 30B A3B Thinking and GLM-4.5-Air publishes its weights (Apache-2.0) and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Qwen3 Omni 30B A3B Thinking is the newest, released Sep 22, 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?

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 Nov 2, 2026.

05 — Keep comparing

Related comparisons