ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Codestral 25.08 vs Qwen3 Coder Flash vs GLM-4.5-Air

Qwen3 Coder Flash comes out ahead, 51 to 48 and 47 on our weighted score, though GLM-4.5-Air is 29% cheaper per token.

  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 Coder Flash

    Released Jul 28, 2025

    51/100
    • ECI—
    • Price$0.30 / $1.50
    • Context1M
    Full specs Remove Qwen3 Coder Flash

  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 Coder Flash is our pick

Qwen3 Coder Flash is the better all-round choice, scoring 51/100 against GLM-4.5-Air (48) and Codestral 25.08 (47). It leads on context window. 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 · Qwen3 Coder Flash $0.60 per 1M tokens (3:1 blend)
  • Longest contextQwen3 Coder FlashQwen3 Coder Flash 1,000,000 · GLM-4.5-Air 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputsSame inputsCodestral 25.08: Text · Qwen3 Coder Flash: Text · GLM-4.5-Air: Text
  • Self-hostingGLM-4.5-AirPublishes downloadable weights
How the score is built
MeasureWeightCodestral 25.08Qwen3 Coder FlashGLM-4.5-Air
Price50%645865
Inputs & features30%353535
Context window20%246025
Overall100%47/10051/10048/100

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 Coder Flash vs GLM-4.5-Air specifications side by side
SpecificationCodestral 25.08Mistral AIQwen3 Coder FlashAlibaba (Qwen)GLM-4.5-AirZ.ai (Zhipu)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.30$0.20 (best)
Output$0.90 (best)$1.50$1.10
Cached input$0.03 (best)$0.06$0.03 (best)
Blended (3:1)$0.45$0.60$0.425 (best)
Long-context rateSame rateOver 32K: $0.50 / $2.50Same rate
Price sourceOfficial Mistral APIOfficial Alibaba APIOfficial Z.AI API
Limits
Context window128,000 tokens1,000,000 tokens (best)131,072 tokens
Max output8,192 tokens65,536 tokens98,304 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpen
API model IDcodestral-2508qwen3-coder-flashglm-4.5-air
API providers111019 (best)
ReleasedJul 30, 2025Jul 28, 2025Jul 28, 2025
Knowledge cutoff—Apr 2025Apr 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 Coder Flash$6.00
  • GLM-4.5-Air$4.20
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, Qwen3 Coder Flash or GLM-4.5-Air?

Qwen3 Coder Flash is the better all-round choice, scoring 51/100 against GLM-4.5-Air (48) and Codestral 25.08 (47). It leads on context window. 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 Coder Flash 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). Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Qwen3 Coder Flash costs $0.30 input / $1.50 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 25.08 (1.1× as much) and $0.60 for Qwen3 Coder Flash (1.4× 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, Qwen3 Coder Flash 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 Coder Flash 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?

Qwen3 Coder Flash has the largest context window at 1,000,000 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, Qwen3 Coder Flash up to 65,536, GLM-4.5-Air up to 98,304 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; Qwen3 Coder Flash accepts text; GLM-4.5-Air accepts text. They handle the same number of input types.

Are any of these open source?

GLM-4.5-Air publishes its weights and can be self-hosted; Codestral 25.08 and Qwen3 Coder Flash is proprietary.

Which is newer?

Codestral 25.08 is the newest, released Jul 30, 2025. Qwen3 Coder Flash came out Jul 28, 2025; GLM-4.5-Air came out Jul 28, 2025. Knowledge cutoff: Qwen3 Coder Flash Apr 2025, 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