ZMIME
Comparison · 3 models · Updated Nov 22, 2026

Codestral 25.08 vs GLM-4.5-Air vs Seed 1.6

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

  1. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025Latest

    54/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  2. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    55/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  3. ByteDance Seed

    Seed 1.6

    Released Oct 15, 2025Deprecated

    60/100
    • ECI—
    • Price$0.119 / $1.19
    • Context256K
  4. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025Latest

    32/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  5. Z.ai (Zhipu)

    GLM-4.5-Air

    Released Jul 28, 2025

    32/100
    • ECI—
    • Price$0.20 / $1.10
    • Context131K
  6. ByteDance Seed

    Seed 1.6

    Released Oct 15, 2025Deprecated

    43/100
    • ECI—
    • Price$0.119 / $1.19
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Seed 1.6 60/100, GLM-4.5-Air 55/100, Codestral 25.08 54/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Seed 1.6 43/100, GLM-4.5-Air 32/100, Codestral 25.08 32/100) compare the available specifications only. The score weighs context window 100%. 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 priceSeed 1.6Seed 1.6 $0.386 · GLM-4.5-Air $0.425 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextSeed 1.6Seed 1.6 256,000 · GLM-4.5-Air 131,072 · Codestral 25.08 128,000 tokens
  • Widest inputsSeed 1.6Codestral 25.08: Text · GLM-4.5-Air: Text · Seed 1.6: Text, Images, Video
  • Self-hostingGLM-4.5-AirPublishes downloadable weights
How the score is built
MeasureWeightCodestral 25.08GLM-4.5-AirSeed 1.6
Price71%636566
Context window29%323243
Specs & price only100%54/10055/10060/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

How the score is built
MeasureWeightCodestral 25.08GLM-4.5-AirSeed 1.6
Context window100%323243
Specs only100%32/10032/10043/100

Left out because at least one model lacks the data: capability and inputs & features. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.

Codestral 25.08 vs GLM-4.5-Air vs Seed 1.6 specifications side by side
SpecificationCodestral 25.08Mistral AIGLM-4.5-AirZ.ai (Zhipu)Seed 1.6ByteDance Seed
Capability
Capabilities Index (ECI)Not publishedNot publishedNot published
ECI rankNot publishedNot publishedNot published
ECI confidence intervalNot publishedNot publishedNot published
ECI evaluation dateNot publishedNot publishedNot published
Documented capabilitiesMistral code model for low-latency completion, fill-in-the-middle, and code generationLighter GLM-4.5 variant for fast coding assistance and cheaper agentsByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks
Model parametersNot publishedNot publishedNot published
Output modalitiesTextTextText
Publisher-reported benchmarks
Artificial Analysis Coding IndexPublisher-reported resultNot published23.8indexReported resultMay 30, 2026Not published
SciCodePublisher-reported resultNot published30.6percent correctReported resultMay 30, 2026Not published
Terminal-Bench HardPublisher-reported resultNot published20.5success rateReported resultMay 30, 2026Not published
Price per million tokens
Input$0.30$0.20$0.119 (best)
Output$0.90 (best)$1.10$1.19
Cached input$0.03$0.03$0.024 (best)
Blended (3:1)$0.45$0.425$0.386 (best)
Long-context rateSame rateSame rateOver 32K: $0.178 / $2.37
Price sourceOfficial Mistral APIOfficial Z.AI APIOfficial Volcengine Ark API
Limits
Context window128,000 tokens131,072 tokens256,000 tokens (best)
Max inputNot publishedNot publishedNot published
Max output8,192 tokens98,304 tokens (best)64,000 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningNoYesYesminimal · low · medium · high
Tool callingYesYesYes
Structured outputYesNot publishedYes
File attachmentsYesNoYes
Temperature controlYesYesYes
Reasoning controlNot publishedtoggleeffort
Availability
WeightsProprietaryOpenProprietary
API model IDcodestral-2508glm-4.5-airdoubao-seed-1-6-251015
API providers1118 (best)2
ReleasedJul 30, 2025Jul 28, 2025Oct 15, 2025
Knowledge cutoffNot publishedApr 2025Not published
Publisher documentationPublisher documentationPublisher documentation · Model weightsPublisher documentation
Source metadata updatedJul 30, 2025Jul 28, 2025Oct 15, 2025
Data sourcesmodels.dev · Epoch AImodels.dev · Epoch AImodels.dev · Epoch AI
Catalog checkedNov 22, 2026Nov 22, 2026Nov 22, 2026
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
  • Seed 1.6$3.56
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, GLM-4.5-Air or Seed 1.6?

There is not enough shared capability evidence to name an overall winner. The scores (Seed 1.6 60/100, GLM-4.5-Air 55/100, Codestral 25.08 54/100) compare the available specifications and price. The score weighs price 71%, context window 29%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.There is not enough shared capability evidence to name an overall winner. The scores (Seed 1.6 43/100, GLM-4.5-Air 32/100, Codestral 25.08 32/100) compare the available specifications only. The score weighs context window 100%. 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 Seed 1.6?

Seed 1.6 is cheaper at $0.119 input / $1.19 output per million tokens (official Volcengine Ark API price). 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 $0.386 per million tokens for Seed 1.6 versus $0.425 for GLM-4.5-Air (1.1× as much) and $0.45 for Codestral 25.08 (1.2× 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 Seed 1.6 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 Seed 1.6 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?

Seed 1.6 has the largest context window at 256,000 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, GLM-4.5-Air up to 98,304, Seed 1.6 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; GLM-4.5-Air accepts text; Seed 1.6 accepts text, images and video. Seed 1.6 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 Seed 1.6 is proprietary.

Which is newer?

Seed 1.6 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 price (71%, blended price per million tokens (3 input : 1 output), log scale); context window (29%, 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 22, 2026.This rating uses context window (100%, 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 22, 2026.