ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Apertus 8B vs Codestral 25.08 vs Granite-4.0-H-Small

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

Price in rating: Included · Exclude price

  1. Swiss AI

    Apertus 8B

    Released Sep 2, 2025

    56/100
    • ECI—
    • Price$0.10 / $0.20
    • Context66K
  2. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  3. IBM

    Granite-4.0-H-Small

    Released Oct 2, 2025

    62/100
    • ECI—
    • Price$0.064 / $0.265
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Small 62/100, Apertus 8B 56/100, Codestral 25.08 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 priceGranite-4.0-H-SmallGranite-4.0-H-Small $0.114 · Apertus 8B $0.125 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextGranite-4.0-H-SmallGranite-4.0-H-Small 131,072 · Codestral 25.08 128,000 · Apertus 8B 65,536 tokens
  • Widest inputsSame inputsApertus 8B: Text · Codestral 25.08: Text · Granite-4.0-H-Small: Text
  • Self-hostingApertus 8B and Granite-4.0-H-SmallPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightApertus 8BCodestral 25.08Granite-4.0-H-Small
Price50%896391
Inputs & features30%253535
Context window20%223232
Specs & price only100%56/10049/10062/100

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.

Apertus 8B vs Codestral 25.08 vs Granite-4.0-H-Small specifications side by side
SpecificationApertus 8BSwiss AICodestral 25.08Mistral AIGranite-4.0-H-SmallIBM
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.10$0.30$0.064 (best)
Output$0.20 (best)$0.90$0.265
Cached input—$0.03—
Blended (3:1)$0.125$0.45$0.114 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Mistral APIOfficial watsonx.ai API
Limits
Context window65,536 tokens128,000 tokens131,072 tokens (best)
Max output8,192 tokens8,192 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsOpenApache-2.0ProprietaryOpen
API model ID—codestral-2508ibm/granite-4-h-small
API providers111 (best)1
ReleasedSep 2, 2025Jul 30, 2025Oct 2, 2025
Knowledge cutoffSep 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.

  • Apertus 8B$1.40
  • Codestral 25.08$4.80
  • Granite-4.0-H-Small$1.17
04 — Questions

Which should you choose?

Which is better: Apertus 8B, Codestral 25.08 or Granite-4.0-H-Small?

There is not enough shared capability evidence to name an overall winner. The scores (Granite-4.0-H-Small 62/100, Apertus 8B 56/100, Codestral 25.08 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, Apertus 8B, Codestral 25.08 or Granite-4.0-H-Small?

Granite-4.0-H-Small is cheaper at $0.064 input / $0.265 output per million tokens (official watsonx.ai API price). Apertus 8B costs $0.10 input / $0.20 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 $0.114 per million tokens for Granite-4.0-H-Small versus $0.125 for Apertus 8B (1.1× as much) and $0.45 for Codestral 25.08 (3.9× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Apertus 8B has not been scored yet, Codestral 25.08 has not been scored yet and Granite-4.0-H-Small has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Apertus 8B, Codestral 25.08 and Granite-4.0-H-Small 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?

Granite-4.0-H-Small has the largest context window at 131,072 tokens, against 128,000 for Codestral 25.08 and 65,536 for Apertus 8B. Maximum output per response: Apertus 8B up to 8,192, Codestral 25.08 up to 8,192, Granite-4.0-H-Small up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Apertus 8B accepts text; Codestral 25.08 accepts text; Granite-4.0-H-Small accepts text. They handle the same number of input types.

Are any of these open source?

Apertus 8B and Granite-4.0-H-Small publishes its weights (Apache-2.0) and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Granite-4.0-H-Small is the newest, released Oct 2, 2025. Apertus 8B came out Sep 2, 2025; Codestral 25.08 came out Jul 30, 2025. Knowledge cutoff: Apertus 8B Sep 2025.

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.