ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Devstral Small vs ERNIE 4.5 21B A3B vs Morph V3 Fast

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

Price in rating: Excluded · Include price

  1. Mistral AI

    Devstral Small

    Released Jul 10, 2025

    28/100
    • ECI—
    • Price—
    • Context128K
  2. Baidu

    ERNIE 4.5 21B A3B

    Released Jun 30, 2025

    28/100
    • ECI—
    • Price$0.07 / $0.28
    • Context131K
  3. Morph

    Morph V3 Fast

    Released Jul 7, 2025

    17/100
    • ECI—
    • Price$0.80 / $1.20
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (ERNIE 4.5 21B A3B 28/100, Devstral Small 28/100, Morph V3 Fast 17/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceERNIE 4.5 21B A3BERNIE 4.5 21B A3B $0.122 · Morph V3 Fast $0.90 per 1M tokens (3:1 blend) · Devstral Small unpriced
  • Longest contextMorph V3 FastMorph V3 Fast 262,144 · ERNIE 4.5 21B A3B 131,072 · Devstral Small 128,000 tokens
  • Widest inputsSame inputsDevstral Small: Text · ERNIE 4.5 21B A3B: Text · Morph V3 Fast: Text
  • Self-hostingDevstral Small and ERNIE 4.5 21B A3BPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightDevstral SmallERNIE 4.5 21B A3BMorph V3 Fast
Inputs & features60%25250
Context window40%323243
Specs only100%28/10028/10017/100

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.

Devstral Small vs ERNIE 4.5 21B A3B vs Morph V3 Fast specifications side by side
SpecificationDevstral SmallMistral AIERNIE 4.5 21B A3BBaiduMorph V3 FastMorph
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input—$0.07 (best)$0.80
Output—$0.28 (best)$1.20
Cached input———
Blended (3:1)—$0.122 (best)$0.90
Long-context rate—Same rateSame rate
Price source—Median of 1 providersMedian of 5 providers
Limits
Context window128,000 tokens131,072 tokens262,144 tokens (best)
Max output128,000 tokens8,000 tokens131,072 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsOpenOpenApache-2.0Proprietary
API model ID———
API providers—15 (best)
ReleasedJul 10, 2025Jun 30, 2025Jul 7, 2025
Knowledge cutoffMay 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.

  • Devstral Small—
  • ERNIE 4.5 21B A3B$1.26
  • Morph V3 Fast$10.40
04 — Questions

Which should you choose?

Which is better: Devstral Small, ERNIE 4.5 21B A3B or Morph V3 Fast?

There is not enough shared capability evidence to name an overall winner. The scores (ERNIE 4.5 21B A3B 28/100, Devstral Small 28/100, Morph V3 Fast 17/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Devstral Small, ERNIE 4.5 21B A3B or Morph V3 Fast?

ERNIE 4.5 21B A3B is cheaper at $0.07 input / $0.28 output per million tokens (median across 1 API provider). Morph V3 Fast costs $0.80 input / $1.20 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.122 per million tokens for ERNIE 4.5 21B A3B versus $0.90 for Morph V3 Fast (7.3× as much). Devstral Small has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Devstral Small has not been scored yet, ERNIE 4.5 21B A3B has not been scored yet and Morph V3 Fast has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Devstral Small, ERNIE 4.5 21B A3B and Morph V3 Fast yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Morph V3 Fast does not support tool calling, which most coding agents need.

Which has the bigger context window?

Morph V3 Fast has the largest context window at 262,144 tokens, against 131,072 for ERNIE 4.5 21B A3B and 128,000 for Devstral Small. Maximum output per response: Devstral Small up to 128,000, ERNIE 4.5 21B A3B up to 8,000, Morph V3 Fast up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Devstral Small accepts text; ERNIE 4.5 21B A3B accepts text; Morph V3 Fast accepts text. They handle the same number of input types.

Are any of these open source?

Devstral Small and ERNIE 4.5 21B A3B publishes its weights (Apache-2.0) and can be self-hosted; Morph V3 Fast is proprietary.

Which is newer?

Devstral Small is the newest, released Jul 10, 2025. Morph V3 Fast came out Jul 7, 2025; ERNIE 4.5 21B A3B came out Jun 30, 2025. Knowledge cutoff: Devstral Small May 2025.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.