ZMIME
Comparison · 3 models · Updated Nov 18, 2026

ERNIE 4.5 21B A3B vs GLM-4.5V vs Mistral Medium 3.1

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. Baidu

    ERNIE 4.5 21B A3B

    Released Jun 30, 2025

    59/100
    • ECI—
    • Price$0.07 / $0.28
    • Context131K
  2. Z.ai (Zhipu)

    GLM-4.5V

    Released Aug 11, 2025

    50/100
    • ECI—
    • Price$0.60 / $1.80
    • Context64K
  3. Mistral AI

    Mistral Medium 3.1

    Released Aug 12, 2025

    50/100
    • ECI—
    • Price$0.44 / $2.20
    • Context131K
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 59/100, GLM-4.5V 50/100, Mistral Medium 3.1 50/100) 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 priceERNIE 4.5 21B A3BERNIE 4.5 21B A3B $0.122 · Mistral Medium 3.1 $0.88 · GLM-4.5V $0.90 per 1M tokens (3:1 blend)
  • Longest contextERNIE 4.5 21B A3B and Mistral Medium 3.1ERNIE 4.5 21B A3B 131,072 · Mistral Medium 3.1 131,072 · GLM-4.5V 64,000 tokens
  • Widest inputsGLM-4.5V and Mistral Medium 3.1ERNIE 4.5 21B A3B: Text · GLM-4.5V: Text, Images, Video · Mistral Medium 3.1: Text, Images, PDFs
  • Self-hostingERNIE 4.5 21B A3B and GLM-4.5VPublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeightERNIE 4.5 21B A3BGLM-4.5VMistral Medium 3.1
Price50%895050
Inputs & features30%257060
Context window20%322132
Specs & price only100%59/10050/10050/100

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.

ERNIE 4.5 21B A3B vs GLM-4.5V vs Mistral Medium 3.1 specifications side by side
SpecificationERNIE 4.5 21B A3BBaiduGLM-4.5VZ.ai (Zhipu)Mistral Medium 3.1Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.07 (best)$0.60$0.44
Output$0.28 (best)$1.80$2.20
Cached input—$0.11—
Blended (3:1)$0.122 (best)$0.90$0.88
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Z.AI APIMedian of 4 providers
Limits
Context window131,072 tokens (best)64,000 tokens131,072 tokens (best)
Max output8,000 tokens16,384 tokens104,857 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoYes
AudioNoNoNo
VideoNoYesNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsOpenApache-2.0OpenProprietary
API model ID—glm-4.5v—
API providers116 (best)4
ReleasedJun 30, 2025Aug 11, 2025Aug 12, 2025
Knowledge cutoff—Apr 2025Jun 30, 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.

  • ERNIE 4.5 21B A3B$1.26
  • GLM-4.5V$9.60
  • Mistral Medium 3.1$8.80
04 — Questions

Which should you choose?

Which is better: ERNIE 4.5 21B A3B, GLM-4.5V or Mistral Medium 3.1?

There is not enough shared capability evidence to name an overall winner. The scores (ERNIE 4.5 21B A3B 59/100, GLM-4.5V 50/100, Mistral Medium 3.1 50/100) 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, ERNIE 4.5 21B A3B, GLM-4.5V or Mistral Medium 3.1?

ERNIE 4.5 21B A3B is cheaper at $0.07 input / $0.28 output per million tokens (median across 1 API provider). Mistral Medium 3.1 costs $0.44 input / $2.20 output per million tokens (median across 4 API providers); GLM-4.5V costs $0.60 input / $1.80 output per million tokens (official Z.AI API price). 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 $0.88 for Mistral Medium 3.1 (7.2× as much) and $0.90 for GLM-4.5V (7.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. ERNIE 4.5 21B A3B has not been scored yet, GLM-4.5V has not been scored yet and Mistral Medium 3.1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for ERNIE 4.5 21B A3B, GLM-4.5V and Mistral Medium 3.1 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?

ERNIE 4.5 21B A3B and Mistral Medium 3.1 have the largest context windows (131,072 and 131,072 tokens), against 64,000 for GLM-4.5V. Maximum output per response: ERNIE 4.5 21B A3B up to 8,000, GLM-4.5V up to 16,384, Mistral Medium 3.1 up to 104,857 tokens.

Which can read images, PDFs, audio or video?

ERNIE 4.5 21B A3B accepts text; GLM-4.5V accepts text, images and video; Mistral Medium 3.1 accepts text, images and PDFs. GLM-4.5V handles the widest range of inputs.

Are any of these open source?

ERNIE 4.5 21B A3B and GLM-4.5V publishes its weights (Apache-2.0) and can be self-hosted; Mistral Medium 3.1 is proprietary.

Which is newer?

Mistral Medium 3.1 is the newest, released Aug 12, 2025. GLM-4.5V came out Aug 11, 2025; ERNIE 4.5 21B A3B came out Jun 30, 2025. Knowledge cutoff: GLM-4.5V Apr 2025, Mistral Medium 3.1 Jun 30, 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.