ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Aya Expanse 32B vs Qwen Plus Character (Japanese) vs Sonar

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. Cohere

    Aya Expanse 32B

    Released Oct 24, 2024

    33/100
    • ECI—
    • Price$0.50 / $1.50
    • Context128K
  2. Alibaba (Qwen)

    Qwen Plus Character (Japanese)

    Released Jan 2024

    27/100
    • ECI—
    • Price$0.50 / $1.40
    • Context8K
  3. Perplexity

    Sonar

    Released Jan 1, 2024Deprecated

    30/100
    • ECI—
    • Price$1.00 / $1.00
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Aya Expanse 32B 33/100, Sonar 30/100, Qwen Plus Character (Japanese) 27/100) 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 priceQwen Plus Character (Japanese)Qwen Plus Character (Japanese) $0.725 · Aya Expanse 32B $0.75 · Sonar $1.00 per 1M tokens (3:1 blend)
  • Longest contextAya Expanse 32B and SonarAya Expanse 32B 128,000 · Sonar 128,000 · Qwen Plus Character (Japanese) 8,192 tokens
  • Widest inputsSame inputsAya Expanse 32B: Text · Qwen Plus Character (Japanese): Text · Sonar: Text
  • Self-hostingAya Expanse 32BPublishes downloadable weights (CC-BY-NC-4.0)
How the score is built
MeasureWeightAya Expanse 32BQwen Plus Character (Japanese)Sonar
Price50%535448
Inputs & features30%000
Context window20%32032
Specs & price only100%33/10027/10030/100

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.

Aya Expanse 32B vs Qwen Plus Character (Japanese) vs Sonar specifications side by side
SpecificationAya Expanse 32BCohereQwen Plus Character (Japanese)Alibaba (Qwen)SonarPerplexity
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.50 (best)$0.50 (best)$1.00
Output$1.50$1.40$1.00 (best)
Cached input———
Blended (3:1)$0.75$0.725 (best)$1.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIOfficial Alibaba APIOfficial Perplexity API
Limits
Context window128,000 tokens (best)8,192 tokens128,000 tokens (best)
Max output4,000 tokens512 tokens4,096 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoNoNo
Structured outputNoNoNo
Availability
WeightsOpenCC-BY-NC-4.0ProprietaryProprietary
API model IDc4ai-aya-expanse-32bqwen-plus-character-jasonar
API providers219 (best)
ReleasedOct 24, 2024Jan 2024Jan 1, 2024
Knowledge cutoff—Apr 2024Sep 1, 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.

  • Aya Expanse 32B$8.00
  • Qwen Plus Character (Japanese)$7.80
  • Sonar$12.00
04 — Questions

Which should you choose?

Which is better: Aya Expanse 32B, Qwen Plus Character (Japanese) or Sonar?

There is not enough shared capability evidence to name an overall winner. The scores (Aya Expanse 32B 33/100, Sonar 30/100, Qwen Plus Character (Japanese) 27/100) 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, Aya Expanse 32B, Qwen Plus Character (Japanese) or Sonar?

Qwen Plus Character (Japanese) is cheaper at $0.50 input / $1.40 output per million tokens (official Alibaba API price). Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price); Sonar costs $1.00 input / $1.00 output per million tokens (official Perplexity API price). At a typical mix of three input tokens to one output token, that is $0.725 per million tokens for Qwen Plus Character (Japanese) versus $0.75 for Aya Expanse 32B (1× as much) and $1.00 for Sonar (1.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Qwen Plus Character (Japanese) has not been scored yet and Sonar has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Aya Expanse 32B, Qwen Plus Character (Japanese) and Sonar yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B, Qwen Plus Character (Japanese) and Sonar does not support tool calling, which most coding agents need.

Which has the bigger context window?

Aya Expanse 32B and Sonar have the largest context windows (128,000 and 128,000 tokens), against 8,192 for Qwen Plus Character (Japanese). Maximum output per response: Aya Expanse 32B up to 4,000, Qwen Plus Character (Japanese) up to 512, Sonar up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Aya Expanse 32B accepts text; Qwen Plus Character (Japanese) accepts text; Sonar accepts text. They handle the same number of input types.

Are any of these open source?

Aya Expanse 32B publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Qwen Plus Character (Japanese) and Sonar is proprietary.

Which is newer?

Aya Expanse 32B is the newest, released Oct 24, 2024. Qwen Plus Character (Japanese) came out Jan 2024; Sonar came out Jan 1, 2024. Knowledge cutoff: Qwen Plus Character (Japanese) Apr 2024, Sonar Sep 1, 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.