ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Sonar Pro vs Vision Medium vs Vision 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. Perplexity

    Sonar Pro

    Released Jan 1, 2024Deprecated

    22/100
    • ECI—
    • Price$3.00 / $15.00
    • Context200K
  2. Vispark

    Vision Medium

    Released May 15, 2024

    49/100
    • ECI—
    • Price$4.21 / $12.63
    • Context1M
  3. Vispark

    Vision Small

    Released May 15, 2024

    62/100
    • ECI—
    • Price$1.05 / $3.16
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Vision Small 62/100, Vision Medium 49/100, Sonar Pro 22/100) 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 priceVision SmallVision Small $1.58 · Sonar Pro $6.00 · Vision Medium $6.32 per 1M tokens (3:1 blend)
  • Longest contextVision Medium and Vision SmallVision Medium 1,000,000 · Vision Small 1,000,000 · Sonar Pro 200,000 tokens
  • Widest inputsVision Medium and Vision SmallSonar Pro: Text, Images · Vision Medium: Text, Images, PDFs, Audio, Video · Vision Small: Text, Images, PDFs, Audio, Video
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeightSonar ProVision MediumVision Small
Price50%121139
Inputs & features30%25100100
Context window20%396464
Specs & price only100%22/10049/10062/100

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.

Sonar Pro vs Vision Medium vs Vision Small specifications side by side
SpecificationSonar ProPerplexityVision MediumVisparkVision SmallVispark
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$3.00$4.21$1.05 (best)
Output$15.00$12.63$3.16 (best)
Cached input———
Blended (3:1)$6.00$6.32$1.58 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Perplexity APIOfficial Vispark APIOfficial Vispark API
Limits
Context window200,000 tokens1,000,000 tokens (best)1,000,000 tokens (best)
Max output8,192 tokens65,536 tokens (best)65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsNoYesYes
AudioNoYesYes
VideoNoYesYes
ReasoningNoYesYes
Tool callingNoYesYes
Structured outputNoYesYes
Availability
WeightsProprietaryProprietaryProprietary
API model IDsonar-provispark/vision-mediumvispark/vision-small
API providers7 (best)11
ReleasedJan 1, 2024May 15, 2024May 15, 2024
Knowledge cutoffSep 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.

  • Sonar Pro$60.00
  • Vision Medium$67.36
  • Vision Small$16.82
04 — Questions

Which should you choose?

Which is better: Sonar Pro, Vision Medium or Vision Small?

There is not enough shared capability evidence to name an overall winner. The scores (Vision Small 62/100, Vision Medium 49/100, Sonar Pro 22/100) 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, Sonar Pro, Vision Medium or Vision Small?

Vision Small is cheaper at $1.05 input / $3.16 output per million tokens (official Vispark API price). Sonar Pro costs $3.00 input / $15.00 output per million tokens (official Perplexity API price); Vision Medium costs $4.21 input / $12.63 output per million tokens (official Vispark API price). At a typical mix of three input tokens to one output token, that is $1.58 per million tokens for Vision Small versus $6.00 for Sonar Pro (3.8× as much) and $6.32 for Vision Medium (4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Sonar Pro has not been scored yet, Vision Medium has not been scored yet and Vision Small has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Sonar Pro, Vision Medium and Vision Small yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sonar Pro does not support tool calling, which most coding agents need.

Which has the bigger context window?

Vision Medium and Vision Small have the largest context windows (1,000,000 and 1,000,000 tokens), against 200,000 for Sonar Pro. Maximum output per response: Sonar Pro up to 8,192, Vision Medium up to 65,536, Vision Small up to 65,536 tokens.

Which can read images, PDFs, audio or video?

Sonar Pro accepts text and images; Vision Medium accepts text, images, PDFs, audio and video; Vision Small accepts text, images, PDFs, audio and video. Vision Medium handles the widest range of inputs.

Are any of these open source?

No. Sonar Pro, Vision Medium and Vision Small are proprietary and only available through APIs and apps.

Which is newer?

Vision Medium is the newest, released May 15, 2024. Vision Small came out May 15, 2024; Sonar Pro came out Jan 1, 2024. Knowledge cutoff: Sonar Pro 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.