ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Vision Large vs SOLAR 10.7B Instruct v1.0 vs Codestral-22B-v0.1

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

Price in rating: Included · Exclude price

  1. Vispark

    Vision Large

    Released May 15, 2024

    86/100
    • ECI—
    • Price$7.37 / $22.11
    • Context1M
  2. Upstage

    SOLAR 10.7B Instruct v1.0

    Released Dec 12, 2023

    0/100
    • ECI—
    • Price—
    • Context4K
  3. Mistral AI

    Codestral-22B-v0.1

    Released May 29, 2024

    4/100
    • ECI—
    • Price—
    • Context33K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 86/100, Codestral-22B-v0.1 4/100, SOLAR 10.7B Instruct v1.0 0/100) compare the available specifications and price. 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 priceVision LargeVision Large $11.05 per 1M tokens (3:1 blend) · SOLAR 10.7B Instruct v1.0 and Codestral-22B-v0.1 unpriced
  • Longest contextVision LargeVision Large 1,000,000 · Codestral-22B-v0.1 32,768 · SOLAR 10.7B Instruct v1.0 4,096 tokens
  • Widest inputsVision LargeVision Large: Text, Images, PDFs, Audio, Video · SOLAR 10.7B Instruct v1.0: Text · Codestral-22B-v0.1: Text
  • Self-hostingSOLAR 10.7B Instruct v1.0 and Codestral-22B-v0.1Publishes downloadable weights (CC-BY-NC-4.0 and Mistral AI Non-Production License)
How the score is built
MeasureWeightVision LargeSOLAR 10.7B Instruct v1.0Codestral-22B-v0.1
Inputs & features60%10000
Context window40%64011
Specs & price only100%86/1000/1004/100

Left out because at least one model lacks the data: capability and price. 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.

Vision Large vs SOLAR 10.7B Instruct v1.0 vs Codestral-22B-v0.1 specifications side by side
SpecificationVision LargeVisparkSOLAR 10.7B Instruct v1.0UpstageCodestral-22B-v0.1Mistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$7.37——
Output$22.11——
Cached input———
Blended (3:1)$11.05——
Long-context rateSame rate——
Price sourceOfficial Vispark API——
Limits
Context window1,000,000 tokens (best)4,096 tokens32,768 tokens
Max output65,536 tokens (best)4,096 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioYesNoNo
VideoYesNoNo
ReasoningYesNoNo
Tool callingYesNoNo
Structured outputYesNoNo
Availability
WeightsProprietaryOpenCC-BY-NC-4.0OpenMistral AI Non-Production License
API model IDvispark/vision-large——
API providers1——
ReleasedMay 15, 2024Dec 12, 2023May 29, 2024
Knowledge cutoff———
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.

  • Vision Large$117.92
  • SOLAR 10.7B Instruct v1.0—
  • Codestral-22B-v0.1—
04 — Questions

Which should you choose?

Which is better: Vision Large, SOLAR 10.7B Instruct v1.0 or Codestral-22B-v0.1?

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 86/100, Codestral-22B-v0.1 4/100, SOLAR 10.7B Instruct v1.0 0/100) compare the available specifications and price. 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, Vision Large, SOLAR 10.7B Instruct v1.0 or Codestral-22B-v0.1?

Vision Large is cheaper at $7.37 input / $22.11 output per million tokens (official Vispark API price). . At a typical mix of three input tokens to one output token, that is $11.05 per million tokens for Vision Large versus . SOLAR 10.7B Instruct v1.0 and Codestral-22B-v0.1 has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Vision Large has not been scored yet, SOLAR 10.7B Instruct v1.0 has not been scored yet and Codestral-22B-v0.1 has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Vision Large, SOLAR 10.7B Instruct v1.0 and Codestral-22B-v0.1 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that SOLAR 10.7B Instruct v1.0 and Codestral-22B-v0.1 does not support tool calling, which most coding agents need.

Which has the bigger context window?

Vision Large has the largest context window at 1,000,000 tokens, against 32,768 for Codestral-22B-v0.1 and 4,096 for SOLAR 10.7B Instruct v1.0. Maximum output per response: Vision Large up to 65,536, SOLAR 10.7B Instruct v1.0 up to 4,096, Codestral-22B-v0.1 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Vision Large accepts text, images, PDFs, audio and video; SOLAR 10.7B Instruct v1.0 accepts text; Codestral-22B-v0.1 accepts text. Vision Large handles the widest range of inputs.

Are any of these open source?

SOLAR 10.7B Instruct v1.0 and Codestral-22B-v0.1 publishes its weights (CC-BY-NC-4.0 and Mistral AI Non-Production License) and can be self-hosted; Vision Large is proprietary.

Which is newer?

Codestral-22B-v0.1 is the newest, released May 29, 2024. Vision Large came out May 15, 2024; SOLAR 10.7B Instruct v1.0 came out Dec 12, 2023.

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.