ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4 Turbo vs Codestral-22B-v0.1 vs Vision Large

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

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-4 Turbo

    Released Nov 6, 2023Deprecated

    43/100
    • ECI—
    • Price$10.00 / $30.00
    • Context128K
  2. Mistral AI

    Codestral-22B-v0.1

    Released May 29, 2024

    4/100
    • ECI—
    • Price—
    • Context33K
  3. Vispark

    Vision Large

    Released May 15, 2024

    86/100
    • ECI—
    • Price$7.37 / $22.11
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 86/100, GPT-4 Turbo 43/100, Codestral-22B-v0.1 4/100) 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 · GPT-4 Turbo $15.00 per 1M tokens (3:1 blend) · Codestral-22B-v0.1 unpriced
  • Longest contextVision LargeVision Large 1,000,000 · GPT-4 Turbo 128,000 · Codestral-22B-v0.1 32,768 tokens
  • Widest inputsVision LargeGPT-4 Turbo: Text, Images · Codestral-22B-v0.1: Text · Vision Large: Text, Images, PDFs, Audio, Video
  • Self-hostingCodestral-22B-v0.1Publishes downloadable weights (Mistral AI Non-Production License)
How the score is built
MeasureWeightGPT-4 TurboCodestral-22B-v0.1Vision Large
Inputs & features60%500100
Context window40%321164
Specs & price only100%43/1004/10086/100

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.

GPT-4 Turbo vs Codestral-22B-v0.1 vs Vision Large specifications side by side
SpecificationGPT-4 TurboOpenAICodestral-22B-v0.1Mistral AIVision LargeVispark
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$10.00—$7.37 (best)
Output$30.00—$22.11 (best)
Cached input———
Blended (3:1)$15.00—$11.05 (best)
Long-context rateSame rate—Same rate
Price sourceOfficial OpenAI API—Official Vispark API
Limits
Context window128,000 tokens32,768 tokens1,000,000 tokens (best)
Max output4,096 tokens8,192 tokens65,536 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsNoNoYes
AudioNoNoYes
VideoNoNoYes
ReasoningNoNoYes
Tool callingYesNoYes
Structured outputNoNoYes
Availability
WeightsProprietaryOpenMistral AI Non-Production LicenseProprietary
API model IDgpt-4-turbo—vispark/vision-large
API providers7 (best)—1
ReleasedNov 6, 2023May 29, 2024May 15, 2024
Knowledge cutoffDec 2023——
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.

  • GPT-4 Turbo$160.00
  • Codestral-22B-v0.1—
  • Vision Large$117.92
04 — Questions

Which should you choose?

Which is better: GPT-4 Turbo, Codestral-22B-v0.1 or Vision Large?

There is not enough shared capability evidence to name an overall winner. The scores (Vision Large 86/100, GPT-4 Turbo 43/100, Codestral-22B-v0.1 4/100) 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, GPT-4 Turbo, Codestral-22B-v0.1 or Vision Large?

Vision Large is cheaper at $7.37 input / $22.11 output per million tokens (official Vispark API price). GPT-4 Turbo costs $10.00 input / $30.00 output per million tokens (official OpenAI 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 $15.00 for GPT-4 Turbo (1.4× as much). 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. GPT-4 Turbo has not been scored yet, Codestral-22B-v0.1 has not been scored yet and Vision Large has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-4 Turbo, Codestral-22B-v0.1 and Vision Large yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that 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 128,000 for GPT-4 Turbo and 32,768 for Codestral-22B-v0.1. Maximum output per response: GPT-4 Turbo up to 4,096, Codestral-22B-v0.1 up to 8,192, Vision Large up to 65,536 tokens.

Which can read images, PDFs, audio or video?

GPT-4 Turbo accepts text and images; Codestral-22B-v0.1 accepts text; Vision Large accepts text, images, PDFs, audio and video. Vision Large handles the widest range of inputs.

Are any of these open source?

Codestral-22B-v0.1 publishes its weights (Mistral AI Non-Production License) and can be self-hosted; GPT-4 Turbo and 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; GPT-4 Turbo came out Nov 6, 2023. Knowledge cutoff: GPT-4 Turbo Dec 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.