ZMIME
Comparison · 3 models · Updated Oct 4, 2026

Qwen2.5-VL 7B Instruct vs Qwen-VL OCR vs Codestral

Qwen2.5-VL 7B Instruct comes out ahead, 51 to 48 and 36 on our weighted score, though Codestral is 14% cheaper per token.

  1. Our pick

    Alibaba (Qwen)

    Qwen2.5-VL 7B Instruct

    Released Sep 2024

    51/100
    • ECI—
    • Price$0.35 / $1.05
    • Context131K
    Full specs Remove Qwen2.5-VL 7B Instruct

  2. Alibaba (Qwen)

    Qwen-VL OCR

    Released Oct 28, 2024

    36/100
    • ECI—
    • Price$0.72 / $0.72
    • Context34K
    Full specs Remove Qwen-VL OCR

  3. Mistral AI

    Codestral

    Released May 29, 2024

    48/100
    • ECI—
    • Price$0.30 / $0.90
    • Context256K
    Full specs Remove Codestral
01 — Verdict

Qwen2.5-VL 7B Instruct is our pick

Qwen2.5-VL 7B Instruct is the better all-round choice, scoring 51/100 against Codestral (48) and Qwen-VL OCR (36). It leads on inputs & features. Codestral wins on price and context window. 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 priceCodestralCodestral $0.45 · Qwen2.5-VL 7B Instruct $0.525 · Qwen-VL OCR $0.72 per 1M tokens (3:1 blend)
  • Longest contextCodestralCodestral 256,000 · Qwen2.5-VL 7B Instruct 131,072 · Qwen-VL OCR 34,096 tokens
  • Widest inputsQwen2.5-VL 7B Instruct and Qwen-VL OCRQwen2.5-VL 7B Instruct: Text, Images · Qwen-VL OCR: Text, Images · Codestral: Text
  • Self-hostingQwen2.5-VL 7B Instruct and CodestralPublishes downloadable weights
How the score is built
MeasureWeightQwen2.5-VL 7B InstructQwen-VL OCRCodestral
Price50%635766
Inputs & features30%502525
Context window20%24136
Overall100%51/10036/10048/100

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.

Qwen2.5-VL 7B Instruct vs Qwen-VL OCR vs Codestral specifications side by side
SpecificationQwen2.5-VL 7B InstructAlibaba (Qwen)Qwen-VL OCRAlibaba (Qwen)CodestralMistral AI
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.35$0.72$0.30 (best)
Output$1.05$0.72 (best)$0.90
Cached input——$0.03
Blended (3:1)$0.525$0.72$0.45 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Alibaba APIOfficial Alibaba APIOfficial Mistral API
Limits
Context window131,072 tokens34,096 tokens256,000 tokens (best)
Max output8,192 tokens (best)4,096 tokens4,096 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesNoYes
Structured outputNoNoNo
Availability
WeightsOpenProprietaryOpen
API model IDqwen2-5-vl-7b-instructqwen-vl-ocrcodestral-latest
API providers113 (best)
ReleasedSep 2024Oct 28, 2024May 29, 2024
Knowledge cutoffApr 2024Apr 2024Oct 2024
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.

  • Qwen2.5-VL 7B Instruct$5.60
  • Qwen-VL OCR$8.64
  • Codestral$4.80
04 — Questions

Which should you choose?

Which is better: Qwen2.5-VL 7B Instruct, Qwen-VL OCR or Codestral?

Qwen2.5-VL 7B Instruct is the better all-round choice, scoring 51/100 against Codestral (48) and Qwen-VL OCR (36). It leads on inputs & features. Codestral wins on price and context window. 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, Qwen2.5-VL 7B Instruct, Qwen-VL OCR or Codestral?

Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price); Qwen-VL OCR costs $0.72 input / $0.72 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $0.525 for Qwen2.5-VL 7B Instruct (1.2× as much) and $0.72 for Qwen-VL OCR (1.6× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Qwen2.5-VL 7B Instruct has not been scored yet, Qwen-VL OCR has not been scored yet and Codestral has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Qwen2.5-VL 7B Instruct, Qwen-VL OCR and Codestral yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen-VL OCR does not support tool calling, which most coding agents need.

Which has the bigger context window?

Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-VL 7B Instruct and 34,096 for Qwen-VL OCR. Maximum output per response: Qwen2.5-VL 7B Instruct up to 8,192, Qwen-VL OCR up to 4,096, Codestral up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Qwen2.5-VL 7B Instruct accepts text and images; Qwen-VL OCR accepts text and images; Codestral accepts text. Qwen2.5-VL 7B Instruct handles the widest range of inputs.

Are any of these open source?

Qwen2.5-VL 7B Instruct and Codestral publishes its weights and can be self-hosted; Qwen-VL OCR is proprietary.

Which is newer?

Qwen-VL OCR is the newest, released Oct 28, 2024. Qwen2.5-VL 7B Instruct came out Sep 2024; Codestral came out May 29, 2024. Knowledge cutoff: Qwen2.5-VL 7B Instruct Apr 2024, Qwen-VL OCR Apr 2024, Codestral Oct 2024.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons