ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Codestral vs Sonar

Codestral comes out ahead, 48 to 30 on our weighted score, and it is the cheaper option too.

  1. Our pick

    Mistral AI

    Codestral

    Released May 29, 2024

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

  2. Perplexity

    Sonar

    Released Jan 1, 2024

    30/100
    • ECI—
    • Price$1.00 / $1.00
    • Context128K
    Full specs Remove Sonar

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Codestral is our pick

Codestral is the better all-round choice, scoring 48/100 against Sonar (30). It leads on price, inputs & features 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 · Sonar $1.00 per 1M tokens (3:1 blend)
  • Longest contextCodestralCodestral 256,000 · Sonar 128,000 tokens
  • Widest inputsSame inputsCodestral: Text · Sonar: Text
  • Self-hostingCodestralPublishes downloadable weights
How the score is built
MeasureWeightCodestralSonar
Price50%6650
Inputs & features30%250
Context window20%3624
Overall100%48/10030/100

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.

Codestral vs Sonar specifications side by side
SpecificationCodestralMistral AISonarPerplexity
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input$0.30 (best)$1.00
Output$0.90 (best)$1.00
Cached input$0.03—
Blended (3:1)$0.45 (best)$1.00
Long-context rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Perplexity API
Limits
Context window256,000 tokens (best)128,000 tokens
Max output4,096 tokens4,096 tokens
Inputs and features
TextYesYes
ImagesNoNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningNoNo
Tool callingYesNo
Structured outputNoNo
Availability
WeightsOpenProprietary
API model IDcodestral-latestsonar
API providers36 (best)
ReleasedMay 29, 2024Jan 1, 2024
Knowledge cutoffOct 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.

  • Codestral$4.80
  • Sonar$12.00
04 — Questions

Which should you choose?

Which is better: Codestral or Sonar?

Codestral is the better all-round choice, scoring 48/100 against Sonar (30). It leads on price, inputs & features 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, Codestral or Sonar?

Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral 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 $0.45 per million tokens for Codestral versus $1.00 for Sonar (2.2× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Codestral 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 Codestral and Sonar yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Sonar 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 128,000 for Sonar. Maximum output per response: Codestral up to 4,096, Sonar up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Codestral accepts text; Sonar accepts text. They handle the same number of input types.

Are any of these open source?

Codestral publishes its weights and can be self-hosted; Sonar is proprietary.

Which is newer?

Codestral is the newest, released May 29, 2024. Sonar came out Jan 1, 2024. Knowledge cutoff: Codestral Oct 2024, Sonar Sep 1, 2025.

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