ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Voxtral Small 24B 2507 vs Sarvam 105B

Sarvam 105B comes out ahead, 65 to 55 on our weighted score, and it is the cheaper option too.

  1. Mistral AI

    Voxtral Small 24B 2507

    Released Jul 15, 2025

    55/100
    • ECI—
    • Price$0.10 / $0.30
    • Context33K
    Full specs Remove Voxtral Small 24B 2507
  2. Our pick

    Sarvam AI

    Sarvam 105B

    Released Sep 1, 2025

    65/100
    • ECI—
    • Price$0.047 / $0.186
    • Context131K
    Full specs Remove Sarvam 105B

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Sarvam 105B is our pick

Sarvam 105B is the better all-round choice, scoring 65/100 against Voxtral Small 24B 2507 (55). It leads 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 priceSarvam 105BSarvam 105B $0.082 · Voxtral Small 24B 2507 $0.15 per 1M tokens (3:1 blend)
  • Longest contextSarvam 105BSarvam 105B 131,072 · Voxtral Small 24B 2507 32,768 tokens
  • Widest inputsVoxtral Small 24B 2507Voxtral Small 24B 2507: Text, Audio · Sarvam 105B: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightVoxtral Small 24B 2507Sarvam 105B
Price50%89100
Inputs & features30%3535
Context window20%024
Overall100%55/10065/100

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.

Voxtral Small 24B 2507 vs Sarvam 105B specifications side by side
SpecificationVoxtral Small 24B 2507Mistral AISarvam 105BSarvam AI
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input$0.10$0.047 (best)
Output$0.30$0.186 (best)
Cached input——
Blended (3:1)$0.15$0.082 (best)
Long-context rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 2 providers
Limits
Context window32,768 tokens131,072 tokens (best)
Max output32,768 tokens131,072 tokens (best)
Inputs and features
TextYesYes
ImagesNoNo
PDFsNoNo
AudioYesNo
VideoNoNo
ReasoningNoYes · low · medium · high
Tool callingYesYes
Structured outputNoNo
Availability
WeightsOpenApache 2.0Open
API model IDvoxtral-small-latestsarvam-105b
API providers7 (best)3
ReleasedJul 15, 2025Sep 1, 2025
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.

  • Voxtral Small 24B 2507$1.60
  • Sarvam 105B$0.842
04 — Questions

Which should you choose?

Which is better: Voxtral Small 24B 2507 or Sarvam 105B?

Sarvam 105B is the better all-round choice, scoring 65/100 against Voxtral Small 24B 2507 (55). It leads 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, Voxtral Small 24B 2507 or Sarvam 105B?

Sarvam 105B is cheaper at $0.047 input / $0.186 output per million tokens (median across 2 API providers). Voxtral Small 24B 2507 costs $0.10 input / $0.30 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.082 per million tokens for Sarvam 105B versus $0.15 for Voxtral Small 24B 2507 (1.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Voxtral Small 24B 2507 has not been scored yet and Sarvam 105B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Voxtral Small 24B 2507 and Sarvam 105B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.

Which has the bigger context window?

Sarvam 105B has the largest context window at 131,072 tokens, against 32,768 for Voxtral Small 24B 2507. Maximum output per response: Voxtral Small 24B 2507 up to 32,768, Sarvam 105B up to 131,072 tokens.

Which can read images, PDFs, audio or video?

Voxtral Small 24B 2507 accepts text and audio; Sarvam 105B accepts text. Voxtral Small 24B 2507 handles the widest range of inputs.

Are any of these open source?

Yes, both publish their weights (Apache 2.0), so you can self-host them.

Which is newer?

Sarvam 105B is the newest, released Sep 1, 2025. Voxtral Small 24B 2507 came out Jul 15, 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