ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Sarvam 30B vs Mistral Small 4 vs Tiny Aya Earth

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

Price in rating: Included · Exclude price

  1. Sarvam AI

    Sarvam 30B

    Released Feb 18, 2026Deprecated

    34/100
    • ECI—
    • Price—
    • Context128K
  2. Mistral AI

    Mistral Small 4

    Released Mar 16, 2026

    59/100
    • ECI—
    • Price$0.15 / $0.60
    • Context256K
  3. Cohere

    Tiny Aya Earth

    Released Feb 17, 2026

    15/100
    • ECI—
    • Price—
    • Context8K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 4 59/100, Sarvam 30B 34/100, Tiny Aya Earth 15/100) 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 priceMistral Small 4Mistral Small 4 $0.263 per 1M tokens (3:1 blend) · Sarvam 30B and Tiny Aya Earth unpriced
  • Longest contextMistral Small 4Mistral Small 4 256,000 · Sarvam 30B 128,000 · Tiny Aya Earth 8,000 tokens
  • Widest inputsMistral Small 4Sarvam 30B: Text · Mistral Small 4: Text, Images · Tiny Aya Earth: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightSarvam 30BMistral Small 4Tiny Aya Earth
Inputs & features60%357025
Context window40%32430
Specs & price only100%34/10059/10015/100

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.

Sarvam 30B vs Mistral Small 4 vs Tiny Aya Earth specifications side by side
SpecificationSarvam 30BSarvam AIMistral Small 4Mistral AITiny Aya EarthCohere
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input—$0.15—
Output—$0.60—
Cached input—$0.015—
Blended (3:1)—$0.263—
Long-context rate—Same rate—
Price source—Official Mistral API—
Limits
Context window128,000 tokens256,000 tokens (best)8,000 tokens
Max output128,000 tokens256,000 tokens (best)8,000 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYeslow · medium · highYeshighNo
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenOpenOpenCC-BY-NC-4.0
API model IDsarvam-30bmistral-small-2603tiny-aya-earth
API providers120 (best)1
ReleasedFeb 18, 2026Mar 16, 2026Feb 17, 2026
Knowledge cutoff—Jun 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.

  • Sarvam 30B—
  • Mistral Small 4$2.70
  • Tiny Aya Earth—
04 — Questions

Which should you choose?

Which is better: Sarvam 30B, Mistral Small 4 or Tiny Aya Earth?

There is not enough shared capability evidence to name an overall winner. The scores (Mistral Small 4 59/100, Sarvam 30B 34/100, Tiny Aya Earth 15/100) 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, Sarvam 30B, Mistral Small 4 or Tiny Aya Earth?

Mistral Small 4 is cheaper at $0.15 input / $0.60 output per million tokens (official Mistral API price). . At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for Mistral Small 4 versus . Sarvam 30B and Tiny Aya Earth has no published per-token price.

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Sarvam 30B has not been scored yet, Mistral Small 4 has not been scored yet and Tiny Aya Earth has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Sarvam 30B, Mistral Small 4 and Tiny Aya Earth yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Mistral Small 4 has the largest context window at 256,000 tokens, against 128,000 for Sarvam 30B and 8,000 for Tiny Aya Earth. Maximum output per response: Sarvam 30B up to 128,000, Mistral Small 4 up to 256,000, Tiny Aya Earth up to 8,000 tokens.

Which can read images, PDFs, audio or video?

Sarvam 30B accepts text; Mistral Small 4 accepts text and images; Tiny Aya Earth accepts text. Mistral Small 4 handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (CC-BY-NC-4.0), so you can self-host them.

Which is newer?

Mistral Small 4 is the newest, released Mar 16, 2026. Sarvam 30B came out Feb 18, 2026; Tiny Aya Earth came out Feb 17, 2026. Knowledge cutoff: Mistral Small 4 Jun 2025.

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.