ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral 25.08 vs Llama 3.3 Nemotron Super 49B v1 vs Phi-4-mini

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

Price in rating: Included · Exclude price

  1. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  2. NVIDIA

    Llama 3.3 Nemotron Super 49B v1

    Released Mar 18, 2025

    60/100
    • ECI—
    • Price$0.15 / $0.15
    • Context131K
  3. Microsoft

    Phi-4-mini

    Released Feb 26, 2025

    58/100
    • ECI—
    • Price$0.075 / $0.30
    • Context128K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Llama 3.3 Nemotron Super 49B v1 60/100, Phi-4-mini 58/100, Codestral 25.08 49/100) compare the available specifications and price. 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 pricePhi-4-miniPhi-4-mini $0.131 · Llama 3.3 Nemotron Super 49B v1 $0.15 · Codestral 25.08 $0.45 per 1M tokens (3:1 blend)
  • Longest contextLlama 3.3 Nemotron Super 49B v1Llama 3.3 Nemotron Super 49B v1 131,072 · Codestral 25.08 128,000 · Phi-4-mini 128,000 tokens
  • Widest inputsSame inputsCodestral 25.08: Text · Llama 3.3 Nemotron Super 49B v1: Text · Phi-4-mini: Text
  • Self-hostingLlama 3.3 Nemotron Super 49B v1 and Phi-4-miniPublishes downloadable weights
How the score is built
MeasureWeightCodestral 25.08Llama 3.3 Nemotron Super 49B v1Phi-4-mini
Price50%638588
Inputs & features30%353525
Context window20%323232
Specs & price only100%49/10060/10058/100

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 25.08 vs Llama 3.3 Nemotron Super 49B v1 vs Phi-4-mini specifications side by side
SpecificationCodestral 25.08Mistral AILlama 3.3 Nemotron Super 49B v1NVIDIAPhi-4-miniMicrosoft
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.15$0.075 (best)
Output$0.90$0.15 (best)$0.30
Cached input$0.03——
Blended (3:1)$0.45$0.15$0.131 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIMedian of 1 providersOfficial Azure API
Limits
Context window128,000 tokens131,072 tokens (best)128,000 tokens
Max output8,192 tokens131,072 tokens (best)4,096 tokens
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenOpen
API model IDcodestral-2508—phi-4-mini
API providers11 (best)12
ReleasedJul 30, 2025Mar 18, 2025Feb 26, 2025
Knowledge cutoff——Jun 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.

  • Codestral 25.08$4.80
  • Llama 3.3 Nemotron Super 49B v1$1.80
  • Phi-4-mini$1.35
04 — Questions

Which should you choose?

Which is better: Codestral 25.08, Llama 3.3 Nemotron Super 49B v1 or Phi-4-mini?

There is not enough shared capability evidence to name an overall winner. The scores (Llama 3.3 Nemotron Super 49B v1 60/100, Phi-4-mini 58/100, Codestral 25.08 49/100) compare the available specifications and price. 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 25.08, Llama 3.3 Nemotron Super 49B v1 or Phi-4-mini?

Phi-4-mini is cheaper at $0.075 input / $0.30 output per million tokens (official Azure API price). Llama 3.3 Nemotron Super 49B v1 costs $0.15 input / $0.15 output per million tokens (median across 1 API provider); Codestral 25.08 costs $0.30 input / $0.90 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.131 per million tokens for Phi-4-mini versus $0.15 for Llama 3.3 Nemotron Super 49B v1 (1.1× as much) and $0.45 for Codestral 25.08 (3.4× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral 25.08 has not been scored yet, Llama 3.3 Nemotron Super 49B v1 has not been scored yet and Phi-4-mini has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral 25.08, Llama 3.3 Nemotron Super 49B v1 and Phi-4-mini 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?

Llama 3.3 Nemotron Super 49B v1 has the largest context window at 131,072 tokens, against 128,000 for Codestral 25.08 and 128,000 for Phi-4-mini. Maximum output per response: Codestral 25.08 up to 8,192, Llama 3.3 Nemotron Super 49B v1 up to 131,072, Phi-4-mini up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Codestral 25.08 accepts text; Llama 3.3 Nemotron Super 49B v1 accepts text; Phi-4-mini accepts text. They handle the same number of input types.

Are any of these open source?

Llama 3.3 Nemotron Super 49B v1 and Phi-4-mini publishes its weights and can be self-hosted; Codestral 25.08 is proprietary.

Which is newer?

Codestral 25.08 is the newest, released Jul 30, 2025. Llama 3.3 Nemotron Super 49B v1 came out Mar 18, 2025; Phi-4-mini came out Feb 26, 2025. Knowledge cutoff: Phi-4-mini Jun 2024.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.