ZMIME
Comparison · 3 models · Updated Nov 18, 2026

o4-mini-deep-research vs Codestral 25.08 vs Jamba Large

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. OpenAI

    o4-mini-deep-research

    Released Jun 26, 2025

    38/100
    • ECI—
    • Price$1.80 / $7.20
    • Context200K
  2. Mistral AI

    Codestral 25.08

    Released Jul 30, 2025

    49/100
    • ECI—
    • Price$0.30 / $0.90
    • Context128K
  3. AI21 Labs

    Jamba Large

    Released Jul 3, 2025

    31/100
    • ECI—
    • Price$2.00 / $8.00
    • Context256K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, o4-mini-deep-research 38/100, Jamba Large 31/100) 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 priceCodestral 25.08Codestral 25.08 $0.45 · o4-mini-deep-research $3.15 · Jamba Large $3.50 per 1M tokens (3:1 blend)
  • Longest contextJamba LargeJamba Large 256,000 · o4-mini-deep-research 200,000 · Codestral 25.08 128,000 tokens
  • Widest inputso4-mini-deep-researcho4-mini-deep-research: Text, Images · Codestral 25.08: Text · Jamba Large: Text
  • Self-hostingJamba LargePublishes downloadable weights
How the score is built
MeasureWeighto4-mini-deep-researchCodestral 25.08Jamba Large
Price50%256323
Inputs & features30%603535
Context window20%393243
Specs & price only100%38/10049/10031/100

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.

o4-mini-deep-research vs Codestral 25.08 vs Jamba Large specifications side by side
Specificationo4-mini-deep-researchOpenAICodestral 25.08Mistral AIJamba LargeAI21 Labs
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.80$0.30 (best)$2.00
Output$7.20$0.90 (best)$8.00
Cached input—$0.03—
Blended (3:1)$3.15$0.45 (best)$3.50
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersOfficial Mistral APIOfficial AI21 Labs API
Limits
Context window200,000 tokens128,000 tokens256,000 tokens (best)
Max output100,000 tokens (best)8,192 tokens4,096 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsProprietaryProprietaryOpen
API model ID—codestral-2508jamba-large
API providers111 (best)1
ReleasedJun 26, 2025Jul 30, 2025Jul 3, 2025
Knowledge cutoffMay 2024—Aug 22, 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.

  • o4-mini-deep-research$32.40
  • Codestral 25.08$4.80
  • Jamba Large$36.00
04 — Questions

Which should you choose?

Which is better: o4-mini-deep-research, Codestral 25.08 or Jamba Large?

There is not enough shared capability evidence to name an overall winner. The scores (Codestral 25.08 49/100, o4-mini-deep-research 38/100, Jamba Large 31/100) 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, o4-mini-deep-research, Codestral 25.08 or Jamba Large?

Codestral 25.08 is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). o4-mini-deep-research costs $1.80 input / $7.20 output per million tokens (median across 1 API provider); Jamba Large costs $2.00 input / $8.00 output per million tokens (official AI21 Labs API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral 25.08 versus $3.15 for o4-mini-deep-research (7× as much) and $3.50 for Jamba Large (7.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. o4-mini-deep-research has not been scored yet, Codestral 25.08 has not been scored yet and Jamba Large has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for o4-mini-deep-research, Codestral 25.08 and Jamba Large 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?

Jamba Large has the largest context window at 256,000 tokens, against 200,000 for o4-mini-deep-research and 128,000 for Codestral 25.08. Maximum output per response: o4-mini-deep-research up to 100,000, Codestral 25.08 up to 8,192, Jamba Large up to 4,096 tokens.

Which can read images, PDFs, audio or video?

o4-mini-deep-research accepts text and images; Codestral 25.08 accepts text; Jamba Large accepts text. o4-mini-deep-research handles the widest range of inputs.

Are any of these open source?

Jamba Large publishes its weights and can be self-hosted; o4-mini-deep-research and Codestral 25.08 is proprietary.

Which is newer?

Codestral 25.08 is the newest, released Jul 30, 2025. Jamba Large came out Jul 3, 2025; o4-mini-deep-research came out Jun 26, 2025. Knowledge cutoff: o4-mini-deep-research May 2024, Jamba Large Aug 22, 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.