ZMIME
Comparison · 3 models · Updated Nov 2, 2026

o4-mini-deep-research vs Apertus 70B vs Jamba Large

o4-mini-deep-research comes out ahead, 37 to 32 and 29 on our weighted score, though Apertus 70B is 2.6× cheaper per token.

  1. Our pick

    OpenAI

    o4-mini-deep-research

    Released Jun 26, 2025

    37/100
    • ECI—
    • Price$1.80 / $7.20
    • Context200K
    Full specs Remove o4-mini-deep-research

  2. Swiss AI

    Apertus 70B

    Released Sep 2, 2025

    32/100
    • ECI—
    • Price$0.82 / $2.42
    • Context66K
    Full specs Remove Apertus 70B

  3. AI21 Labs

    Jamba Large

    Released Jul 3, 2025

    29/100
    • ECI—
    • Price$2.00 / $8.00
    • Context256K
    Full specs Remove Jamba Large
01 — Verdict

o4-mini-deep-research is our pick

o4-mini-deep-research is the better all-round choice, scoring 37/100 against Apertus 70B (32) and Jamba Large (29). It leads on inputs & features. Apertus 70B wins on price. Jamba Large wins on 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 priceApertus 70BApertus 70B $1.22 · 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 · Apertus 70B 65,536 tokens
  • Widest inputso4-mini-deep-researcho4-mini-deep-research: Text, Images · Apertus 70B: Text · Jamba Large: Text
  • Self-hostingApertus 70B and Jamba LargePublishes downloadable weights (Apache-2.0)
How the score is built
MeasureWeighto4-mini-deep-researchApertus 70BJamba Large
Price50%254423
Inputs & features30%602535
Context window20%321236
Overall100%37/10032/10029/100

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 Apertus 70B vs Jamba Large specifications side by side
Specificationo4-mini-deep-researchOpenAIApertus 70BSwiss AIJamba LargeAI21 Labs
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.80$0.82 (best)$2.00
Output$7.20$2.42 (best)$8.00
Cached input———
Blended (3:1)$3.15$1.22 (best)$3.50
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 3 providersOfficial AI21 Labs API
Limits
Context window200,000 tokens65,536 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 outputNoNoYes
Availability
WeightsProprietaryOpenApache-2.0Open
API model ID——jamba-large
API providers13 (best)1
ReleasedJun 26, 2025Sep 2, 2025Jul 3, 2025
Knowledge cutoffMay 2024Sep 2025Aug 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
  • Apertus 70B$13.04
  • Jamba Large$36.00
04 — Questions

Which should you choose?

Which is better: o4-mini-deep-research, Apertus 70B or Jamba Large?

o4-mini-deep-research is the better all-round choice, scoring 37/100 against Apertus 70B (32) and Jamba Large (29). It leads on inputs & features. Apertus 70B wins on price. Jamba Large wins on 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, o4-mini-deep-research, Apertus 70B or Jamba Large?

Apertus 70B is cheaper at $0.82 input / $2.42 output per million tokens (median across 3 API providers). 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 $1.22 per million tokens for Apertus 70B versus $3.15 for o4-mini-deep-research (2.6× as much) and $3.50 for Jamba Large (2.9× 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, Apertus 70B 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, Apertus 70B 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 65,536 for Apertus 70B. Maximum output per response: o4-mini-deep-research up to 100,000, Apertus 70B 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; Apertus 70B accepts text; Jamba Large accepts text. o4-mini-deep-research handles the widest range of inputs.

Are any of these open source?

Apertus 70B and Jamba Large publishes its weights (Apache-2.0) and can be self-hosted; o4-mini-deep-research is proprietary.

Which is newer?

Apertus 70B is the newest, released Sep 2, 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, Apertus 70B Sep 2025, Jamba Large Aug 22, 2024.

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 Nov 2, 2026.

05 — Keep comparing

Related comparisons