ZMIME
Comparison · 3 models · Updated Nov 2, 2026

o4-mini-deep-research vs Gemini 2.5 Pro Preview 06-05 vs Jamba Large

Gemini 2.5 Pro Preview 06-05 comes out ahead, 48 to 37 and 29 on our weighted score, though o4-mini-deep-research is 6% cheaper per token.

  1. 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. Our pick

    Google

    Gemini 2.5 Pro Preview 06-05

    Released Jun 5, 2025

    48/100
    • ECI—
    • Price$1.22 / $9.75
    • Context1.05M
    Full specs Remove Gemini 2.5 Pro Preview 06-05

  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

Gemini 2.5 Pro Preview 06-05 is our pick

Gemini 2.5 Pro Preview 06-05 is the better all-round choice, scoring 48/100 against o4-mini-deep-research (37) and Jamba Large (29). It leads on inputs & features 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 priceo4-mini-deep-researcho4-mini-deep-research $3.15 · Gemini 2.5 Pro Preview 06-05 $3.35 · Jamba Large $3.50 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Pro Preview 06-05Gemini 2.5 Pro Preview 06-05 1,048,576 · Jamba Large 256,000 · o4-mini-deep-research 200,000 tokens
  • Widest inputsGemini 2.5 Pro Preview 06-05o4-mini-deep-research: Text, Images · Gemini 2.5 Pro Preview 06-05: Text, Images, PDFs, Audio · Jamba Large: Text
  • Self-hostingJamba LargePublishes downloadable weights
How the score is built
MeasureWeighto4-mini-deep-researchGemini 2.5 Pro Preview 06-05Jamba Large
Price50%252423
Inputs & features30%608035
Context window20%326136
Overall100%37/10048/10029/100

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 Gemini 2.5 Pro Preview 06-05 vs Jamba Large specifications side by side
Specificationo4-mini-deep-researchOpenAIGemini 2.5 Pro Preview 06-05GoogleJamba LargeAI21 Labs
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$1.80$1.22 (best)$2.00
Output$7.20 (best)$9.75$8.00
Cached input———
Blended (3:1)$3.15 (best)$3.35$3.50
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 4 providersOfficial AI21 Labs API
Limits
Context window200,000 tokens1,048,576 tokens (best)256,000 tokens
Max output100,000 tokens (best)65,536 tokens4,096 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsNoYesNo
AudioNoYesNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryProprietaryOpen
API model ID——jamba-large
API providers14 (best)1
ReleasedJun 26, 2025Jun 5, 2025Jul 3, 2025
Knowledge cutoffMay 2024Jan 31, 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
  • Gemini 2.5 Pro Preview 06-05$31.69
  • Jamba Large$36.00
04 — Questions

Which should you choose?

Which is better: o4-mini-deep-research, Gemini 2.5 Pro Preview 06-05 or Jamba Large?

Gemini 2.5 Pro Preview 06-05 is the better all-round choice, scoring 48/100 against o4-mini-deep-research (37) and Jamba Large (29). It leads on inputs & features 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, o4-mini-deep-research, Gemini 2.5 Pro Preview 06-05 or Jamba Large?

o4-mini-deep-research is cheaper at $1.80 input / $7.20 output per million tokens (median across 1 API provider). Gemini 2.5 Pro Preview 06-05 costs $1.22 input / $9.75 output per million tokens (median across 4 API providers); 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 $3.15 per million tokens for o4-mini-deep-research versus $3.35 for Gemini 2.5 Pro Preview 06-05 (1.1× as much) and $3.50 for Jamba Large (1.1× 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, Gemini 2.5 Pro Preview 06-05 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, Gemini 2.5 Pro Preview 06-05 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?

Gemini 2.5 Pro Preview 06-05 has the largest context window at 1,048,576 tokens, against 256,000 for Jamba Large and 200,000 for o4-mini-deep-research. Maximum output per response: o4-mini-deep-research up to 100,000, Gemini 2.5 Pro Preview 06-05 up to 65,536, Jamba Large up to 4,096 tokens.

Which can read images, PDFs, audio or video?

o4-mini-deep-research accepts text and images; Gemini 2.5 Pro Preview 06-05 accepts text, images, PDFs and audio; Jamba Large accepts text. Gemini 2.5 Pro Preview 06-05 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 Gemini 2.5 Pro Preview 06-05 is proprietary.

Which is newer?

Jamba Large is the newest, released Jul 3, 2025. o4-mini-deep-research came out Jun 26, 2025; Gemini 2.5 Pro Preview 06-05 came out Jun 5, 2025. Knowledge cutoff: o4-mini-deep-research May 2024, Gemini 2.5 Pro Preview 06-05 Jan 31, 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