ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Command A vs Gemini 2.5 Pro Preview 06-05 vs Nova Premier

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. Cohere

    Command A

    Released Mar 13, 2025

    28/100
    • ECI—
    • Price$2.50 / $10.00
    • Context256K
  2. Google

    Gemini 2.5 Pro Preview 06-05

    Released Jun 5, 2025

    49/100
    • ECI—
    • Price$1.25 / $9.75
    • Context1.05M
  3. Amazon

    Nova Premier

    Released Apr 30, 2025Deprecated

    42/100
    • ECI—
    • Price$2.50 / $12.50
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Pro Preview 06-05 49/100, Nova Premier 42/100, Command A 28/100) 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 priceGemini 2.5 Pro Preview 06-05Gemini 2.5 Pro Preview 06-05 $3.38 · Command A $4.38 · Nova Premier $5.00 per 1M tokens (3:1 blend)
  • Longest contextGemini 2.5 Pro Preview 06-05Gemini 2.5 Pro Preview 06-05 1,048,576 · Nova Premier 1,000,000 · Command A 256,000 tokens
  • Widest inputsGemini 2.5 Pro Preview 06-05 and Nova PremierCommand A: Text · Gemini 2.5 Pro Preview 06-05: Text, Images, PDFs, Audio · Nova Premier: Text, Images, PDFs, Video
  • Self-hostingCommand APublishes downloadable weights
How the score is built
MeasureWeightCommand AGemini 2.5 Pro Preview 06-05Nova Premier
Price50%192416
Inputs & features30%358070
Context window20%436564
Specs & price only100%28/10049/10042/100

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.

Command A vs Gemini 2.5 Pro Preview 06-05 vs Nova Premier specifications side by side
SpecificationCommand ACohereGemini 2.5 Pro Preview 06-05GoogleNova PremierAmazon
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$2.50$1.25 (best)$2.50
Output$10.00$9.75 (best)$12.50
Cached input——$0.625
Blended (3:1)$4.38$3.38 (best)$5.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Cohere APIMedian of 4 providersOfficial Amazon Bedrock API
Limits
Context window256,000 tokens1,048,576 tokens (best)1,000,000 tokens
Max output8,000 tokens65,536 tokens (best)10,000 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesYes
AudioNoYesNo
VideoNoNoYes
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsOpenProprietaryProprietary
API model IDcommand-a-03-2025—us.amazon.nova-premier-v1:0
API providers7 (best)43
ReleasedMar 13, 2025Jun 5, 2025Apr 30, 2025
Knowledge cutoffJun 1, 2024Jan 31, 2025Oct 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.

  • Command A$45.00
  • Gemini 2.5 Pro Preview 06-05$32.00
  • Nova Premier$50.00
04 — Questions

Which should you choose?

Which is better: Command A, Gemini 2.5 Pro Preview 06-05 or Nova Premier?

There is not enough shared capability evidence to name an overall winner. The scores (Gemini 2.5 Pro Preview 06-05 49/100, Nova Premier 42/100, Command A 28/100) 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, Command A, Gemini 2.5 Pro Preview 06-05 or Nova Premier?

Gemini 2.5 Pro Preview 06-05 is cheaper at $1.25 input / $9.75 output per million tokens (median across 4 API providers). Command A costs $2.50 input / $10.00 output per million tokens (official Cohere API price); Nova Premier costs $2.50 input / $12.50 output per million tokens (official Amazon Bedrock API price). At a typical mix of three input tokens to one output token, that is $3.38 per million tokens for Gemini 2.5 Pro Preview 06-05 versus $4.38 for Command A (1.3× as much) and $5.00 for Nova Premier (1.5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Command A has not been scored yet, Gemini 2.5 Pro Preview 06-05 has not been scored yet and Nova Premier has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Command A, Gemini 2.5 Pro Preview 06-05 and Nova Premier 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 1,000,000 for Nova Premier and 256,000 for Command A. Maximum output per response: Command A up to 8,000, Gemini 2.5 Pro Preview 06-05 up to 65,536, Nova Premier up to 10,000 tokens.

Which can read images, PDFs, audio or video?

Command A accepts text; Gemini 2.5 Pro Preview 06-05 accepts text, images, PDFs and audio; Nova Premier accepts text, images, PDFs and video. Gemini 2.5 Pro Preview 06-05 handles the widest range of inputs.

Are any of these open source?

Command A publishes its weights and can be self-hosted; Gemini 2.5 Pro Preview 06-05 and Nova Premier is proprietary.

Which is newer?

Gemini 2.5 Pro Preview 06-05 is the newest, released Jun 5, 2025. Nova Premier came out Apr 30, 2025; Command A came out Mar 13, 2025. Knowledge cutoff: Command A Jun 1, 2024, Gemini 2.5 Pro Preview 06-05 Jan 31, 2025, Nova Premier Oct 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.