ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Nova Pro vs Qwen2.5-Coder-32B-Instruct vs Aion-RP 1.0 (8B)

Nova Pro comes out ahead, 49 to 39 and 24 on our weighted score, though Qwen2.5-Coder-32B-Instruct is 47% cheaper per token.

  1. Our pick

    Amazon

    Nova Pro

    Released Dec 3, 2024

    49/100
    • ECI—
    • Price$0.80 / $3.20
    • Context300K
    Full specs Remove Nova Pro

  2. Alibaba (Qwen)

    Qwen2.5-Coder-32B-Instruct

    Released Nov 12, 2024

    39/100
    • ECI—
    • Price$0.66 / $1.00
    • Context131K
    Full specs Remove Qwen2.5-Coder-32B-Instruct

  3. Aion Labs

    Aion-RP 1.0 (8B)

    Released Feb 4, 2025

    24/100
    • ECI—
    • Price$0.80 / $1.60
    • Context33K
    Full specs Remove Aion-RP 1.0 (8B)
01 — Verdict

Nova Pro is our pick

Nova Pro is the better all-round choice, scoring 49/100 against Qwen2.5-Coder-32B-Instruct (39) and Aion-RP 1.0 (8B) (24). It leads on inputs & features and context window. Qwen2.5-Coder-32B-Instruct wins on 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 priceQwen2.5-Coder-32B-InstructQwen2.5-Coder-32B-Instruct $0.745 · Aion-RP 1.0 (8B) $1.00 · Nova Pro $1.40 per 1M tokens (3:1 blend)
  • Longest contextNova ProNova Pro 300,000 · Qwen2.5-Coder-32B-Instruct 131,072 · Aion-RP 1.0 (8B) 32,768 tokens
  • Widest inputsNova ProNova Pro: Text, Images, PDFs, Video · Qwen2.5-Coder-32B-Instruct: Text · Aion-RP 1.0 (8B): Text
  • Self-hostingQwen2.5-Coder-32B-Instruct and Aion-RP 1.0 (8B)Publishes downloadable weights
How the score is built
MeasureWeightNova ProQwen2.5-Coder-32B-InstructAion-RP 1.0 (8B)
Price50%415448
Inputs & features30%70250
Context window20%39250
Overall100%49/10039/10024/100

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.

Nova Pro vs Qwen2.5-Coder-32B-Instruct vs Aion-RP 1.0 (8B) specifications side by side
SpecificationNova ProAmazonQwen2.5-Coder-32B-InstructAlibaba (Qwen)Aion-RP 1.0 (8B)Aion Labs
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.80$0.66 (best)$0.80
Output$3.20$1.00 (best)$1.60
Cached input$0.20——
Blended (3:1)$1.40$0.745 (best)$1.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Amazon Bedrock APIMedian of 7 providersMedian of 4 providers
Limits
Context window300,000 tokens (best)131,072 tokens32,768 tokens
Max output10,000 tokens8,192 tokens29,491 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioNoNoNo
VideoYesNoNo
ReasoningNoNoNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsProprietaryOpenOpen
API model IDamazon.nova-pro-v1:0——
API providers9 (best)74
ReleasedDec 3, 2024Nov 12, 2024Feb 4, 2025
Knowledge cutoffOct 2024—Dec 31, 2023
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.

  • Nova Pro$14.40
  • Qwen2.5-Coder-32B-Instruct$8.60
  • Aion-RP 1.0 (8B)$11.20
04 — Questions

Which should you choose?

Which is better: Nova Pro, Qwen2.5-Coder-32B-Instruct or Aion-RP 1.0 (8B)?

Nova Pro is the better all-round choice, scoring 49/100 against Qwen2.5-Coder-32B-Instruct (39) and Aion-RP 1.0 (8B) (24). It leads on inputs & features and context window. Qwen2.5-Coder-32B-Instruct wins on 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, Nova Pro, Qwen2.5-Coder-32B-Instruct or Aion-RP 1.0 (8B)?

Qwen2.5-Coder-32B-Instruct is cheaper at $0.66 input / $1.00 output per million tokens (median across 7 API providers). Aion-RP 1.0 (8B) costs $0.80 input / $1.60 output per million tokens (median across 4 API providers); Nova Pro costs $0.80 input / $3.20 output per million tokens (official Amazon Bedrock API price). At a typical mix of three input tokens to one output token, that is $0.745 per million tokens for Qwen2.5-Coder-32B-Instruct versus $1.00 for Aion-RP 1.0 (8B) (1.3× as much) and $1.40 for Nova Pro (1.9× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Nova Pro has not been scored yet, Qwen2.5-Coder-32B-Instruct has not been scored yet and Aion-RP 1.0 (8B) has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Nova Pro, Qwen2.5-Coder-32B-Instruct and Aion-RP 1.0 (8B) yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aion-RP 1.0 (8B) does not support tool calling, which most coding agents need.

Which has the bigger context window?

Nova Pro has the largest context window at 300,000 tokens, against 131,072 for Qwen2.5-Coder-32B-Instruct and 32,768 for Aion-RP 1.0 (8B). Maximum output per response: Nova Pro up to 10,000, Qwen2.5-Coder-32B-Instruct up to 8,192, Aion-RP 1.0 (8B) up to 29,491 tokens.

Which can read images, PDFs, audio or video?

Nova Pro accepts text, images, PDFs and video; Qwen2.5-Coder-32B-Instruct accepts text; Aion-RP 1.0 (8B) accepts text. Nova Pro handles the widest range of inputs.

Are any of these open source?

Qwen2.5-Coder-32B-Instruct and Aion-RP 1.0 (8B) publishes its weights and can be self-hosted; Nova Pro is proprietary.

Which is newer?

Aion-RP 1.0 (8B) is the newest, released Feb 4, 2025. Nova Pro came out Dec 3, 2024; Qwen2.5-Coder-32B-Instruct came out Nov 12, 2024. Knowledge cutoff: Nova Pro Oct 2024, Aion-RP 1.0 (8B) Dec 31, 2023.

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