Aion-RP 1.0 (8B) vs Nova Pro vs Qwen2.5-Coder-32B-Instruct
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.
Aion Labs
Aion-RP 1.0 (8B)
24/100- ECI—
- Price$0.80 / $1.60
- Context33K
- Our pick
AmazonNova Pro
49/100- ECI—
- Price$0.80 / $3.20
- Context300K
Alibaba (Qwen)Qwen2.5-Coder-32B-Instruct
39/100- ECI—
- Price$0.66 / $1.00
- Context131K
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 ProAion-RP 1.0 (8B): Text · Nova Pro: Text, Images, PDFs, Video · Qwen2.5-Coder-32B-Instruct: Text
- Self-hostingAion-RP 1.0 (8B) and Qwen2.5-Coder-32B-InstructPublishes downloadable weights
| Measure | Weight | Aion-RP 1.0 (8B) | Nova Pro | Qwen2.5-Coder-32B-Instruct |
|---|---|---|---|---|
| Price | 50% | 48 | 41 | 54 |
| Inputs & features | 30% | 0 | 70 | 25 |
| Context window | 20% | 0 | 39 | 25 |
| Overall | 100% | 24/100 | 49/100 | 39/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Aion-RP 1.0 (8B)Aion Labs | Nova ProAmazon | Qwen2.5-Coder-32B-InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.80 | $0.80 | $0.66 (best) |
| Output | $1.60 | $3.20 | $1.00 (best) |
| Cached input | — | $0.20 | — |
| Blended (3:1) | $1.00 | $1.40 | $0.745 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 4 providers | Official Amazon Bedrock API | Median of 7 providers |
| Limits | |||
| Context window | 32,768 tokens | 300,000 tokens (best) | 131,072 tokens |
| Max output | 29,491 tokens (best) | 10,000 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | Yes | No |
| Audio | No | No | No |
| Video | No | Yes | No |
| Reasoning | No | No | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Proprietary | Open |
| API model ID | — | amazon.nova-pro-v1:0 | — |
| API providers | 4 | 9 (best) | 7 |
| Released | Feb 4, 2025 | Dec 3, 2024 | Nov 12, 2024 |
| Knowledge cutoff | Dec 31, 2023 | Oct 2024 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Aion-RP 1.0 (8B)$11.20
- Nova Pro$14.40
- Qwen2.5-Coder-32B-Instruct$8.60
Which should you choose?
Which is better: Aion-RP 1.0 (8B), Nova Pro or Qwen2.5-Coder-32B-Instruct?
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, Aion-RP 1.0 (8B), Nova Pro or Qwen2.5-Coder-32B-Instruct?
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. Aion-RP 1.0 (8B) has not been scored yet, Nova Pro has not been scored yet and Qwen2.5-Coder-32B-Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aion-RP 1.0 (8B), Nova Pro and Qwen2.5-Coder-32B-Instruct 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: Aion-RP 1.0 (8B) up to 29,491, Nova Pro up to 10,000, Qwen2.5-Coder-32B-Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Aion-RP 1.0 (8B) accepts text; Nova Pro accepts text, images, PDFs and video; Qwen2.5-Coder-32B-Instruct accepts text. Nova Pro handles the widest range of inputs.
Are any of these open source?
Aion-RP 1.0 (8B) and Qwen2.5-Coder-32B-Instruct 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: Aion-RP 1.0 (8B) Dec 31, 2023, Nova Pro Oct 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.
