Aion-RP 1.0 (8B) vs Hermes 3 405B Instruct vs Nova Pro
Nova Pro comes out ahead, 49 to 29 and 24 on our weighted score, though Aion-RP 1.0 (8B) is 29% cheaper per token.
Aion Labs
Aion-RP 1.0 (8B)
24/100- ECI—
- Price$0.80 / $1.60
- Context33K
Nous ResearchHermes 3 405B Instruct
29/100- ECI—
- Price$1.00 / $1.00
- Context131K
- Our pick
AmazonNova Pro
49/100- ECI—
- Price$0.80 / $3.20
- Context300K
Nova Pro is our pick
Nova Pro is the better all-round choice, scoring 49/100 against Hermes 3 405B Instruct (29) and Aion-RP 1.0 (8B) (24). 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 priceAion-RP 1.0 (8B) and Hermes 3 405B InstructAion-RP 1.0 (8B) $1.00 · Hermes 3 405B Instruct $1.00 · Nova Pro $1.40 per 1M tokens (3:1 blend)
- Longest contextNova ProNova Pro 300,000 · Hermes 3 405B Instruct 131,072 · Aion-RP 1.0 (8B) 32,768 tokens
- Widest inputsNova ProAion-RP 1.0 (8B): Text · Hermes 3 405B Instruct: Text · Nova Pro: Text, Images, PDFs, Video
- Self-hostingAion-RP 1.0 (8B) and Hermes 3 405B InstructPublishes downloadable weights
| Measure | Weight | Aion-RP 1.0 (8B) | Hermes 3 405B Instruct | Nova Pro |
|---|---|---|---|---|
| Price | 50% | 48 | 48 | 41 |
| Inputs & features | 30% | 0 | 0 | 70 |
| Context window | 20% | 0 | 25 | 39 |
| Overall | 100% | 24/100 | 29/100 | 49/100 |
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 | Hermes 3 405B InstructNous Research | Nova ProAmazon |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.80 (best) | $1.00 | $0.80 (best) |
| Output | $1.60 | $1.00 (best) | $3.20 |
| Cached input | — | — | $0.20 |
| Blended (3:1) | $1.00 (best) | $1.00 (best) | $1.40 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 4 providers | Median of 5 providers | Official Amazon Bedrock API |
| Limits | |||
| Context window | 32,768 tokens | 131,072 tokens | 300,000 tokens (best) |
| Max output | 29,491 tokens (best) | 16,384 tokens | 10,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| PDFs | No | No | Yes |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | No |
| Tool calling | No | No | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | Open | Proprietary |
| API model ID | — | — | amazon.nova-pro-v1:0 |
| API providers | 4 | 5 | 9 (best) |
| Released | Feb 4, 2025 | Aug 16, 2024 | Dec 3, 2024 |
| Knowledge cutoff | Dec 31, 2023 | 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
- Hermes 3 405B Instruct$12.00
- Nova Pro$14.40
Which should you choose?
Which is better: Aion-RP 1.0 (8B), Hermes 3 405B Instruct or Nova Pro?
Nova Pro is the better all-round choice, scoring 49/100 against Hermes 3 405B Instruct (29) and Aion-RP 1.0 (8B) (24). 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, Aion-RP 1.0 (8B), Hermes 3 405B Instruct or Nova Pro?
Aion-RP 1.0 (8B) is cheaper at $0.80 input / $1.60 output per million tokens (median across 4 API providers). Hermes 3 405B Instruct costs $1.00 input / $1.00 output per million tokens (median across 5 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 $1.00 per million tokens for Aion-RP 1.0 (8B) versus $1.00 for Hermes 3 405B Instruct (1× as much) and $1.40 for Nova Pro (1.4× 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, Hermes 3 405B Instruct has not been scored yet and Nova Pro has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aion-RP 1.0 (8B), Hermes 3 405B Instruct and Nova Pro 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) and Hermes 3 405B Instruct 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 Hermes 3 405B Instruct and 32,768 for Aion-RP 1.0 (8B). Maximum output per response: Aion-RP 1.0 (8B) up to 29,491, Hermes 3 405B Instruct up to 16,384, Nova Pro up to 10,000 tokens.
Which can read images, PDFs, audio or video?
Aion-RP 1.0 (8B) accepts text; Hermes 3 405B Instruct accepts text; Nova Pro accepts text, images, PDFs and video. Nova Pro handles the widest range of inputs.
Are any of these open source?
Aion-RP 1.0 (8B) and Hermes 3 405B 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; Hermes 3 405B Instruct came out Aug 16, 2024. Knowledge cutoff: Aion-RP 1.0 (8B) Dec 31, 2023, Hermes 3 405B Instruct 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.
