Aya Expanse 32B vs Llama 3.1 Nemotron 70B Instruct vs Qwen2.5 14B Instruct
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Excluded · Include price
Retired Qwen2.5 14B Instruct is no longer offered by any provider we track. Its figures are the last published listing, kept so this comparison stays available.
Cohere
Aya Expanse 32B
13/100- ECI—
- Price$0.50 / $1.50
- Context128K
NVIDIA
Llama 3.1 Nemotron 70B Instruct
28/100- ECI—
- Price$0.478 / $0.504
- Context128K
Alibaba (Qwen)
Qwen2.5 14B Instruct
25/100- ECI—
- Price$0.35 / $1.40
- Context131K
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Llama 3.1 Nemotron 70B Instruct 28/100, Qwen2.5 14B Instruct 25/100, Aya Expanse 32B 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceLlama 3.1 Nemotron 70B InstructLlama 3.1 Nemotron 70B Instruct $0.485 · Qwen2.5 14B Instruct $0.613 · Aya Expanse 32B $0.75 per 1M tokens (3:1 blend)
- Longest contextQwen2.5 14B InstructQwen2.5 14B Instruct 131,072 · Aya Expanse 32B 128,000 · Llama 3.1 Nemotron 70B Instruct 128,000 tokens
- Widest inputsSame inputsAya Expanse 32B: Text · Llama 3.1 Nemotron 70B Instruct: Text · Qwen2.5 14B Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Aya Expanse 32B | Llama 3.1 Nemotron 70B Instruct | Qwen2.5 14B Instruct |
|---|---|---|---|---|
| Inputs & features | 60% | 0 | 25 | 25 |
| Context window | 40% | 32 | 32 | 24 |
| Specs only | 100% | 13/100 | 28/100 | 25/100 |
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 | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.50 | $0.478 | $0.35 (best) |
| Output | $1.50 | $0.504 (best) | $1.40 |
| Cached input | — | — | — |
| Blended (3:1) | $0.75 | $0.485 (best) | $0.613 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Median of 2 providers | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 131,072 tokens (best) |
| Max output | 4,000 tokens | 8,192 tokens (best) | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | No | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | OpenCC-BY-NC-4.0 | Open | Open |
| API model ID | c4ai-aya-expanse-32b | nvidia/llama-3.1-nemotron-70b-instruct | qwen2-5-14b-instruct |
| API providers | 2 | 3 (best) | 1 |
| Released | Oct 24, 2024 | Apr 15, 2025 | Sep 2024 |
| Knowledge cutoff | — | — | Apr 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Aya Expanse 32B$8.00
Llama 3.1 Nemotron 70B Instruct$5.79
Qwen2.5 14B Instruct$6.30
Which should you choose?
Which is better: Aya Expanse 32B, Llama 3.1 Nemotron 70B Instruct or Qwen2.5 14B Instruct?
There is not enough shared capability evidence to name an overall winner. The scores (Llama 3.1 Nemotron 70B Instruct 28/100, Qwen2.5 14B Instruct 25/100, Aya Expanse 32B 13/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Aya Expanse 32B, Llama 3.1 Nemotron 70B Instruct or Qwen2.5 14B Instruct?
Llama 3.1 Nemotron 70B Instruct is cheaper at $0.478 input / $0.504 output per million tokens (median across 2 API providers; free on Nvidia). Qwen2.5 14B Instruct costs $0.35 input / $1.40 output per million tokens (official Alibaba API price); Aya Expanse 32B costs $0.50 input / $1.50 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.485 per million tokens for Llama 3.1 Nemotron 70B Instruct versus $0.613 for Qwen2.5 14B Instruct (1.3× as much) and $0.75 for Aya Expanse 32B (1.5× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Aya Expanse 32B has not been scored yet, Llama 3.1 Nemotron 70B Instruct has not been scored yet and Qwen2.5 14B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Aya Expanse 32B, Llama 3.1 Nemotron 70B Instruct and Qwen2.5 14B Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Aya Expanse 32B does not support tool calling, which most coding agents need.
Which has the bigger context window?
Qwen2.5 14B Instruct has the largest context window at 131,072 tokens, against 128,000 for Aya Expanse 32B and 128,000 for Llama 3.1 Nemotron 70B Instruct. Maximum output per response: Aya Expanse 32B up to 4,000, Llama 3.1 Nemotron 70B Instruct up to 8,192, Qwen2.5 14B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Aya Expanse 32B accepts text; Llama 3.1 Nemotron 70B Instruct accepts text; Qwen2.5 14B Instruct accepts text. They handle the same number of input types.
Are any of these open source?
Yes, all three publish their weights (CC-BY-NC-4.0), so you can self-host them.
Which is newer?
Llama 3.1 Nemotron 70B Instruct is the newest, released Apr 15, 2025. Aya Expanse 32B came out Oct 24, 2024; Qwen2.5 14B Instruct came out Sep 2024. Knowledge cutoff: Qwen2.5 14B Instruct Apr 2024.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.