Solar Pro 2 vs Llama 3.1 Nemotron 70B Instruct vs Qwen-MT Turbo
Solar Pro 2 comes out ahead, 52 to 45 and 40 on our weighted score.
- Our pick
Upstage
Solar Pro 2
52/100- ECI—
- Price$0.25 / $0.25
- Context66K
NVIDIALlama 3.1 Nemotron 70B Instruct
45/100- ECI—
- Price$0.478 / $0.504
- Context128K
Alibaba (Qwen)Qwen-MT Turbo
40/100- ECI—
- Price$0.16 / $0.49
- Context16K
Solar Pro 2 is our pick
Solar Pro 2 is the better all-round choice, scoring 52/100 against Llama 3.1 Nemotron 70B Instruct (45) and Qwen-MT Turbo (40). It leads on inputs & features. Llama 3.1 Nemotron 70B Instruct wins on 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 priceQwen-MT TurboQwen-MT Turbo $0.242 · Solar Pro 2 $0.25 · Llama 3.1 Nemotron 70B Instruct $0.485 per 1M tokens (3:1 blend)
- Longest contextLlama 3.1 Nemotron 70B InstructLlama 3.1 Nemotron 70B Instruct 128,000 · Solar Pro 2 65,536 · Qwen-MT Turbo 16,384 tokens
- Widest inputsSame inputsSolar Pro 2: Text · Llama 3.1 Nemotron 70B Instruct: Text · Qwen-MT Turbo: Text
- Self-hostingLlama 3.1 Nemotron 70B InstructPublishes downloadable weights
| Measure | Weight | Solar Pro 2 | Llama 3.1 Nemotron 70B Instruct | Qwen-MT Turbo |
|---|---|---|---|---|
| Price | 50% | 78 | 65 | 79 |
| Inputs & features | 30% | 35 | 25 | 0 |
| Context window | 20% | 12 | 24 | 0 |
| Overall | 100% | 52/100 | 45/100 | 40/100 |
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 | Solar Pro 2Upstage | Llama 3.1 Nemotron 70B InstructNVIDIA | Qwen-MT TurboAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.25 | $0.478 | $0.16 (best) |
| Output | $0.25 (best) | $0.504 | $0.49 |
| Cached input | — | — | — |
| Blended (3:1) | $0.25 | $0.485 | $0.242 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Upstage API | Median of 2 providers | Official Alibaba API |
| Limits | |||
| Context window | 65,536 tokens | 128,000 tokens (best) | 16,384 tokens |
| Max output | 8,192 tokens | 8,192 tokens | 8,192 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yesminimal · high | No | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | solar-pro2 | nvidia/llama-3.1-nemotron-70b-instruct | qwen-mt-turbo |
| API providers | 2 | 3 (best) | 1 |
| Released | May 20, 2025 | Apr 15, 2025 | Jan 2025 |
| Knowledge cutoff | Mar 2025 | — | 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.
- Solar Pro 2$3.00
- Llama 3.1 Nemotron 70B Instruct$5.79
- Qwen-MT Turbo$2.58
Which should you choose?
Which is better: Solar Pro 2, Llama 3.1 Nemotron 70B Instruct or Qwen-MT Turbo?
Solar Pro 2 is the better all-round choice, scoring 52/100 against Llama 3.1 Nemotron 70B Instruct (45) and Qwen-MT Turbo (40). It leads on inputs & features. Llama 3.1 Nemotron 70B Instruct wins on 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, Solar Pro 2, Llama 3.1 Nemotron 70B Instruct or Qwen-MT Turbo?
Qwen-MT Turbo is cheaper at $0.16 input / $0.49 output per million tokens (official Alibaba API price). Solar Pro 2 costs $0.25 input / $0.25 output per million tokens (official Upstage API price); Llama 3.1 Nemotron 70B Instruct costs $0.478 input / $0.504 output per million tokens (median across 2 API providers; free on Nvidia). At a typical mix of three input tokens to one output token, that is $0.242 per million tokens for Qwen-MT Turbo versus $0.25 for Solar Pro 2 (1× as much) and $0.485 for Llama 3.1 Nemotron 70B Instruct (2× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Solar Pro 2 has not been scored yet, Llama 3.1 Nemotron 70B Instruct has not been scored yet and Qwen-MT Turbo has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Solar Pro 2, Llama 3.1 Nemotron 70B Instruct and Qwen-MT Turbo yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen-MT Turbo does not support tool calling, which most coding agents need.
Which has the bigger context window?
Llama 3.1 Nemotron 70B Instruct has the largest context window at 128,000 tokens, against 65,536 for Solar Pro 2 and 16,384 for Qwen-MT Turbo. Maximum output per response: Solar Pro 2 up to 8,192, Llama 3.1 Nemotron 70B Instruct up to 8,192, Qwen-MT Turbo up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Solar Pro 2 accepts text; Llama 3.1 Nemotron 70B Instruct accepts text; Qwen-MT Turbo accepts text. They handle the same number of input types.
Are any of these open source?
Llama 3.1 Nemotron 70B Instruct publishes its weights and can be self-hosted; Solar Pro 2 and Qwen-MT Turbo is proprietary.
Which is newer?
Solar Pro 2 is the newest, released May 20, 2025. Llama 3.1 Nemotron 70B Instruct came out Apr 15, 2025; Qwen-MT Turbo came out Jan 2025. Knowledge cutoff: Solar Pro 2 Mar 2025, Qwen-MT Turbo Apr 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 Oct 4, 2026.
Related comparisons
- Solar Pro 2 vs Voxtral Small 24B 2507Mistral AI
- Solar Pro 2 vs Grok 4.1 FastxAI
- Solar Pro 2 vs GLM-4.6V-FlashZ.ai (Zhipu)
- Llama 3.1 Nemotron 70B Instruct vs Qwen3-VL 30B-A3BAlibaba (Qwen)
- Llama 3.1 Nemotron 70B Instruct vs GLM-4.5-AirZ.ai (Zhipu)
- Llama 3.1 Nemotron 70B Instruct vs Seed 1.6 VisionByteDance Seed
