GPT-4o mini vs Llama-3.1-70B-Instruct vs Nova Pro
GPT-4o mini comes out ahead, 56 to 48 and 44 on our weighted score, and it is the cheaper option too.
- Our pick
OpenAIGPT-4o mini
56/100- ECI126.6
- Price$0.15 / $0.60
- Context128K
MetaLlama-3.1-70B-Instruct
44/100- ECI125.9
- Price$0.72 / $0.72
- Context128K
AmazonNova Pro
48/100- ECI123.8
- Price$0.80 / $3.20
- Context300K
GPT-4o mini is our pick
GPT-4o mini is the better all-round choice, scoring 56/100 against Nova Pro (48) and Llama-3.1-70B-Instruct (44). It leads on price. Nova Pro wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityGPT-4o miniCapabilities Index (ECI): GPT-4o mini 126.6 · Llama-3.1-70B-Instruct 125.9 · Nova Pro 123.8
- Lowest priceGPT-4o miniGPT-4o mini $0.263 · Llama-3.1-70B-Instruct $0.72 · Nova Pro $1.40 per 1M tokens (3:1 blend)
- Longest contextNova ProNova Pro 300,000 · GPT-4o mini 128,000 · Llama-3.1-70B-Instruct 128,000 tokens
- Widest inputsNova ProGPT-4o mini: Text, Images, PDFs · Llama-3.1-70B-Instruct: Text · Nova Pro: Text, Images, PDFs, Video
- Self-hostingLlama-3.1-70B-InstructPublishes downloadable weights
| Measure | Weight | GPT-4o mini | Llama-3.1-70B-Instruct | Nova Pro |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 49 | 48 | 45 |
| Price | 25% | 77 | 57 | 43 |
| Inputs & features | 15% | 70 | 25 | 70 |
| Context window | 10% | 24 | 24 | 39 |
| Overall | 100% | 56/100 | 44/100 | 48/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | GPT-4o miniOpenAI | Llama-3.1-70B-InstructMeta | Nova ProAmazon |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 126.6 (best) | 125.9 | 123.8 |
| ECI rank | #135 of 148 (best) | #136 of 148 | #137 of 148 |
| GPQA DiamondGraduate-level science questions | 37.7% | 44.2% (best) | — |
| FrontierMath Tiers 1–3Research-level mathematics | 0.7% | — | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 6.9% (best) | 3.6% | — |
| SimpleQA VerifiedShort factual questions | 8.3% | — | — |
| Price per million tokens | |||
| Input | $0.15 (best) | $0.72 | $0.80 |
| Output | $0.60 (best) | $0.72 | $3.20 |
| Cached input | $0.075 (best) | — | $0.20 |
| Blended (3:1) | $0.263 (best) | $0.72 | $1.40 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official OpenAI API | Median of 5 providers | Official Amazon Bedrock API |
| Limits | |||
| Context window | 128,000 tokens | 128,000 tokens | 300,000 tokens (best) |
| Max output | 16,384 tokens (best) | 4,096 tokens | 10,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | Yes | No | Yes |
| Audio | No | No | No |
| Video | No | No | Yes |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | No | No |
| Availability | |||
| Weights | Proprietary | Open | Proprietary |
| API model ID | gpt-4o-mini | — | amazon.nova-pro-v1:0 |
| API providers | 21 (best) | 5 | 3 |
| Released | Jul 18, 2024 | Jul 23, 2024 | Dec 3, 2024 |
| Knowledge cutoff | Sep 2023 | Dec 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.
- GPT-4o mini$2.70
- Llama-3.1-70B-Instruct$8.64
- Nova Pro$14.40
Which should you choose?
Which is better: GPT-4o mini, Llama-3.1-70B-Instruct or Nova Pro?
GPT-4o mini is the better all-round choice, scoring 56/100 against Nova Pro (48) and Llama-3.1-70B-Instruct (44). It leads on price. Nova Pro wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, GPT-4o mini, Llama-3.1-70B-Instruct or Nova Pro?
GPT-4o mini is cheaper at $0.15 input / $0.60 output per million tokens (official OpenAI API price). Llama-3.1-70B-Instruct costs $0.72 input / $0.72 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 $0.263 per million tokens for GPT-4o mini versus $0.72 for Llama-3.1-70B-Instruct (2.7× as much) and $1.40 for Nova Pro (5.3× as much).
Which scores higher on benchmarks?
GPT-4o mini scores higher on the Capabilities Index (ECI): GPT-4o mini 126.6 (#135 of 148), Llama-3.1-70B-Instruct 125.9 (#136 of 148) and Nova Pro 123.8 (#137 of 148). The confidence ranges of the top two overlap (120.5–128.5 vs 121.0–128.1), so treat the gap as small.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-4o mini, Llama-3.1-70B-Instruct and Nova Pro yet, so there is no like-for-like coding score. On overall capability, GPT-4o mini leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Nova Pro has the largest context window at 300,000 tokens, against 128,000 for GPT-4o mini and 128,000 for Llama-3.1-70B-Instruct. Maximum output per response: GPT-4o mini up to 16,384, Llama-3.1-70B-Instruct up to 4,096, Nova Pro up to 10,000 tokens.
Which can read images, PDFs, audio or video?
GPT-4o mini accepts text, images and PDFs; Llama-3.1-70B-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?
Llama-3.1-70B-Instruct publishes its weights and can be self-hosted; GPT-4o mini and Nova Pro is proprietary.
Which is newer?
Nova Pro is the newest, released Dec 3, 2024. Llama-3.1-70B-Instruct came out Jul 23, 2024; GPT-4o mini came out Jul 18, 2024. Knowledge cutoff: GPT-4o mini Sep 2023, Llama-3.1-70B-Instruct Dec 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 Oct 4, 2026.
Related comparisons
- GPT-4o mini vs Mistral Small 3.1 24BMistral AI · ECI 127.5
- GPT-4o mini vs Claude Haiku 3.5Anthropic · ECI 127.2
- GPT-4o mini vs Qwen2.5 7B InstructAlibaba (Qwen) · ECI 118.5
- Llama-3.1-70B-Instruct vs Qwen2.5 32B InstructAlibaba (Qwen) · ECI 128.5
- Llama-3.1-70B-Instruct vs Claude Haiku 3.5Anthropic · ECI 127.2
- Nova Pro vs Qwen2.5 32B InstructAlibaba (Qwen) · ECI 128.5
