Llama 3 Modal: pricing, context window and benchmarks
Llama 3 Modal is a multimodal model from Modal. It offers a 32,768-token context window, costs $3.82 per million input tokens and $17.80 per million output tokens, and averages 74.9 across the index's benchmark suite.
Pricing
Llama 3 Modal costs $3.82 per million input tokens and $17.80 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.31 per million tokens. Cached input is listed at $0.52 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.82 | per 1M tokens |
| Output | $17.80 | per 1M tokens |
| Cached input | $0.52 | per 1M tokens |
| Blended 3:1 | $7.31 | estimate per 1M tokens |
| 1M in + 1M out | $21.62 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 76.4 | 294 | 51th | |
| GPQA Diamond | 71.0 | 238 | 60th | |
| SWE-bench Verified | 63.6 | 243 | 60th | |
| HumanEval | 78.8 | 269 | 55th | |
| MATH-500 | 79.1 | 232 | 61th | |
| AIME 2025 | 70.8 | 240 | 60th | |
| LiveCodeBench | 67.4 | 240 | 60th | |
| IFEval | 81.4 | 292 | 51th | |
| TruthfulQA | 79.5 | 202 | 66th | |
| HellaSwag | 84.1 | 278 | 54th | |
| MMMU | 71.6 | 251 | 58th | |
| Arena Elo | 1391.4 | 244 | 59th |
What Llama 3 Modal is good for
Llama 3 Modal is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.82 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.82 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3 DeepInfra Chat | DeepInfra | 200000 | $3.74 | 75.0 |
| Nemotron 4 Chat | NVIDIA | 65536 | $3.99 | 75.0 |
| GLM-4.5 Base | Zhipu AI | 32768 | $3.99 | 74.9 |
| Llama 3 Baseten | Baseten | 128000 | $3.62 | 74.9 |
| Llama 3 Modal | Modal | 32768 | $3.82 | 74.9 |
| MiniMax-Text Base | MiniMax | 128000 | $3.66 | 74.9 |
FAQ
How much does Llama 3 Modal cost?
Llama 3 Modal is listed at $3.82 per million input tokens and $17.80 per million output tokens. Cached input is $0.52 per million tokens. A blended 3:1 input-to-output mix is about $7.31 per million tokens.
What is the context window of Llama 3 Modal?
Llama 3 Modal has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is Llama 3 Modal open weights?
Yes. Llama 3 Modal is listed as an open-weight model under a open weights licence.
How does Llama 3 Modal score on benchmarks?
Llama 3 Modal averages 74.9 across the scored benchmarks in this index, ranking #257 of 600 models. Its strongest relative result is Arena Elo at 1391.4.
What is Llama 3 Modal best for?
Llama 3 Modal is an open-weight model, so it can be self-hosted or run through a third-party inference provider. That matters for data residency, fine-tuning and long-run cost control. At $3.82 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.