Llama 3 Modal Base: pricing, context window and benchmarks
Llama 3 Modal Base is a open-weight model from Modal. It offers a 16,384-token context window, costs $3.21 per million input tokens and $17.08 per million output tokens, and averages 72.2 across the index's benchmark suite.
Pricing
Llama 3 Modal Base costs $3.21 per million input tokens and $17.08 per million output tokens. A blended 3:1 input-to-output mix works out to about $6.68 per million tokens. Cached input is listed at $0.28 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.21 | per 1M tokens |
| Output | $17.08 | per 1M tokens |
| Cached input | $0.28 | per 1M tokens |
| Blended 3:1 | $6.68 | estimate per 1M tokens |
| 1M in + 1M out | $20.29 | 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 | 76.6 | 288 | 52th | |
| GPQA Diamond | 66.2 | 340 | 43th | |
| SWE-bench Verified | 60.1 | 325 | 46th | |
| HumanEval | 78.9 | 268 | 55th | |
| MATH-500 | 75.8 | 305 | 49th | |
| AIME 2025 | 64.9 | 338 | 44th | |
| LiveCodeBench | 65.1 | 291 | 52th | |
| IFEval | 79.7 | 340 | 43th | |
| TruthfulQA | 73.6 | 363 | 40th | |
| HellaSwag | 84.1 | 279 | 54th | |
| MMMU | 68.9 | 327 | 46th | |
| Arena Elo | 1363.9 | 336 | 44th |
What Llama 3 Modal Base is good for
Llama 3 Modal Base 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 $3.21 per million input tokens (hosted list price) and a 16,384-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.21 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
- Context window of 16,384 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Firefunction | Fireworks AI | 16384 | $8.16 | 72.3 |
| Fusion Pro | OpenRouter | 65536 | $8.69 | 72.2 |
| Fusion Reasoning | OpenRouter | 65536 | $8.59 | 72.2 |
| Llama 3 Modal Base | Modal | 16384 | $3.21 | 72.2 |
| Llama 3.1 Base | Meta AI | 32768 | $3.39 | 72.2 |
| Seed-OSS Base | ByteDance | 16384 | $3.14 | 72.2 |
FAQ
How much does Llama 3 Modal Base cost?
Llama 3 Modal Base is listed at $3.21 per million input tokens and $17.08 per million output tokens. Cached input is $0.28 per million tokens. A blended 3:1 input-to-output mix is about $6.68 per million tokens.
What is the context window of Llama 3 Modal Base?
Llama 3 Modal Base has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is Llama 3 Modal Base open weights?
Yes. Llama 3 Modal Base is listed as an open-weight model under a open weights licence.
How does Llama 3 Modal Base score on benchmarks?
Llama 3 Modal Base averages 72.2 across the scored benchmarks in this index, ranking #323 of 600 models. Its strongest relative result is Arena Elo at 1363.9.
What is Llama 3 Modal Base best for?
Llama 3 Modal Base 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 $3.21 per million input tokens (hosted list price) and a 16,384-token context window, it is a practical option for teams that want more control than a closed API allows.