Llama 3 Modal Instruct: pricing, context window and benchmarks
Llama 3 Modal Instruct is a multimodal model from Modal. It offers a 128,000-token context window, costs $3.84 per million input tokens and $18.84 per million output tokens, and averages 75.2 across the index's benchmark suite.
Pricing
Llama 3 Modal Instruct costs $3.84 per million input tokens and $18.84 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.59 per million tokens. Cached input is listed at $0.55 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.84 | per 1M tokens |
| Output | $18.84 | per 1M tokens |
| Cached input | $0.55 | per 1M tokens |
| Blended 3:1 | $7.59 | estimate per 1M tokens |
| 1M in + 1M out | $22.68 | 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 | 80.6 | 166 | 72th | |
| GPQA Diamond | 71.9 | 221 | 63th | |
| SWE-bench Verified | 63.6 | 244 | 59th | |
| HumanEval | 79.5 | 248 | 59th | |
| MATH-500 | 81.3 | 183 | 70th | |
| AIME 2025 | 68.7 | 285 | 53th | |
| LiveCodeBench | 67.0 | 251 | 58th | |
| IFEval | 83.7 | 219 | 64th | |
| TruthfulQA | 78.6 | 233 | 61th | |
| HellaSwag | 83.5 | 305 | 49th | |
| MMMU | 69.2 | 323 | 46th | |
| Arena Elo | 1407.2 | 189 | 69th |
What Llama 3 Modal Instruct is good for
Llama 3 Modal Instruct 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 $3.84 per million input tokens (hosted list price) and a 128,000-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Large 128,000-token context window for long documents and agent traces.
- Input price of $3.84 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 3.1 Chat | Meta AI | 32768 | $3.82 | 75.3 |
| Mistral Small 3 | Mistral AI | 32768 | $3.90 | 75.3 |
| Phi-4 Instruct | Microsoft | 128000 | $3.79 | 75.3 |
| Seed-OSS | ByteDance | 32768 | $3.74 | 75.3 |
| Llama 3 Modal Instruct | Modal | 128000 | $3.84 | 75.2 |
| Reka Flash Pro | Reka AI | 200000 | $10.82 | 75.2 |
FAQ
How much does Llama 3 Modal Instruct cost?
Llama 3 Modal Instruct is listed at $3.84 per million input tokens and $18.84 per million output tokens. Cached input is $0.55 per million tokens. A blended 3:1 input-to-output mix is about $7.59 per million tokens.
What is the context window of Llama 3 Modal Instruct?
Llama 3 Modal Instruct has a context window of 128,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Llama 3 Modal Instruct open weights?
Yes. Llama 3 Modal Instruct is listed as an open-weight model under a open weights licence.
How does Llama 3 Modal Instruct score on benchmarks?
Llama 3 Modal Instruct averages 75.2 across the scored benchmarks in this index, ranking #246 of 600 models. Its strongest relative result is Arena Elo at 1407.2.
What is Llama 3 Modal Instruct best for?
Llama 3 Modal Instruct 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 $3.84 per million input tokens (hosted list price) and a 128,000-token context window, it is a practical option for teams that want more control than a closed API allows.