Llama 3 Modal Chat: pricing, context window and benchmarks
Llama 3 Modal Chat is a multimodal model from Modal. It offers a 65,536-token context window, costs $3.55 per million input tokens and $12.52 per million output tokens, and averages 73.3 across the index's benchmark suite.
Pricing
Llama 3 Modal Chat costs $3.55 per million input tokens and $12.52 per million output tokens. A blended 3:1 input-to-output mix works out to about $5.79 per million tokens. Cached input is listed at $0.29 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.55 | per 1M tokens |
| Output | $12.52 | per 1M tokens |
| Cached input | $0.29 | per 1M tokens |
| Blended 3:1 | $5.79 | estimate per 1M tokens |
| 1M in + 1M out | $16.07 | 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 | 76.8 | 283 | 53th | |
| GPQA Diamond | 69.8 | 270 | 55th | |
| SWE-bench Verified | 59.8 | 331 | 45th | |
| HumanEval | 76.6 | 316 | 47th | |
| MATH-500 | 79.0 | 234 | 61th | |
| AIME 2025 | 66.3 | 325 | 46th | |
| LiveCodeBench | 67.2 | 243 | 60th | |
| IFEval | 81.2 | 297 | 51th | |
| TruthfulQA | 77.0 | 284 | 53th | |
| HellaSwag | 83.1 | 317 | 47th | |
| MMMU | 69.5 | 317 | 47th | |
| Arena Elo | 1379.1 | 275 | 54th |
What Llama 3 Modal Chat is good for
Llama 3 Modal Chat 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 $3.55 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.55 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 |
|---|---|---|---|---|
| Claude Opus 4.5 Nano | Anthropic | 32768 | $9.38 | 73.3 |
| DBRX | Databricks | 65536 | $3.29 | 73.3 |
| Llama 3 Modal Chat | Modal | 65536 | $3.55 | 73.3 |
| Firefunction Max | Fireworks AI | 32768 | $9.12 | 73.2 |
| Gemini 3 Pro Nano | Google DeepMind | 8192 | $9.11 | 73.2 |
| Llama 3 Baseten Chat | Baseten | 200000 | $3.55 | 73.2 |
FAQ
How much does Llama 3 Modal Chat cost?
Llama 3 Modal Chat is listed at $3.55 per million input tokens and $12.52 per million output tokens. Cached input is $0.29 per million tokens. A blended 3:1 input-to-output mix is about $5.79 per million tokens.
What is the context window of Llama 3 Modal Chat?
Llama 3 Modal Chat has a context window of 65,536 tokens and can emit up to 16,384 output tokens per request in this index.
Is Llama 3 Modal Chat open weights?
Yes. Llama 3 Modal Chat is listed as an open-weight model under a open weights licence.
How does Llama 3 Modal Chat score on benchmarks?
Llama 3 Modal Chat averages 73.3 across the scored benchmarks in this index, ranking #294 of 600 models. Its strongest relative result is Arena Elo at 1379.1.
What is Llama 3 Modal Chat best for?
Llama 3 Modal Chat 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 $3.55 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.