Llama 3.1 Chat: pricing, context window and benchmarks
Llama 3.1 Chat is a multimodal model from Meta AI. It offers a 32,768-token context window, costs $3.82 per million input tokens and $18.65 per million output tokens, and averages 75.3 across the index's benchmark suite.
Pricing
Llama 3.1 Chat costs $3.82 per million input tokens and $18.65 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.53 per million tokens. Cached input is listed at $0.41 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.82 | per 1M tokens |
| Output | $18.65 | per 1M tokens |
| Cached input | $0.41 | per 1M tokens |
| Blended 3:1 | $7.53 | estimate per 1M tokens |
| 1M in + 1M out | $22.47 | 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 | 79.9 | 186 | 69th | |
| GPQA Diamond | 72.4 | 211 | 65th | |
| SWE-bench Verified | 62.0 | 280 | 53th | |
| HumanEval | 79.3 | 256 | 57th | |
| MATH-500 | 78.9 | 239 | 60th | |
| AIME 2025 | 67.7 | 300 | 50th | |
| LiveCodeBench | 68.5 | 216 | 64th | |
| IFEval | 81.9 | 280 | 53th | |
| TruthfulQA | 79.6 | 198 | 67th | |
| HellaSwag | 83.7 | 293 | 51th | |
| MMMU | 74.3 | 177 | 71th | |
| Arena Elo | 1392.5 | 239 | 60th |
What Llama 3.1 Chat is good for
Llama 3.1 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 $3.82 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 3.1 Chat | Meta AI | 32768 | $3.82 | 75.3 |
| Llama 4 Scout Base | Meta AI | 32768 | $3.95 | 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 |
FAQ
How much does Llama 3.1 Chat cost?
Llama 3.1 Chat is listed at $3.82 per million input tokens and $18.65 per million output tokens. Cached input is $0.41 per million tokens. A blended 3:1 input-to-output mix is about $7.53 per million tokens.
What is the context window of Llama 3.1 Chat?
Llama 3.1 Chat has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is Llama 3.1 Chat open weights?
Yes. Llama 3.1 Chat is listed as an open-weight model under a open weights licence.
How does Llama 3.1 Chat score on benchmarks?
Llama 3.1 Chat averages 75.3 across the scored benchmarks in this index, ranking #241 of 600 models. Its strongest relative result is Arena Elo at 1392.5.
What is Llama 3.1 Chat best for?
Llama 3.1 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 $3.82 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.