Llama 3 Replicate: pricing, context window and benchmarks
Llama 3 Replicate is a multimodal model from Replicate. It offers a 200,000-token context window, costs $3.75 per million input tokens and $13.86 per million output tokens, and averages 75.7 across the index's benchmark suite.
Pricing
Llama 3 Replicate costs $3.75 per million input tokens and $13.86 per million output tokens. A blended 3:1 input-to-output mix works out to about $6.28 per million tokens. Cached input is listed at $0.49 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.75 | per 1M tokens |
| Output | $13.86 | per 1M tokens |
| Cached input | $0.49 | per 1M tokens |
| Blended 3:1 | $6.28 | estimate per 1M tokens |
| 1M in + 1M out | $17.61 | 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 | 78.8 | 219 | 64th | |
| GPQA Diamond | 67.7 | 318 | 47th | |
| SWE-bench Verified | 65.4 | 207 | 66th | |
| HumanEval | 81.0 | 214 | 64th | |
| MATH-500 | 80.0 | 206 | 66th | |
| AIME 2025 | 72.6 | 208 | 65th | |
| LiveCodeBench | 69.2 | 205 | 66th | |
| IFEval | 83.6 | 224 | 63th | |
| TruthfulQA | 75.5 | 320 | 47th | |
| HellaSwag | 86.5 | 192 | 68th | |
| MMMU | 72.5 | 231 | 62th | |
| Arena Elo | 1373.6 | 303 | 50th |
What Llama 3 Replicate is good for
Llama 3 Replicate 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 $3.75 per million input tokens (hosted list price) and a 200,000-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Large 200,000-token context window for long documents and agent traces.
- Input price of $3.75 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 |
|---|---|---|---|---|
| Hunyuan-Turbo | Tencent | 128000 | $10.55 | 75.8 |
| Llama 3 Lambda Instruct | Lambda | 32768 | $3.92 | 75.8 |
| Llama 3 Anyscale Instruct | Anyscale | 200000 | $3.91 | 75.7 |
| Llama 3 Replicate | Replicate | 200000 | $3.75 | 75.7 |
| Llama 3.1 Instruct | Meta AI | 200000 | $4.05 | 75.7 |
| Sonar Turbo | Perplexity | 65536 | $10.71 | 75.7 |
FAQ
How much does Llama 3 Replicate cost?
Llama 3 Replicate is listed at $3.75 per million input tokens and $13.86 per million output tokens. Cached input is $0.49 per million tokens. A blended 3:1 input-to-output mix is about $6.28 per million tokens.
What is the context window of Llama 3 Replicate?
Llama 3 Replicate has a context window of 200,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Llama 3 Replicate open weights?
Yes. Llama 3 Replicate is listed as an open-weight model under a open weights licence.
How does Llama 3 Replicate score on benchmarks?
Llama 3 Replicate averages 75.7 across the scored benchmarks in this index, ranking #231 of 600 models. Its strongest relative result is Arena Elo at 1373.6.
What is Llama 3 Replicate best for?
Llama 3 Replicate 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 $3.75 per million input tokens (hosted list price) and a 200,000-token context window, it is a practical option for teams that want more control than a closed API allows.