Llama 3 Replicate Instruct: pricing, context window and benchmarks
Llama 3 Replicate Instruct is a multimodal model from Replicate. It offers a 128,000-token context window, costs $3.71 per million input tokens and $19.99 per million output tokens, and averages 75.1 across the index's benchmark suite.
Pricing
Llama 3 Replicate Instruct costs $3.71 per million input tokens and $19.99 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.78 per million tokens. Cached input is listed at $0.33 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.71 | per 1M tokens |
| Output | $19.99 | per 1M tokens |
| Cached input | $0.33 | per 1M tokens |
| Blended 3:1 | $7.78 | estimate per 1M tokens |
| 1M in + 1M out | $23.70 | 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 | 75.8 | 309 | 49th | |
| GPQA Diamond | 72.7 | 205 | 66th | |
| SWE-bench Verified | 62.4 | 269 | 55th | |
| HumanEval | 80.5 | 221 | 63th | |
| MATH-500 | 79.9 | 213 | 65th | |
| AIME 2025 | 66.1 | 329 | 45th | |
| LiveCodeBench | 65.9 | 275 | 54th | |
| IFEval | 83.7 | 220 | 63th | |
| TruthfulQA | 78.7 | 228 | 62th | |
| HellaSwag | 86.3 | 205 | 66th | |
| MMMU | 74.4 | 174 | 71th | |
| Arena Elo | 1377.7 | 281 | 53th |
What Llama 3 Replicate Instruct is good for
Llama 3 Replicate 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 $3.71 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 $3.71 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 |
|---|---|---|---|---|
| Codestral Instruct | Mistral AI | 65536 | $4.01 | 75.1 |
| Llama 3 Hyperbolic Chat | Hyperbolic | 200000 | $3.64 | 75.1 |
| Llama 3 Replicate Instruct | Replicate | 128000 | $3.71 | 75.1 |
| Mistral Small 3 Instruct | Mistral AI | 32768 | $3.97 | 75.1 |
| Reka Flash Turbo | Reka AI | 128000 | $10.19 | 75.1 |
| Nemotron 4 Chat | NVIDIA | 65536 | $3.99 | 75.0 |
FAQ
How much does Llama 3 Replicate Instruct cost?
Llama 3 Replicate Instruct is listed at $3.71 per million input tokens and $19.99 per million output tokens. Cached input is $0.33 per million tokens. A blended 3:1 input-to-output mix is about $7.78 per million tokens.
What is the context window of Llama 3 Replicate Instruct?
Llama 3 Replicate Instruct has a context window of 128,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Llama 3 Replicate Instruct open weights?
Yes. Llama 3 Replicate Instruct is listed as an open-weight model under a open weights licence.
How does Llama 3 Replicate Instruct score on benchmarks?
Llama 3 Replicate Instruct averages 75.1 across the scored benchmarks in this index, ranking #250 of 600 models. Its strongest relative result is Arena Elo at 1377.7.
What is Llama 3 Replicate Instruct best for?
Llama 3 Replicate 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 $3.71 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.