Llama 3 Baseten Instruct: pricing, context window and benchmarks
Llama 3 Baseten Instruct is a multimodal model from Baseten. It offers a 200,000-token context window, costs $3.91 per million input tokens and $20.18 per million output tokens, and averages 76.2 across the index's benchmark suite.
Pricing
Llama 3 Baseten Instruct costs $3.91 per million input tokens and $20.18 per million output tokens. A blended 3:1 input-to-output mix works out to about $7.98 per million tokens. Cached input is listed at $0.41 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.91 | per 1M tokens |
| Output | $20.18 | per 1M tokens |
| Cached input | $0.41 | per 1M tokens |
| Blended 3:1 | $7.98 | estimate per 1M tokens |
| 1M in + 1M out | $24.09 | 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 | 80.0 | 182 | 70th | |
| GPQA Diamond | 73.9 | 171 | 72th | |
| SWE-bench Verified | 62.8 | 257 | 57th | |
| HumanEval | 78.6 | 273 | 55th | |
| MATH-500 | 77.4 | 269 | 55th | |
| AIME 2025 | 74.7 | 159 | 74th | |
| LiveCodeBench | 70.1 | 189 | 69th | |
| IFEval | 83.1 | 241 | 60th | |
| TruthfulQA | 79.3 | 205 | 66th | |
| HellaSwag | 86.8 | 184 | 69th | |
| MMMU | 72.0 | 244 | 59th | |
| Arena Elo | 1397.8 | 214 | 64th |
What Llama 3 Baseten Instruct is good for
Llama 3 Baseten 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 $3.91 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 $3.91 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 | Meta AI | 200000 | $4.16 | 76.3 |
| Command R+ Instruct | Cohere | 200000 | $4.16 | 76.2 |
| Llama 3 Baseten Instruct | Baseten | 200000 | $3.91 | 76.2 |
| Llama 3 Hyperbolic Instruct | Hyperbolic | 200000 | $3.79 | 76.2 |
| Sonar Reasoning | Perplexity | 200000 | $11.48 | 76.2 |
| o3 Mini | OpenAI | 128000 | $10.68 | 76.2 |
FAQ
How much does Llama 3 Baseten Instruct cost?
Llama 3 Baseten Instruct is listed at $3.91 per million input tokens and $20.18 per million output tokens. Cached input is $0.41 per million tokens. A blended 3:1 input-to-output mix is about $7.98 per million tokens.
What is the context window of Llama 3 Baseten Instruct?
Llama 3 Baseten Instruct has a context window of 200,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Llama 3 Baseten Instruct open weights?
Yes. Llama 3 Baseten Instruct is listed as an open-weight model under a open weights licence.
How does Llama 3 Baseten Instruct score on benchmarks?
Llama 3 Baseten Instruct averages 76.2 across the scored benchmarks in this index, ranking #214 of 600 models. Its strongest relative result is Arena Elo at 1397.8.
What is Llama 3 Baseten Instruct best for?
Llama 3 Baseten 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 $3.91 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.