Llama 3 Baseten Base: pricing, context window and benchmarks
Llama 3 Baseten Base is a open-weight model from Baseten. It offers a 16,384-token context window, costs $3.16 per million input tokens and $13.67 per million output tokens, and averages 72.4 across the index's benchmark suite.
Pricing
Llama 3 Baseten Base costs $3.16 per million input tokens and $13.67 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 $0.35 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.16 | per 1M tokens |
| Output | $13.67 | per 1M tokens |
| Cached input | $0.35 | per 1M tokens |
| Blended 3:1 | $5.79 | estimate per 1M tokens |
| 1M in + 1M out | $16.83 | 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 | 73.5 | 363 | 40th | |
| GPQA Diamond | 67.7 | 317 | 47th | |
| SWE-bench Verified | 62.9 | 254 | 58th | |
| HumanEval | 75.8 | 331 | 45th | |
| MATH-500 | 75.9 | 301 | 50th | |
| AIME 2025 | 69.1 | 278 | 54th | |
| LiveCodeBench | 67.1 | 245 | 59th | |
| IFEval | 79.2 | 350 | 42th | |
| TruthfulQA | 74.7 | 338 | 44th | |
| HellaSwag | 82.7 | 329 | 45th | |
| MMMU | 67.8 | 346 | 42th | |
| Arena Elo | 1366.8 | 327 | 46th |
What Llama 3 Baseten Base is good for
Llama 3 Baseten Base 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 $3.16 per million input tokens (hosted list price) and a 16,384-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.16 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
- Context window of 16,384 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Firefunction Reasoning | Fireworks AI | 8192 | $9.08 | 72.5 |
| Fusion Max | OpenRouter | 65536 | $9.14 | 72.5 |
| Mixtral Groq Instruct | Groq | 16384 | $3.25 | 72.5 |
| DBRX Instruct | Databricks | 8192 | $3.21 | 72.4 |
| Llama 3 Baseten Base | Baseten | 16384 | $3.16 | 72.4 |
| Mixtral Turbo | Together AI | 65536 | $3.20 | 72.4 |
FAQ
How much does Llama 3 Baseten Base cost?
Llama 3 Baseten Base is listed at $3.16 per million input tokens and $13.67 per million output tokens. Cached input is $0.35 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 Baseten Base?
Llama 3 Baseten Base has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is Llama 3 Baseten Base open weights?
Yes. Llama 3 Baseten Base is listed as an open-weight model under a open weights licence.
How does Llama 3 Baseten Base score on benchmarks?
Llama 3 Baseten Base averages 72.4 across the scored benchmarks in this index, ranking #317 of 600 models. Its strongest relative result is Arena Elo at 1366.8.
What is Llama 3 Baseten Base best for?
Llama 3 Baseten Base 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 $3.16 per million input tokens (hosted list price) and a 16,384-token context window, it is a practical option for teams that want more control than a closed API allows.