Llama 3 Baseten: pricing, context window and benchmarks
Llama 3 Baseten is a multimodal model from Baseten. It offers a 128,000-token context window, costs $3.62 per million input tokens and $14.04 per million output tokens, and averages 74.9 across the index's benchmark suite.
Pricing
Llama 3 Baseten costs $3.62 per million input tokens and $14.04 per million output tokens. A blended 3:1 input-to-output mix works out to about $6.22 per million tokens. Cached input is listed at $0.51 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.62 | per 1M tokens |
| Output | $14.04 | per 1M tokens |
| Cached input | $0.51 | per 1M tokens |
| Blended 3:1 | $6.22 | estimate per 1M tokens |
| 1M in + 1M out | $17.66 | 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 | 77.6 | 255 | 58th | |
| GPQA Diamond | 70.8 | 241 | 60th | |
| SWE-bench Verified | 62.7 | 261 | 57th | |
| HumanEval | 81.0 | 213 | 65th | |
| MATH-500 | 78.0 | 258 | 57th | |
| AIME 2025 | 72.2 | 213 | 65th | |
| LiveCodeBench | 63.2 | 335 | 44th | |
| IFEval | 83.9 | 216 | 64th | |
| TruthfulQA | 76.6 | 290 | 52th | |
| HellaSwag | 84.2 | 270 | 55th | |
| MMMU | 73.7 | 200 | 67th | |
| Arena Elo | 1400.4 | 207 | 66th |
What Llama 3 Baseten is good for
Llama 3 Baseten 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 $3.62 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 $3.62 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 DeepInfra Chat | DeepInfra | 200000 | $3.74 | 75.0 |
| Nemotron 4 Chat | NVIDIA | 65536 | $3.99 | 75.0 |
| GLM-4.5 Base | Zhipu AI | 32768 | $3.99 | 74.9 |
| Llama 3 Baseten | Baseten | 128000 | $3.62 | 74.9 |
| Llama 3 Modal | Modal | 32768 | $3.82 | 74.9 |
| MiniMax-Text Base | MiniMax | 128000 | $3.66 | 74.9 |
FAQ
How much does Llama 3 Baseten cost?
Llama 3 Baseten is listed at $3.62 per million input tokens and $14.04 per million output tokens. Cached input is $0.51 per million tokens. A blended 3:1 input-to-output mix is about $6.22 per million tokens.
What is the context window of Llama 3 Baseten?
Llama 3 Baseten 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 Baseten open weights?
Yes. Llama 3 Baseten is listed as an open-weight model under a open weights licence.
How does Llama 3 Baseten score on benchmarks?
Llama 3 Baseten averages 74.9 across the scored benchmarks in this index, ranking #256 of 600 models. Its strongest relative result is Arena Elo at 1400.4.
What is Llama 3 Baseten best for?
Llama 3 Baseten 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 $3.62 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.