OLMo 2 Base: pricing, context window and benchmarks
OLMo 2 Base is a open-weight model from Allen Institute for AI. It offers a 65,536-token context window, costs $2.39 per million input tokens and $11.05 per million output tokens, and averages 67.4 across the index's benchmark suite.
Pricing
OLMo 2 Base costs $2.39 per million input tokens and $11.05 per million output tokens. A blended 3:1 input-to-output mix works out to about $4.55 per million tokens. Cached input is listed at $0.33 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.39 | per 1M tokens |
| Output | $11.05 | per 1M tokens |
| Cached input | $0.33 | per 1M tokens |
| Blended 3:1 | $4.55 | estimate per 1M tokens |
| 1M in + 1M out | $13.44 | 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 | 69.8 | 398 | 34th | |
| GPQA Diamond | 62.1 | 390 | 35th | |
| SWE-bench Verified | 52.0 | 406 | 32th | |
| HumanEval | 70.2 | 391 | 35th | |
| MATH-500 | 72.6 | 362 | 40th | |
| AIME 2025 | 62.4 | 373 | 38th | |
| LiveCodeBench | 58.1 | 389 | 35th | |
| IFEval | 76.4 | 383 | 36th | |
| TruthfulQA | 72.5 | 376 | 37th | |
| HellaSwag | 81.5 | 359 | 40th | |
| MMMU | 64.1 | 388 | 35th | |
| Arena Elo | 1326.6 | 391 | 35th |
What OLMo 2 Base is good for
OLMo 2 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 $2.39 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $2.39 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
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Sonar Mini | Perplexity | 65536 | $6.52 | 67.9 |
| Grok 3 Nano | xAI | 8192 | $7.12 | 67.8 |
| Arctic Base | Snowflake | 32768 | $2.27 | 67.5 |
| Nemotron Nano Instruct | NVIDIA | 32768 | $2.33 | 67.4 |
| OLMo 2 Base | Allen Institute for AI | 65536 | $2.39 | 67.4 |
| Molmo Chat | Allen Institute for AI | 32768 | $2.40 | 66.7 |
FAQ
How much does OLMo 2 Base cost?
OLMo 2 Base is listed at $2.39 per million input tokens and $11.05 per million output tokens. Cached input is $0.33 per million tokens. A blended 3:1 input-to-output mix is about $4.55 per million tokens.
What is the context window of OLMo 2 Base?
OLMo 2 Base has a context window of 65,536 tokens and can emit up to 65,536 output tokens per request in this index.
Is OLMo 2 Base open weights?
Yes. OLMo 2 Base is listed as an open-weight model under a open weights licence.
How does OLMo 2 Base score on benchmarks?
OLMo 2 Base averages 67.4 across the scored benchmarks in this index, ranking #387 of 600 models. Its strongest relative result is Arena Elo at 1326.6.
What is OLMo 2 Base best for?
OLMo 2 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 $2.39 per million input tokens (hosted list price) and a 65,536-token context window, it is a practical option for teams that want more control than a closed API allows.