OLMo 2: pricing, context window and benchmarks
OLMo 2 is a open-weight model from Allen Institute for AI. It offers a 65,536-token context window, costs $2.99 per million input tokens and $11.52 per million output tokens, and averages 71.0 across the index's benchmark suite.
Pricing
OLMo 2 costs $2.99 per million input tokens and $11.52 per million output tokens. A blended 3:1 input-to-output mix works out to about $5.12 per million tokens. Cached input is listed at $0.32 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.99 | per 1M tokens |
| Output | $11.52 | per 1M tokens |
| Cached input | $0.32 | per 1M tokens |
| Blended 3:1 | $5.12 | estimate per 1M tokens |
| 1M in + 1M out | $14.51 | 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 | 75.5 | 318 | 47th | |
| GPQA Diamond | 65.1 | 358 | 40th | |
| SWE-bench Verified | 57.5 | 363 | 40th | |
| HumanEval | 77.3 | 305 | 49th | |
| MATH-500 | 75.0 | 324 | 46th | |
| AIME 2025 | 63.9 | 358 | 40th | |
| LiveCodeBench | 59.8 | 370 | 38th | |
| IFEval | 80.9 | 313 | 48th | |
| TruthfulQA | 75.5 | 321 | 47th | |
| HellaSwag | 82.5 | 337 | 44th | |
| MMMU | 68.3 | 340 | 43th | |
| Arena Elo | 1373.1 | 306 | 49th |
What OLMo 2 is good for
OLMo 2 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 $2.99 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 $2.99 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 |
|---|---|---|---|---|
| Fusion | OpenRouter | 16384 | $8.41 | 71.1 |
| Gemma 3 Base | Google DeepMind | 65536 | $3.09 | 71.1 |
| Mixtral Base | Mistral AI | 65536 | $2.95 | 71.1 |
| Command A Mini | Cohere | 8192 | $8.12 | 71.0 |
| ERNIE 4.5 Mini | Baidu | 32768 | $8.62 | 71.0 |
| OLMo 2 | Allen Institute for AI | 65536 | $2.99 | 71.0 |
FAQ
How much does OLMo 2 cost?
OLMo 2 is listed at $2.99 per million input tokens and $11.52 per million output tokens. Cached input is $0.32 per million tokens. A blended 3:1 input-to-output mix is about $5.12 per million tokens.
What is the context window of OLMo 2?
OLMo 2 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 open weights?
Yes. OLMo 2 is listed as an open-weight model under a open weights licence.
How does OLMo 2 score on benchmarks?
OLMo 2 averages 71.0 across the scored benchmarks in this index, ranking #349 of 600 models. Its strongest relative result is Arena Elo at 1373.1.
What is OLMo 2 best for?
OLMo 2 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 $2.99 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.