OLMo 2 Chat: pricing, context window and benchmarks
OLMo 2 Chat is a open-weight model from Allen Institute for AI. It offers a 16,384-token context window, costs $2.94 per million input tokens and $12.06 per million output tokens, and averages 70.6 across the index's benchmark suite.
Pricing
OLMo 2 Chat costs $2.94 per million input tokens and $12.06 per million output tokens. A blended 3:1 input-to-output mix works out to about $5.22 per million tokens. Cached input is listed at $0.37 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $2.94 | per 1M tokens |
| Output | $12.06 | per 1M tokens |
| Cached input | $0.37 | per 1M tokens |
| Blended 3:1 | $5.22 | estimate per 1M tokens |
| 1M in + 1M out | $15.00 | 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 | 73.7 | 360 | 40th | |
| GPQA Diamond | 64.1 | 377 | 37th | |
| SWE-bench Verified | 60.9 | 307 | 49th | |
| HumanEval | 74.7 | 348 | 42th | |
| MATH-500 | 72.4 | 364 | 39th | |
| AIME 2025 | 62.9 | 366 | 39th | |
| LiveCodeBench | 61.8 | 351 | 42th | |
| IFEval | 81.2 | 301 | 50th | |
| TruthfulQA | 74.4 | 345 | 43th | |
| HellaSwag | 81.1 | 369 | 39th | |
| MMMU | 69.0 | 326 | 46th | |
| Arena Elo | 1365.6 | 330 | 45th |
What OLMo 2 Chat is good for
OLMo 2 Chat 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 $2.94 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 $2.94 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 Turbo | Fireworks AI | 32768 | $8.44 | 70.7 |
| Arctic Instruct | Snowflake | 65536 | $2.83 | 70.6 |
| Nova Pro Mini | Amazon | 16384 | $7.74 | 70.6 |
| OLMo 2 Chat | Allen Institute for AI | 16384 | $2.94 | 70.6 |
| o3 Nano | OpenAI | 32768 | $7.78 | 70.6 |
| GPT-4.1 Nano | OpenAI | 32768 | $7.42 | 70.5 |
FAQ
How much does OLMo 2 Chat cost?
OLMo 2 Chat is listed at $2.94 per million input tokens and $12.06 per million output tokens. Cached input is $0.37 per million tokens. A blended 3:1 input-to-output mix is about $5.22 per million tokens.
What is the context window of OLMo 2 Chat?
OLMo 2 Chat has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is OLMo 2 Chat open weights?
Yes. OLMo 2 Chat is listed as an open-weight model under a open weights licence.
How does OLMo 2 Chat score on benchmarks?
OLMo 2 Chat averages 70.6 across the scored benchmarks in this index, ranking #355 of 600 models. Its strongest relative result is Arena Elo at 1365.6.
What is OLMo 2 Chat best for?
OLMo 2 Chat 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 $2.94 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.