OLMo 2 8B: pricing, context window and benchmarks
OLMo 2 8B is a small open-weight model from Allen Institute for AI. It offers a 4,096-token context window, costs $0.64 per million input tokens and $3.18 per million output tokens, and averages 52.5 across the index's benchmark suite.
Pricing
OLMo 2 8B costs $0.64 per million input tokens and $3.18 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.27 per million tokens. Cached input is listed at $0.08 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.64 | per 1M tokens |
| Output | $3.18 | per 1M tokens |
| Cached input | $0.08 | per 1M tokens |
| Blended 3:1 | $1.27 | estimate per 1M tokens |
| 1M in + 1M out | $3.82 | 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 | 58.6 | 543 | 10th | |
| GPQA Diamond | 50.5 | 518 | 14th | |
| SWE-bench Verified | 39.4 | 527 | 12th | |
| HumanEval | 53.9 | 550 | 8th | |
| MATH-500 | 51.0 | 548 | 9th | |
| AIME 2025 | 41.2 | 536 | 11th | |
| LiveCodeBench | 39.0 | 543 | 10th | |
| IFEval | 61.8 | 556 | 7th | |
| TruthfulQA | 60.0 | 530 | 12th | |
| HellaSwag | 71.3 | 515 | 14th | |
| MMMU | 50.3 | 550 | 8th | |
| Arena Elo | 1212.1 | 541 | 10th |
What OLMo 2 8B is good for
OLMo 2 8B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.64 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.64 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- Context window of 4,096 tokens is small for long-document work.
- Average benchmark score is below the index median; test it on your own task.
- Less reliable on open-ended reasoning and complex multi-step instructions.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 4 Scout 1.5B | Meta AI | 8192 | $0.66 | 53.0 |
| Qwen3-Coder 1.5B | Alibaba Cloud | 32768 | $0.76 | 52.8 |
| Magistral 1.5B | Mistral AI | 4096 | $0.67 | 52.7 |
| OLMo 2 8B | Allen Institute for AI | 4096 | $0.64 | 52.5 |
| Arctic 8B | Snowflake | 8192 | $0.65 | 52.4 |
| Llama 3.3 1.5B | Meta AI | 4096 | $0.61 | 52.2 |
FAQ
How much does OLMo 2 8B cost?
OLMo 2 8B is listed at $0.64 per million input tokens and $3.18 per million output tokens. Cached input is $0.077 per million tokens. A blended 3:1 input-to-output mix is about $1.27 per million tokens.
What is the context window of OLMo 2 8B?
OLMo 2 8B has a context window of 4,096 tokens and can emit up to 4,096 output tokens per request in this index.
Is OLMo 2 8B open weights?
Yes. OLMo 2 8B is listed as an open-weight model under a open weights licence.
How does OLMo 2 8B score on benchmarks?
OLMo 2 8B averages 52.5 across the scored benchmarks in this index, ranking #539 of 600 models. Its strongest relative result is Arena Elo at 1212.1.
What is OLMo 2 8B best for?
OLMo 2 8B is a small model. That makes it a good fit for classification, extraction, routing, summarization and other high-volume jobs where latency and cost dominate. It is not the right pick for open-ended frontier reasoning, but at $0.64 per million input tokens it can handle a large share of production traffic.