GPT-NeoX Base: pricing, context window and benchmarks
GPT-NeoX Base is a open-weight model from EleutherAI. It offers a 16,384-token context window, costs $1.22 per million input tokens and $4.64 per million output tokens, and averages 59.7 across the index's benchmark suite.
Pricing
GPT-NeoX Base costs $1.22 per million input tokens and $4.64 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.08 per million tokens. Cached input is listed at $0.18 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.22 | per 1M tokens |
| Output | $4.64 | per 1M tokens |
| Cached input | $0.18 | per 1M tokens |
| Blended 3:1 | $2.08 | estimate per 1M tokens |
| 1M in + 1M out | $5.86 | 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 | 65.2 | 450 | 25th | |
| GPQA Diamond | 56.0 | 448 | 25th | |
| SWE-bench Verified | 47.8 | 437 | 27th | |
| HumanEval | 64.4 | 447 | 26th | |
| MATH-500 | 60.1 | 461 | 23th | |
| AIME 2025 | 46.3 | 486 | 19th | |
| LiveCodeBench | 49.1 | 455 | 24th | |
| IFEval | 70.8 | 443 | 26th | |
| TruthfulQA | 67.0 | 430 | 28th | |
| HellaSwag | 73.3 | 473 | 21th | |
| MMMU | 56.8 | 473 | 21th | |
| Arena Elo | 1256.7 | 479 | 20th |
What GPT-NeoX Base is good for
GPT-NeoX 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 $1.22 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 $1.22 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 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 |
|---|---|---|---|---|
| Kimi K1.5 7B | Moonshot AI | 8192 | $1.35 | 59.9 |
| Pythia | EleutherAI | 32768 | $1.29 | 59.8 |
| Qwen3 7B | Alibaba Cloud | 32768 | $1.37 | 59.8 |
| GPT-NeoX Base | EleutherAI | 16384 | $1.22 | 59.7 |
| Qwen3-Coder 7B | Alibaba Cloud | 32768 | $1.24 | 59.6 |
| Nova Lite Nano | Amazon | 8192 | $3.29 | 59.5 |
FAQ
How much does GPT-NeoX Base cost?
GPT-NeoX Base is listed at $1.22 per million input tokens and $4.64 per million output tokens. Cached input is $0.18 per million tokens. A blended 3:1 input-to-output mix is about $2.08 per million tokens.
What is the context window of GPT-NeoX Base?
GPT-NeoX Base has a context window of 16,384 tokens and can emit up to 16,384 output tokens per request in this index.
Is GPT-NeoX Base open weights?
Yes. GPT-NeoX Base is listed as an open-weight model under a open weights licence.
How does GPT-NeoX Base score on benchmarks?
GPT-NeoX Base averages 59.7 across the scored benchmarks in this index, ranking #456 of 600 models. Its strongest relative result is Arena Elo at 1256.7.
What is GPT-NeoX Base best for?
GPT-NeoX 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 $1.22 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.