GPT-NeoX Instruct: pricing, context window and benchmarks
GPT-NeoX Instruct is a open-weight model from EleutherAI. It offers a 16,384-token context window, costs $1.52 per million input tokens and $5.60 per million output tokens, and averages 62.6 across the index's benchmark suite.
Pricing
GPT-NeoX Instruct costs $1.52 per million input tokens and $5.60 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.54 per million tokens. Cached input is listed at $0.21 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.52 | per 1M tokens |
| Output | $5.60 | per 1M tokens |
| Cached input | $0.21 | per 1M tokens |
| Blended 3:1 | $2.54 | estimate per 1M tokens |
| 1M in + 1M out | $7.12 | 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 | 67.9 | 420 | 30th | |
| GPQA Diamond | 58.5 | 420 | 30th | |
| SWE-bench Verified | 50.5 | 418 | 30th | |
| HumanEval | 63.7 | 452 | 25th | |
| MATH-500 | 64.9 | 419 | 30th | |
| AIME 2025 | 54.1 | 423 | 30th | |
| LiveCodeBench | 53.9 | 412 | 31th | |
| IFEval | 71.2 | 439 | 27th | |
| TruthfulQA | 66.0 | 444 | 26th | |
| HellaSwag | 75.4 | 435 | 28th | |
| MMMU | 62.5 | 404 | 33th | |
| Arena Elo | 1292.6 | 429 | 29th |
What GPT-NeoX Instruct is good for
GPT-NeoX Instruct 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 $1.52 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 $1.52 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 |
|---|---|---|---|---|
| DeepSeek-R1 7B | DeepSeek | 32768 | $1.79 | 63.0 |
| Zephyr | Hugging Face | 8192 | $1.61 | 62.8 |
| Hunyuan-Turbo Nano | Tencent | 32768 | $4.65 | 62.7 |
| Kimi K2 7B | Moonshot AI | 16384 | $1.72 | 62.7 |
| GPT-NeoX Instruct | EleutherAI | 16384 | $1.52 | 62.6 |
| Zephyr Instruct | Hugging Face | 4096 | $1.66 | 62.4 |
FAQ
How much does GPT-NeoX Instruct cost?
GPT-NeoX Instruct is listed at $1.52 per million input tokens and $5.60 per million output tokens. Cached input is $0.21 per million tokens. A blended 3:1 input-to-output mix is about $2.54 per million tokens.
What is the context window of GPT-NeoX Instruct?
GPT-NeoX Instruct 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 Instruct open weights?
Yes. GPT-NeoX Instruct is listed as an open-weight model under a open weights licence.
How does GPT-NeoX Instruct score on benchmarks?
GPT-NeoX Instruct averages 62.6 across the scored benchmarks in this index, ranking #424 of 600 models. Its strongest relative result is Arena Elo at 1292.6.
What is GPT-NeoX Instruct best for?
GPT-NeoX Instruct 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 $1.52 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.