GPT-NeoX 1.5B: pricing, context window and benchmarks
GPT-NeoX 1.5B is a small open-weight model from EleutherAI. It offers a 32,768-token context window, costs $0.06 per million input tokens and $0.32 per million output tokens, and averages 36.4 across the index's benchmark suite.
Pricing
GPT-NeoX 1.5B costs $0.06 per million input tokens and $0.32 per million output tokens. A blended 3:1 input-to-output mix works out to about $0.12 per million tokens. Cached input is listed at $0.01 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.06 | per 1M tokens |
| Output | $0.32 | per 1M tokens |
| Cached input | $0.01 | per 1M tokens |
| Blended 3:1 | $0.12 | estimate per 1M tokens |
| 1M in + 1M out | $0.38 | 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 | 47.0 | 598 | 1th | |
| GPQA Diamond | 32.4 | 598 | 1th | |
| SWE-bench Verified | 18.3 | 600 | 1th | |
| HumanEval | 37.0 | 600 | 1th | |
| MATH-500 | 35.7 | 597 | 1th | |
| AIME 2025 | 17.6 | 598 | 1th | |
| LiveCodeBench | 22.0 | 598 | 1th | |
| IFEval | 49.5 | 600 | 1th | |
| TruthfulQA | 44.3 | 599 | 1th | |
| HellaSwag | 58.1 | 598 | 1th | |
| MMMU | 38.6 | 598 | 1th | |
| Arena Elo | 1112.0 | 596 | 1th |
What GPT-NeoX 1.5B is good for
GPT-NeoX 1.5B 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 $0.060 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.060 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
Trade-offs
- 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 |
|---|---|---|---|---|
| Pythia 7B | EleutherAI | 8192 | $0.10 | 40.7 |
| StableLM 2 1.5B | Stability AI | 16384 | $0.13 | 38.3 |
| Zephyr 1.5B | Hugging Face | 32768 | $0.10 | 38.0 |
| SmolLM3 1.5B | Hugging Face | 8192 | $0.04 | 36.8 |
| GPT-NeoX 1.5B | EleutherAI | 32768 | $0.06 | 36.4 |
| Pythia 1.5B | EleutherAI | 4096 | $0.10 | 35.8 |
FAQ
How much does GPT-NeoX 1.5B cost?
GPT-NeoX 1.5B is listed at $0.060 per million input tokens and $0.32 per million output tokens. Cached input is $0.007 per million tokens. A blended 3:1 input-to-output mix is about $0.12 per million tokens.
What is the context window of GPT-NeoX 1.5B?
GPT-NeoX 1.5B has a context window of 32,768 tokens and can emit up to 8,192 output tokens per request in this index.
Is GPT-NeoX 1.5B open weights?
Yes. GPT-NeoX 1.5B is listed as an open-weight model under a open weights licence.
How does GPT-NeoX 1.5B score on benchmarks?
GPT-NeoX 1.5B averages 36.4 across the scored benchmarks in this index, ranking #599 of 600 models. Its strongest relative result is Arena Elo at 1112.0.
What is GPT-NeoX 1.5B best for?
GPT-NeoX 1.5B 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 $0.060 per million input tokens it can handle a large share of production traffic.