Yi-Lightning 8B: pricing, context window and benchmarks
Yi-Lightning 8B is a small open-weight model from 01.AI. It offers a 4,096-token context window, costs $1.16 per million input tokens and $5.13 per million output tokens, and averages 59.2 across the index's benchmark suite.
Pricing
Yi-Lightning 8B costs $1.16 per million input tokens and $5.13 per million output tokens. A blended 3:1 input-to-output mix works out to about $2.15 per million tokens. Cached input is listed at $0.12 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $1.16 | per 1M tokens |
| Output | $5.13 | per 1M tokens |
| Cached input | $0.12 | per 1M tokens |
| Blended 3:1 | $2.15 | estimate per 1M tokens |
| 1M in + 1M out | $6.29 | 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 | 65.3 | 449 | 25th | |
| GPQA Diamond | 55.2 | 461 | 23th | |
| SWE-bench Verified | 44.6 | 471 | 22th | |
| HumanEval | 60.4 | 499 | 17th | |
| MATH-500 | 60.2 | 460 | 23th | |
| AIME 2025 | 51.3 | 446 | 26th | |
| LiveCodeBench | 46.6 | 482 | 20th | |
| IFEval | 68.9 | 479 | 20th | |
| TruthfulQA | 65.8 | 448 | 25th | |
| HellaSwag | 74.1 | 455 | 24th | |
| MMMU | 58.6 | 449 | 25th | |
| Arena Elo | 1257.5 | 478 | 20th |
What Yi-Lightning 8B is good for
Yi-Lightning 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 $1.16 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $1.16 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 |
|---|---|---|---|---|
| Nova Lite Nano | Amazon | 8192 | $3.29 | 59.5 |
| QwQ 8B | Alibaba Cloud | 16384 | $1.37 | 59.5 |
| Zephyr Base | Hugging Face | 4096 | $1.26 | 59.5 |
| Yi-Lightning 8B | 01.AI | 4096 | $1.16 | 59.2 |
| Pythia Chat | EleutherAI | 4096 | $1.31 | 59.1 |
| Codestral 8B | Mistral AI | 4096 | $1.18 | 59.0 |
FAQ
How much does Yi-Lightning 8B cost?
Yi-Lightning 8B is listed at $1.16 per million input tokens and $5.13 per million output tokens. Cached input is $0.12 per million tokens. A blended 3:1 input-to-output mix is about $2.15 per million tokens.
What is the context window of Yi-Lightning 8B?
Yi-Lightning 8B has a context window of 4,096 tokens and can emit up to 4,096 output tokens per request in this index.
Is Yi-Lightning 8B open weights?
Yes. Yi-Lightning 8B is listed as an open-weight model under a open weights licence.
How does Yi-Lightning 8B score on benchmarks?
Yi-Lightning 8B averages 59.2 across the scored benchmarks in this index, ranking #463 of 600 models. Its strongest relative result is Arena Elo at 1257.5.
What is Yi-Lightning 8B best for?
Yi-Lightning 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 $1.16 per million input tokens it can handle a large share of production traffic.