Yi-Lightning Instruct: pricing, context window and benchmarks
Yi-Lightning Instruct is a multimodal model from 01.AI. It offers a 128,000-token context window, costs $4.16 per million input tokens and $22.74 per million output tokens, and averages 76.5 across the index's benchmark suite.
Pricing
Yi-Lightning Instruct costs $4.16 per million input tokens and $22.74 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.80 per million tokens. Cached input is listed at $0.35 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.16 | per 1M tokens |
| Output | $22.74 | per 1M tokens |
| Cached input | $0.35 | per 1M tokens |
| Blended 3:1 | $8.80 | estimate per 1M tokens |
| 1M in + 1M out | $26.90 | 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 | 78.4 | 231 | 62th | |
| GPQA Diamond | 73.0 | 200 | 67th | |
| SWE-bench Verified | 65.3 | 209 | 65th | |
| HumanEval | 79.1 | 264 | 56th | |
| MATH-500 | 78.2 | 255 | 58th | |
| AIME 2025 | 71.7 | 225 | 63th | |
| LiveCodeBench | 70.3 | 186 | 69th | |
| IFEval | 85.6 | 171 | 72th | |
| TruthfulQA | 81.5 | 143 | 76th | |
| HellaSwag | 85.9 | 221 | 63th | |
| MMMU | 72.1 | 241 | 60th | |
| Arena Elo | 1415.8 | 166 | 72th |
What Yi-Lightning Instruct is good for
Yi-Lightning Instruct is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.16 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 128,000-token context window for long documents and agent traces.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Llama 3.3 Instruct | Meta AI | 128000 | $4.33 | 76.6 |
| Nemotron 4 | NVIDIA | 65536 | $4.18 | 76.6 |
| Qwen3-Coder Base | Alibaba Cloud | 200000 | $3.99 | 76.6 |
| Claude Sonnet 4.5 Mini | Anthropic | 32768 | $11.43 | 76.5 |
| Qwen3-Max Mini | Alibaba Cloud | 128000 | $11.13 | 76.5 |
| Yi-Lightning Instruct | 01.AI | 128000 | $4.16 | 76.5 |
FAQ
How much does Yi-Lightning Instruct cost?
Yi-Lightning Instruct is listed at $4.16 per million input tokens and $22.74 per million output tokens. Cached input is $0.35 per million tokens. A blended 3:1 input-to-output mix is about $8.80 per million tokens.
What is the context window of Yi-Lightning Instruct?
Yi-Lightning Instruct has a context window of 128,000 tokens and can emit up to 16,384 output tokens per request in this index.
Is Yi-Lightning Instruct open weights?
Yes. Yi-Lightning Instruct is listed as an open-weight model under a open weights licence.
How does Yi-Lightning Instruct score on benchmarks?
Yi-Lightning Instruct averages 76.5 across the scored benchmarks in this index, ranking #208 of 600 models. Its strongest relative result is Arena Elo at 1415.8.
What is Yi-Lightning Instruct best for?
Yi-Lightning Instruct is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.16 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.