Yi-Large: pricing, context window and benchmarks
Yi-Large is a multimodal model from 01.AI. It offers a 32,768-token context window, costs $3.40 per million input tokens and $13.35 per million output tokens, and averages 73.5 across the index's benchmark suite.
Pricing
Yi-Large costs $3.40 per million input tokens and $13.35 per million output tokens. A blended 3:1 input-to-output mix works out to about $5.89 per million tokens. Cached input is listed at $0.40 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $3.40 | per 1M tokens |
| Output | $13.35 | per 1M tokens |
| Cached input | $0.40 | per 1M tokens |
| Blended 3:1 | $5.89 | estimate per 1M tokens |
| 1M in + 1M out | $16.75 | 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 | 77.1 | 274 | 54th | |
| GPQA Diamond | 70.7 | 242 | 60th | |
| SWE-bench Verified | 63.7 | 241 | 60th | |
| HumanEval | 79.4 | 254 | 58th | |
| MATH-500 | 76.2 | 295 | 51th | |
| AIME 2025 | 66.2 | 327 | 46th | |
| LiveCodeBench | 62.7 | 338 | 44th | |
| IFEval | 81.2 | 304 | 49th | |
| TruthfulQA | 78.0 | 255 | 58th | |
| HellaSwag | 85.2 | 237 | 61th | |
| MMMU | 67.8 | 347 | 42th | |
| Arena Elo | 1389.1 | 253 | 58th |
What Yi-Large is good for
Yi-Large 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 $3.40 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.
Strengths
- Input price of $3.40 per million tokens is at or below the index median.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
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 |
|---|---|---|---|---|
| Gemma 3 | Google DeepMind | 65536 | $3.68 | 73.6 |
| GPT-5.2 Nano | OpenAI | 128000 | $9.73 | 73.5 |
| Llama 3.3 Groq Base | Groq | 16384 | $3.24 | 73.5 |
| Yi-Large | 01.AI | 32768 | $3.40 | 73.5 |
| Yi-Large Chat | 01.AI | 65536 | $3.49 | 73.5 |
| Nova Lite | Amazon | 65536 | $9.20 | 73.4 |
FAQ
How much does Yi-Large cost?
Yi-Large is listed at $3.40 per million input tokens and $13.35 per million output tokens. Cached input is $0.40 per million tokens. A blended 3:1 input-to-output mix is about $5.89 per million tokens.
What is the context window of Yi-Large?
Yi-Large has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is Yi-Large open weights?
Yes. Yi-Large is listed as an open-weight model under a open weights licence.
How does Yi-Large score on benchmarks?
Yi-Large averages 73.5 across the scored benchmarks in this index, ranking #287 of 600 models. Its strongest relative result is Arena Elo at 1389.1.
What is Yi-Large best for?
Yi-Large 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 $3.40 per million input tokens (hosted list price) and a 32,768-token context window, it is a practical option for teams that want more control than a closed API allows.