Yi-Large 8B: pricing, context window and benchmarks
Yi-Large 8B is a small open-weight model from 01.AI. It offers a 32,768-token context window, costs $0.88 per million input tokens and $3.98 per million output tokens, and averages 56.1 across the index's benchmark suite.
Pricing
Yi-Large 8B costs $0.88 per million input tokens and $3.98 per million output tokens. A blended 3:1 input-to-output mix works out to about $1.66 per million tokens. Cached input is listed at $0.12 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $0.88 | per 1M tokens |
| Output | $3.98 | per 1M tokens |
| Cached input | $0.12 | per 1M tokens |
| Blended 3:1 | $1.66 | estimate per 1M tokens |
| 1M in + 1M out | $4.86 | 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 | 60.0 | 529 | 12th | |
| GPQA Diamond | 52.3 | 499 | 17th | |
| SWE-bench Verified | 40.5 | 518 | 14th | |
| HumanEval | 61.3 | 481 | 20th | |
| MATH-500 | 53.6 | 529 | 12th | |
| AIME 2025 | 43.8 | 513 | 15th | |
| LiveCodeBench | 46.2 | 485 | 19th | |
| IFEval | 66.9 | 505 | 16th | |
| TruthfulQA | 63.7 | 479 | 20th | |
| HellaSwag | 73.6 | 465 | 23th | |
| MMMU | 55.0 | 498 | 17th | |
| Arena Elo | 1242.0 | 507 | 16th |
What Yi-Large 8B is good for
Yi-Large 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 $0.88 per million input tokens it can handle a large share of production traffic.
Strengths
- Input price of $0.88 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 |
|---|---|---|---|---|
| Llama 3 Novita 7B | Novita AI | 8192 | $0.92 | 56.3 |
| Command R+ 7B | Cohere | 8192 | $0.95 | 56.2 |
| Llama 3 Anyscale 7B | Anyscale | 4096 | $0.98 | 56.2 |
| Yi-Large 8B | 01.AI | 32768 | $0.88 | 56.1 |
| Llama 3 Hyperbolic 8B | Hyperbolic | 16384 | $0.92 | 56.0 |
| Llama 3 Replicate 7B | Replicate | 32768 | $0.91 | 56.0 |
FAQ
How much does Yi-Large 8B cost?
Yi-Large 8B is listed at $0.88 per million input tokens and $3.98 per million output tokens. Cached input is $0.12 per million tokens. A blended 3:1 input-to-output mix is about $1.66 per million tokens.
What is the context window of Yi-Large 8B?
Yi-Large 8B 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 8B open weights?
Yes. Yi-Large 8B is listed as an open-weight model under a open weights licence.
How does Yi-Large 8B score on benchmarks?
Yi-Large 8B averages 56.1 across the scored benchmarks in this index, ranking #504 of 600 models. Its strongest relative result is Arena Elo at 1242.0.
What is Yi-Large 8B best for?
Yi-Large 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 $0.88 per million input tokens it can handle a large share of production traffic.