ERNIE 4.5 Mini: pricing, context window and benchmarks
ERNIE 4.5 Mini is a mid-range model from Baidu. It offers a 32,768-token context window, costs $8.62 per million input tokens and $33.67 per million output tokens, and averages 71.0 across the index's benchmark suite.
Pricing
ERNIE 4.5 Mini costs $8.62 per million input tokens and $33.67 per million output tokens. A blended 3:1 input-to-output mix works out to about $14.88 per million tokens. Cached input is listed at $0.97 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $8.62 | per 1M tokens |
| Output | $33.67 | per 1M tokens |
| Cached input | $0.97 | per 1M tokens |
| Blended 3:1 | $14.88 | estimate per 1M tokens |
| 1M in + 1M out | $42.29 | 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 | 74.9 | 334 | 44th | |
| GPQA Diamond | 64.5 | 370 | 38th | |
| SWE-bench Verified | 60.9 | 302 | 50th | |
| HumanEval | 73.7 | 361 | 40th | |
| MATH-500 | 75.3 | 318 | 47th | |
| AIME 2025 | 62.4 | 372 | 38th | |
| LiveCodeBench | 63.0 | 336 | 44th | |
| IFEval | 78.9 | 358 | 40th | |
| TruthfulQA | 76.6 | 289 | 52th | |
| HellaSwag | 81.0 | 370 | 38th | |
| MMMU | 69.9 | 307 | 49th | |
| Arena Elo | 1362.6 | 339 | 44th |
What ERNIE 4.5 Mini is good for
ERNIE 4.5 Mini is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $8.62 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.
Strengths
- Accepts more than text, including image input where the provider supports it.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $8.62 per million tokens.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Fusion | OpenRouter | 16384 | $8.41 | 71.1 |
| Gemma 3 Base | Google DeepMind | 65536 | $3.09 | 71.1 |
| Mixtral Base | Mistral AI | 65536 | $2.95 | 71.1 |
| Command A Mini | Cohere | 8192 | $8.12 | 71.0 |
| ERNIE 4.5 Mini | Baidu | 32768 | $8.62 | 71.0 |
| OLMo 2 | Allen Institute for AI | 65536 | $2.99 | 71.0 |
FAQ
How much does ERNIE 4.5 Mini cost?
ERNIE 4.5 Mini is listed at $8.62 per million input tokens and $33.67 per million output tokens. Cached input is $0.97 per million tokens. A blended 3:1 input-to-output mix is about $14.88 per million tokens.
What is the context window of ERNIE 4.5 Mini?
ERNIE 4.5 Mini has a context window of 32,768 tokens and can emit up to 32,768 output tokens per request in this index.
Is ERNIE 4.5 Mini open weights?
No. ERNIE 4.5 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does ERNIE 4.5 Mini score on benchmarks?
ERNIE 4.5 Mini averages 71.0 across the scored benchmarks in this index, ranking #348 of 600 models. Its strongest relative result is Arena Elo at 1362.6.
What is ERNIE 4.5 Mini best for?
ERNIE 4.5 Mini is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $8.62 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.