ERNIE 4.5 Pro: pricing, context window and benchmarks
ERNIE 4.5 Pro is a multimodal model from Baidu. It offers a 1,000,000-token context window, costs $13.89 per million input tokens and $65.19 per million output tokens, and averages 80.5 across the index's benchmark suite.
Pricing
ERNIE 4.5 Pro costs $13.89 per million input tokens and $65.19 per million output tokens. A blended 3:1 input-to-output mix works out to about $26.71 per million tokens. Cached input is listed at $1.37 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $13.89 | per 1M tokens |
| Output | $65.19 | per 1M tokens |
| Cached input | $1.37 | per 1M tokens |
| Blended 3:1 | $26.71 | estimate per 1M tokens |
| 1M in + 1M out | $79.08 | 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 | 80.3 | 175 | 71th | |
| GPQA Diamond | 74.7 | 149 | 75th | |
| SWE-bench Verified | 66.5 | 178 | 70th | |
| HumanEval | 86.9 | 90 | 85th | |
| MATH-500 | 87.2 | 75 | 88th | |
| AIME 2025 | 76.3 | 136 | 77th | |
| LiveCodeBench | 76.4 | 77 | 87th | |
| IFEval | 86.0 | 156 | 74th | |
| TruthfulQA | 83.1 | 105 | 83th | |
| HellaSwag | 90.2 | 80 | 87th | |
| MMMU | 78.4 | 86 | 86th | |
| Arena Elo | 1414.3 | 171 | 72th |
What ERNIE 4.5 Pro is good for
ERNIE 4.5 Pro 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 $13.89 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 1,000,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $13.89 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| ERNIE 4.5 Max | Baidu | 128000 | $14.41 | 80.6 |
| MiniMax-M2 | MiniMax | 200000 | $5.19 | 80.6 |
| ERNIE 4.5 Pro | Baidu | 1000000 | $13.89 | 80.5 |
| Kimi K1.5 Instruct | Moonshot AI | 200000 | $5.15 | 80.5 |
| Sonar Pro Reasoning | Perplexity | 128000 | $13.94 | 80.5 |
| GPT-5.2 Mini | OpenAI | 200000 | $13.34 | 80.4 |
FAQ
How much does ERNIE 4.5 Pro cost?
ERNIE 4.5 Pro is listed at $13.89 per million input tokens and $65.19 per million output tokens. Cached input is $1.37 per million tokens. A blended 3:1 input-to-output mix is about $26.71 per million tokens.
What is the context window of ERNIE 4.5 Pro?
ERNIE 4.5 Pro has a context window of 1,000,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is ERNIE 4.5 Pro open weights?
No. ERNIE 4.5 Pro is a proprietary model with a proprietary licence, so you cannot download the weights.
How does ERNIE 4.5 Pro score on benchmarks?
ERNIE 4.5 Pro averages 80.5 across the scored benchmarks in this index, ranking #106 of 600 models. Its strongest relative result is Arena Elo at 1414.3.
What is ERNIE 4.5 Pro best for?
ERNIE 4.5 Pro 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 $13.89 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.