ERNIE 4.5 Nano: pricing, context window and benchmarks
ERNIE 4.5 Nano is a mid-range model from Baidu. It offers a 32,768-token context window, costs $6.01 per million input tokens and $22.92 per million output tokens, and averages 65.6 across the index's benchmark suite.
Pricing
ERNIE 4.5 Nano costs $6.01 per million input tokens and $22.92 per million output tokens. A blended 3:1 input-to-output mix works out to about $10.24 per million tokens. Cached input is listed at $0.74 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $6.01 | per 1M tokens |
| Output | $22.92 | per 1M tokens |
| Cached input | $0.74 | per 1M tokens |
| Blended 3:1 | $10.24 | estimate per 1M tokens |
| 1M in + 1M out | $28.93 | 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 | 69.7 | 399 | 34th | |
| GPQA Diamond | 60.0 | 405 | 33th | |
| SWE-bench Verified | 56.2 | 375 | 38th | |
| HumanEval | 69.4 | 405 | 33th | |
| MATH-500 | 68.1 | 399 | 34th | |
| AIME 2025 | 57.8 | 401 | 33th | |
| LiveCodeBench | 55.5 | 400 | 33th | |
| IFEval | 76.8 | 379 | 37th | |
| TruthfulQA | 68.9 | 405 | 33th | |
| HellaSwag | 77.4 | 410 | 32th | |
| MMMU | 61.5 | 416 | 31th | |
| Arena Elo | 1310.0 | 409 | 32th |
What ERNIE 4.5 Nano is good for
ERNIE 4.5 Nano 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 $6.01 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.
- Average benchmark score is below the index median; test it on your own task.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Sonar Pro Nano | Perplexity | 32768 | $5.50 | 66.1 |
| ERNIE 4.5 Nano | Baidu | 32768 | $6.01 | 65.6 |
| Reka Flash Mini | Reka AI | 16384 | $5.77 | 65.5 |
| Nova Pro Nano | Amazon | 8192 | $5.44 | 65.4 |
| Embed 4 Reasoning | Cohere | 4096 | $5.50 | 65.3 |
| StableLM 2 Instruct | Stability AI | 16384 | $1.93 | 65.2 |
FAQ
How much does ERNIE 4.5 Nano cost?
ERNIE 4.5 Nano is listed at $6.01 per million input tokens and $22.92 per million output tokens. Cached input is $0.74 per million tokens. A blended 3:1 input-to-output mix is about $10.24 per million tokens.
What is the context window of ERNIE 4.5 Nano?
ERNIE 4.5 Nano 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 Nano open weights?
No. ERNIE 4.5 Nano is a proprietary model with a proprietary licence, so you cannot download the weights.
How does ERNIE 4.5 Nano score on benchmarks?
ERNIE 4.5 Nano averages 65.6 across the scored benchmarks in this index, ranking #397 of 600 models. Its strongest relative result is Arena Elo at 1310.0.
What is ERNIE 4.5 Nano best for?
ERNIE 4.5 Nano 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 $6.01 per million input tokens with a 32,768-token window, check its benchmark profile against the specific task before committing.