ERNIE 4.0 Turbo: pricing, context window and benchmarks
ERNIE 4.0 Turbo is a multimodal model from Baidu. It offers a 65,536-token context window, costs $12.00 per million input tokens and $55.04 per million output tokens, and averages 78.0 across the index's benchmark suite.
Pricing
ERNIE 4.0 Turbo costs $12.00 per million input tokens and $55.04 per million output tokens. A blended 3:1 input-to-output mix works out to about $22.76 per million tokens. Cached input is listed at $1.30 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $12.00 | per 1M tokens |
| Output | $55.04 | per 1M tokens |
| Cached input | $1.30 | per 1M tokens |
| Blended 3:1 | $22.76 | estimate per 1M tokens |
| 1M in + 1M out | $67.04 | 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 | 80.5 | 168 | 72th | |
| GPQA Diamond | 76.2 | 115 | 81th | |
| SWE-bench Verified | 64.7 | 217 | 64th | |
| HumanEval | 82.6 | 168 | 72th | |
| MATH-500 | 82.0 | 167 | 72th | |
| AIME 2025 | 72.6 | 207 | 66th | |
| LiveCodeBench | 71.9 | 147 | 76th | |
| IFEval | 85.2 | 182 | 70th | |
| TruthfulQA | 79.0 | 216 | 64th | |
| HellaSwag | 87.0 | 176 | 71th | |
| MMMU | 76.8 | 115 | 81th | |
| Arena Elo | 1422.9 | 134 | 78th |
What ERNIE 4.0 Turbo is good for
ERNIE 4.0 Turbo 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 $12.00 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.
Strengths
- 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 $12.00 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-Coder | DeepSeek | 32768 | $4.55 | 78.1 |
| Gemini 3 Pro Mini | Google DeepMind | 128000 | $12.27 | 78.1 |
| Hunyuan-Large Chat | Tencent | 200000 | $4.35 | 78.1 |
| Qwen3-Coder Instruct | Alibaba Cloud | 128000 | $4.66 | 78.1 |
| ERNIE 4.0 Turbo | Baidu | 65536 | $12.00 | 78.0 |
| Llama 4 Scout Chat | Meta AI | 32768 | $4.66 | 78.0 |
FAQ
How much does ERNIE 4.0 Turbo cost?
ERNIE 4.0 Turbo is listed at $12.00 per million input tokens and $55.04 per million output tokens. Cached input is $1.30 per million tokens. A blended 3:1 input-to-output mix is about $22.76 per million tokens.
What is the context window of ERNIE 4.0 Turbo?
ERNIE 4.0 Turbo has a context window of 65,536 tokens and can emit up to 4,096 output tokens per request in this index.
Is ERNIE 4.0 Turbo open weights?
No. ERNIE 4.0 Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does ERNIE 4.0 Turbo score on benchmarks?
ERNIE 4.0 Turbo averages 78.0 across the scored benchmarks in this index, ranking #173 of 600 models. Its strongest relative result is Arena Elo at 1422.9.
What is ERNIE 4.0 Turbo best for?
ERNIE 4.0 Turbo 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 $12.00 per million input tokens, it sits in the mid-range of the index, and the 65,536-token context window is enough for large files and multi-file diffs.