Head-to-Head Pricing Benchmark
Side-by-side pricing and context window comparison for production model selection.
Default Recommendation (120M input + 60M output)
Google: Gemma 4 31B is lower-cost for the default monthly workload scenario.
Adjust the workload in the calculator below to see a live recommendation for your usage.
| Metric | Google: Gemma 4 31B | Baidu: ERNIE 4.5 VL 28B A3B |
|---|---|---|
| Developer | baidu | |
| Context Window | 262,144 | 30,000 |
| Max Output Tokens | 131,072 | 8,000 |
| Input Cost / 1M Tokens | $0.1400 | $0.1400 |
| Output Cost / 1M Tokens | $0.4000 | $0.5600 |
| Projected Monthly Cost | $41 | $50 |
| Vision | ✅ Yes | ✅ Yes |
| Tool Calling | ❌ No | ✅ Yes |
| Structured Output | ✅ Yes | ❌ No |
| Reasoning | ✅ Yes | ✅ Yes |
| Web Search | ❌ No | ❌ No |
| Tokenizer | Gemini | Other |
| MMLU Score | N/A | N/A |
Price History
Not enough data yet. Price tracking started recently — check back in a few days.
Price History
Current Input / 1M
$0.1400
Current Output / 1M
$0.5600
Adjust your workload to see projected monthly costs.
Google: Gemma 4 31B
$41
per month
Lower costBaidu: ERNIE 4.5 VL 28B A3B
$50
per month
Live Recommendation
Google: Gemma 4 31B is lower-cost at 120M input + 60M output tokens/month.
Continue evaluation with more “A vs B pricing” decision pages.