Head-to-Head Pricing Benchmark
Side-by-side pricing and context window comparison for production model selection.
Default Recommendation (120M input + 60M output)
DeepSeek: R1 Distill Qwen 32B 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 | DeepSeek: R1 Distill Qwen 32B | Baidu: ERNIE 4.5 300B A47B |
|---|---|---|
| Developer | deepseek | baidu |
| Context Window | 32,768 | 123,000 |
| Max Output Tokens | 32,768 | 12,000 |
| Input Cost / 1M Tokens | $0.2900 | $0.2800 |
| Output Cost / 1M Tokens | $0.2900 | $1.10 |
| Projected Monthly Cost | $52 | $100 |
| Vision | ❌ No | ❌ No |
| Tool Calling | ❌ No | ❌ No |
| Structured Output | ✅ Yes | ❌ No |
| Reasoning | ✅ Yes | ❌ No |
| Web Search | ❌ No | ❌ No |
| Tokenizer | Qwen | Other |
| MMLU Score | 73.9 | 77.6★ |
| GPQA | 61.5 | 81.1★ |
Price History
Current Input / 1M
$0.2900
Current Output / 1M
$0.2900
Price History
Current Input / 1M
$0.2800
Current Output / 1M
$1.10
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
Adjust your workload to see projected monthly costs.
DeepSeek: R1 Distill Qwen 32B
$52
per month
Lower costBaidu: ERNIE 4.5 300B A47B
$100
per month
Live Recommendation
DeepSeek: R1 Distill Qwen 32B is lower-cost at 120M input + 60M output tokens/month.
Continue evaluation with more “A vs B pricing” decision pages.