Models
| Model Name | Provider | Latency (ms) | Throughput (req/s) | Accuracy (%) | Cost/1K Tokens (INR) | API Calls | Error Rate (%) | Uptime (%) |
|---|---|---|---|---|---|---|---|---|
| GPT-4o | OpenAI | 320 | 42 | 94.2% | 0.030 | 18,200 | 1.2% | 99.97% |
| Claude 3 Opus | Anthropic | 410 | 35 | 93.8% | 0.028 | 15,600 | 0.9% | 99.99% |
| Gemini Pro | 280 | 48 | 92.5% | 0.025 | 14,700 | 1.8% | 99.95% | |
| Llama 3 70B | Meta | 350 | 40 | 91% | 0.022 | 12,100 | 2.1% | 99.89% |
| Mixtral 8x7B | Mistral | 260 | 55 | 90.3% | 0.020 | 9,800 | 2.5% | 99.85% |
| GPT-4 Turbo | OpenAI | 340 | 45 | 93.1% | 0.032 | 20,400 | 1% | 99.96% |
Total Models
24
+3 this month
Avg Latency
312ms
-8% vs last week
Top Throughput
55 req/s
Mixtral 8x7B
Best Accuracy
94.2%
GPT-4o
Avg Cost/1K tokens
₹0.025
+0.001 from last mth
Latency spread across models (50-350ms)

No comments yet. Be the first!