AI Models Directory
Compare latency, reliability, and rate-limit pressure across popular AI models.
last 60mlast 24hlast 7d
P95 latency
Error rate
Rate limit
Filters
Public data includes the latest 24 hours. Sign in for model comparisons.
Compare models
Compare up to 3 models on latency, error rate, and cost. Sign in to unlock side-by-side views.
| Model | Provider | Status | Reliability | P95 latency | Error rate | Rate limit | Availability | Cost (1M) | Trend |
|---|---|---|---|---|---|---|---|---|---|
| Bedrock (Claude) | AWS Bedrock | Degraded | 86/100 | 1410 ms | 0.45% | 2.10% | 99.55% | $3.80 | |
| Claude 3 Haiku | Anthropic | OK | 96/100 | 600 ms | 0.08% | 0.40% | 99.92% | $0.75 | |
| Claude 3 Opus | Anthropic | OK | 90/100 | 1040 ms | 0.18% | 0.70% | 99.82% | $4.90 | |
| Claude 3.5 Sonnet | Anthropic | OK | 93/100 | 820 ms | 0.10% | 0.50% | 99.90% | $9.00 | |
| Azure GPT‑4o | Azure OpenAI | OK | 93/100 | 870 ms | 0.09% | 0.40% | 99.91% | $3.70 | |
| Command R | Cohere | OK | 92/100 | 870 ms | 0.22% | 0.70% | 99.78% | $1.00 | |
| Command R+ | Cohere | OK | 92/100 | 920 ms | 0.20% | 0.60% | 99.80% | $9.00 | |
| Llama 3.1 70B | Fireworks | OK | 92/100 | 920 ms | 0.26% | 0.90% | 99.74% | $1.10 | |
| Gemini 1.5 Pro | OK | 91/100 | 980 ms | 0.10% | 0.60% | 99.90% | $2.80 | ||
| Gemini 2.0 Flash | OK | 93/100 | 780 ms | 0.20% | 0.70% | 99.80% | $0.25 | ||
| Gemini 2.0 Flash-Lite | OK | 95/100 | 650 ms | 0.22% | 0.60% | 99.78% | $0.19 | ||
| Llama 3.1 8B (Groq) | Groq | OK | 98/100 | 320 ms | 0.35% | 0.90% | 99.65% | $0.07 | |
| Llama 3.3 70B (Groq) | Groq | OK | 97/100 | 450 ms | 0.40% | 1.20% | 99.60% | $0.69 | |
| Mistral Large | Mistral | OK | 92/100 | 910 ms | 0.21% | 0.80% | 99.79% | $2.10 | |
| Mistral Large 3 | Mistral | OK | 92/100 | 900 ms | 0.30% | 0.80% | 99.70% | $1.00 | |
| Mistral Medium 3.1 | Mistral | OK | 93/100 | 850 ms | 0.25% | 0.70% | 99.75% | $1.20 | |
| GPT-4o | OpenAI | OK | 91/100 | 950 ms | 0.15% | 0.80% | 99.85% | $6.25 | |
| GPT-4o mini | OpenAI | OK | 94/100 | 700 ms | 0.10% | 0.60% | 99.90% | $0.38 | |
| GPT‑4.1 | OpenAI | OK | 92/100 | 920 ms | 0.12% | 0.90% | 99.88% | $3.60 | |
| Llama 3.1 405B | Together | OK | 89/100 | 1160 ms | 0.30% | 1.00% | 99.70% | $2.40 |
Need model-level alerts?
Track reliability changes and route traffic to healthier models.