Llama 3.2 3B Instruct: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Cloudflarecloudflare | Healthy | 100%◆ (best) | 99.67% | 97.01% | 98.22% | 143ms◆ (best) | 1.02s◆ (best) | 197 tps◆ (best) | 80K | $0.051 / $0.335 |
| Healthy | 100%◆ (best) | 99.99% | 99.99%◆ (best) | 99.96%◆ (best) | 426ms | 1.41s | 185 tps | 131K | $0.050 / $0.330◆ (best) |
- Cloudflare100%◆ (best)Healthy24h 99.67%
- 7d
- 97.01%
- 30d
- 98.22%
- p50
- 143ms◆ (best)
- p99
- 1.02s◆ (best)
- Throughput
- 197 tps◆ (best)
- Context
- 80K
- $/Mtok
- $0.051 / $0.335
cloudflare - Parasail100%◆ (best)Healthy24h 99.99%
- 7d
- 99.99%◆ (best)
- 30d
- 99.96%◆ (best)
- p50
- 426ms
- p99
- 1.41s
- Throughput
- 185 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.330◆ (best)
parasail/bf16bf16
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.