Provider Overview
Type
inference
Billing
Per token
Egress
Free
SLA Uptime
99.9%
Autoscaling
Yes
Cold Start
None
Model Pricing (10)
| Model | Input $/M | Output $/M | Latency | Throughput | Context |
|---|---|---|---|---|---|
| llama-3.1-8bCheapest | $0.05 | $0.08 | 0.05s | 1250 t/s | 128k |
| qwen-2.5-7b | $0.05 | $0.08 | 0.05s | 1100 t/s | 32k |
| phi-3-mini-128k | $0.05 | $0.08 | 0.04s | 1300 t/s | 128k |
| gemma-2-9b | $0.20 | $0.20 | 0.06s | 900 t/s | 8k |
| mixtral-8x7b | $0.24 | $0.24 | 0.08s | 575 t/s | 33k |
| qwen-2.5-32b | $0.40 | $0.40 | 0.1s | 400 t/s | 32k |
| gemma-2-27b | $0.50 | $0.50 | 0.08s | 500 t/s | 8k |
| llama-3.3-70b | $0.59 | $0.79 | 0.1s | 350 t/s | 128k |
| llama-3.1-70b | $0.59 | $0.79 | 0.1s | 330 t/s | 128k |
| deepseek-r1-distill-llama-70b | $0.75 | $0.99 | 0.3s | 275 t/s | 128k |
Reputation Details
Pricing
90
Reliability
90
Features
75
Highlights
- Very competitive token pricing
- 99.9%+ SLA
- Autoscaling supported
- Fast cold start
Compare with Others
| Provider | Overall | Pricing | Reliability | Features | Models |
|---|---|---|---|---|---|
| Groq | 86 | 90 | 90 | 75 | 10 |
| Together AI | 78 | 70 | 90 | 75 | 20 |
| Fireworks AI | 78 | 70 | 90 | 75 | 14 |
| DeepInfra | 86 | 90 | 90 | 75 | 21 |
| DeepSeek | 72 | 70 | 70 | 75 | 3 |