Provider Overview
Type
inference
Billing
Per token
Egress
Free
SLA Uptime
99.5%
Autoscaling
Yes
Cold Start
None
Model Pricing (9)
| Model | Input $/M | Output $/M | Latency | Throughput | Context |
|---|---|---|---|---|---|
| llama-3.1-8bCheapest | $0.06 | $0.06 | 0.2s | 180 t/s | 128k |
| qwen-2.5-7b | $0.06 | $0.06 | 0.15s | 180 t/s | 32k |
| mixtral-8x7b | $0.20 | $0.20 | 0.2s | 110 t/s | 33k |
| deepseek-v3 | $0.30 | $0.30 | 0.35s | 70 t/s | 64k |
| llama-3.1-70b | $0.40 | $0.40 | 0.35s | 80 t/s | 128k |
| llama-3.3-70b | $0.40 | $0.40 | 0.3s | 85 t/s | 128k |
| qwen-2.5-72b | $0.40 | $0.40 | 0.35s | 75 t/s | 32k |
| llama-3.1-405b | $2.00 | $2.00 | 0.8s | 30 t/s | 128k |
| deepseek-r1 | $1.50 | $4.00 | 2.5s | 25 t/s | 64k |
Reputation Details
Pricing
70
Reliability
70
Features
75
Highlights
- Good pricing
- Autoscaling supported
- Fast cold start
Compare with Others
| Provider | Overall | Pricing | Reliability | Features | Models |
|---|---|---|---|---|---|
| Hyperbolic | 72 | 70 | 70 | 75 | 9 |
| Together AI | 78 | 70 | 90 | 75 | 20 |
| Fireworks AI | 78 | 70 | 90 | 75 | 14 |
| Groq | 86 | 90 | 90 | 75 | 10 |
| DeepInfra | 86 | 90 | 90 | 75 | 21 |