DeepInfra

DeepInfra

Inference

Cheap serverless inference — Llama, Mistral, FLUX at low cost

Operational

All systems responding normally

Last checked 10/06/2026, 1:46:52 pm

706ms response

Uptime History100.00% uptime
2026-06-04Today

Uptime

100.00%

Avg Latency

679ms

P95 Latency

951ms

Fastest

440ms

Checks

150

Response Time

Last 60 checks
440ms min679ms avg1915ms max

💰 Pricing

llama-3.3-70b
Input: $0.23/1MOutput: $0.4/1M

Cheapest 70B inference. meta-llama-3.1-8b: $0.06/$0.06

⚡ Rate Limits

free
RPM: 30TPM: 120,000

Free: 30 RPM, 120K TPM. Paid: up to 1000 RPM.

🤖 Models (1)

ModelTaskContextVisionToolsJSON
Llama 3.3 70B

Cheap inference. $0.23/$0.40 per 1M tokens.

llm128k

Recent Checks

Showing last 15
Operational
706ms10 June, 01:46 pm
Operational
795ms10 June, 12:22 pm
Operational
1319ms10 June, 11:20 am
Operational
758ms10 June, 10:04 am
Operational
724ms10 June, 09:31 am
Operational
717ms10 June, 08:52 am
Operational
619ms10 June, 08:13 am
Operational
749ms10 June, 07:36 am
Operational
836ms10 June, 06:51 am
Operational
628ms10 June, 06:05 am
Operational
629ms10 June, 05:17 am
Operational
567ms10 June, 04:22 am
Operational
615ms10 June, 03:32 am
Operational
699ms10 June, 02:42 am
Operational
498ms10 June, 01:42 am