DeepInfra

DeepInfra

Inference

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

Operational

All systems responding normally

Last checked 09/06/2026, 5:29:51 am

588ms response

Uptime History100.00% uptime
2026-06-02Today

Uptime

100.00%

Avg Latency

657ms

P95 Latency

896ms

Fastest

440ms

Checks

150

Response Time

Last 60 checks
440ms min657ms avg1247ms 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
588ms9 June, 05:29 am
Operational
587ms9 June, 04:32 am
Operational
690ms9 June, 03:38 am
Operational
595ms9 June, 02:33 am
Operational
726ms9 June, 01:01 am
Operational
615ms8 June, 11:49 pm
Operational
690ms8 June, 10:16 pm
Operational
544ms8 June, 08:38 pm
Operational
564ms8 June, 06:51 pm
Operational
610ms8 June, 05:07 pm
Operational
528ms8 June, 03:22 pm
Operational
665ms8 June, 01:47 pm
Operational
802ms8 June, 12:21 pm
Operational
708ms8 June, 12:21 pm
Operational
682ms8 June, 11:23 am