Together AI
InferenceFREE TIEROpen-source model inference — Llama, Mixtral, FLUX
Operational
All systems responding normally
Last checked 13/09/2026, 12:52:59 pm
796ms response
Uptime History100.00% uptime
2026-09-11Today
Uptime
100.00%
Avg Latency
799ms
P95 Latency
1033ms
Fastest
503ms
Checks
150
Response Time
Last 60 checks503ms min799ms avg1122ms max
💰 Pricing
llama-3.3-70b-turbo
Input: $0.88/1MOutput: $0.88/1M
Free $1 credit on signup
⚡ Rate Limits
standard
RPM: 60
Limits vary by model and account tier.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B Turbo Open-source model inference. Fast and reliable. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
796ms13 Sept, 12:52 pm
Operational
924ms13 Sept, 12:45 pm
Operational
845ms13 Sept, 12:28 pm
Operational
1122ms13 Sept, 11:59 am
Operational
741ms13 Sept, 11:40 am
Operational
1071ms13 Sept, 11:14 am
Operational
809ms13 Sept, 10:35 am
Operational
566ms13 Sept, 09:52 am
Operational
834ms13 Sept, 09:42 am
Operational
667ms13 Sept, 09:35 am
Operational
879ms13 Sept, 09:20 am
Operational
670ms13 Sept, 09:09 am
Operational
1023ms13 Sept, 08:53 am
Operational
949ms13 Sept, 08:43 am
Operational
997ms13 Sept, 08:35 am
Other Inference Providers
Groq
LPU inference — fastest tokens per second on the market
Cerebras
Wafer-scale chip inference — 1,000+ tokens/sec
Fireworks AI
Fast open-model inference — FireFunction, Llama, Mixtral
OpenRouter
Unified API across 200+ models — route by price or speed
Hugging Face
Serverless inference API — 100k+ open models on demand
fal.ai
Ultra-fast image & video model inference for agents