Fireworks AI
InferenceFREE TIERFast open-model inference — FireFunction, Llama, Mixtral
Operational
All systems responding normally
Last checked 03/08/2026, 11:47:04 pm
202ms response
Uptime History100.00% uptime
2026-07-30Today
Uptime
100.00%
Avg Latency
181ms
P95 Latency
240ms
Fastest
65ms
Checks
150
Response Time
Last 60 checks65ms min181ms avg282ms max
💰 Pricing
llama-v3p3-70b-instruct
Input: $0.9/1MOutput: $0.9/1M
Free tier: 40 req/min up to 10k tokens
⚡ Rate Limits
free
RPM: 40TPM: 10,000Concurrent: 5
Free tier. Paid plans remove limits.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Llama 3.3 70B Instruct Fast inference. DeepSeek and Qwen also available. | llm | 128k | — | ✅ | ✅ |
Recent Checks
Showing last 15Operational
202ms3 Aug, 11:47 pm
Operational
172ms3 Aug, 10:48 pm
Operational
179ms3 Aug, 09:43 pm
Operational
214ms3 Aug, 08:28 pm
Operational
199ms3 Aug, 07:09 pm
Operational
147ms3 Aug, 05:51 pm
Operational
183ms3 Aug, 04:30 pm
Operational
197ms3 Aug, 03:15 pm
Operational
132ms3 Aug, 01:54 pm
Operational
237ms3 Aug, 12:35 pm
Operational
160ms3 Aug, 11:37 am
Operational
185ms3 Aug, 10:54 am
Operational
109ms3 Aug, 10:01 am
Operational
193ms3 Aug, 09:34 am
Operational
174ms3 Aug, 09:09 am
Other Inference Providers
Groq
LPU inference — fastest tokens per second on the market
Cerebras
Wafer-scale chip inference — 1,000+ tokens/sec
Together AI
Open-source model inference — Llama, Mixtral, FLUX
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