Models
Llama 3.3 70B
This model delivers enhanced performance for chat, coding, instruction following, mathematics, and reasoning use cases.
Context Length
Free Tier8,192 tokens
Paid TiersUp to 64k
Speed
~2100
tokens/sec
Input / Output
Input Formats JSON, plain text
Output FormatsJSON, plain text, structured
Model Notes
Model ID:
llama3.3-70b
Available through our Hugging Face InferenceClient.
Rate Limits
Tier | Requests/min | Input Tokens/min | Output Tokens/min | Daily Tokens |
---|---|---|---|---|
Free | 30 | 60k | - | 1M |
1 | 300 | 300k | 30k | 41M |
2 | 600 | 600k | 60k | 85M |
3 | 1000 | 1M | 100k | 140M |
4 | 1200 | 1.2M | 120k | 190M |
5 | 1450 | 1.45M | 145k | 275M |
Endpoints
Chat Completions
Completions
Features
Streaming
Structured Outputs
Streaming w/ Structured Outputs
Tool Calling
Parallel Tool Calling
Top P
Temperature
Max Completion Tokens
Logit Probabilities
Need Higher Limits?
Reach out for custom pricing with our Enterprise tier for higher rate limits and dedicated support.
Contact Sales