← All models
Try in Chat
LLaMA 3.3 70B
llama-3.3-70b-instruct
Meta's open-weight 70B parameter model. Available on multiple EU providers.
chatreasoningcodetools
pricing
this model runs at 2 EU providers. you pay the price of the provider that serves your request, ozeye's margin included. the usage dashboard shows which provider served each request, and you can block providers in your settings. prices excl. VAT.
| provider | location | input | cached input | output | context window |
|---|---|---|---|---|---|
| OVHcloud | Gravelines, France | €0.7504/M | as input | €0.7504/M | 128K |
| Scaleway | Paris, France | €1.008/M | as input | €1.008/M | 128K |
OVHcloud Gravelines, France
- input
- €0.7504/M
- cached input
- as input
- output
- €0.7504/M
- context
- 128K
Scaleway Paris, France
- input
- €1.008/M
- cached input
- as input
- output
- €1.008/M
- context
- 128K
Specifications
Context window
128K
Providers
2
Released
Dec 2024
Try LLaMA 3.3 70B
Use this model directly in the ozeye chat interface.
Benchmarks
Scores on standardized evaluations. Higher percentages are better. Rank percentile shows where this model lands among all models on ozeye.
Coding
Python function generation
78.0%
Better than 70% of models
Knowledge
Massive Multitask Language Understanding
86.0%
Better than 88% of models
Latency
Loading latency data...
API
curl https://ozeye.ai/v1/chat/completions \
-H "Authorization: Bearer $OZEYE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b-instruct",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'