- Input
- $0.69/M
- Output
- $2.76/M
- Cache read
- $0.16/M
- Context
- 262.1K
- Max output
- 182.5K
EndpointsChat Completion
/v1/chat/completionsResponses /v1/responsesMessages /v1/messagesGemini Call this model.
curl https://api.freetheai.org/v1/chat/completions \
-H "Authorization: Bearer $FTAI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-3-ultra-550b-a55b",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'Replace $FTAI_KEY with your API key. Get one at the quickstart page.
What you would pay.
- 1,000 input tokens
- ~$0.0007
- 1,000 output tokens
- ~$0.0028
- 100 requests (500 in + 200 out each)
- ~$0.09
Estimates based on listed per-token pricing. Cache discounts apply for repeated prompts.
Community rating
Votes from people who have used this model through FreeTheAI. One vote per account; you can change it anytime.
No votes yet.
Sign in to rate models you have used.