Inception: Mercury 3
InceptionNew
inception/mercury-3About this model
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
Make a request
OpenAI-compatible: set the base URL and your Promptix API key, keep your existing SDK.
curl https://promptix.tn/api/v1/chat/completions \ -H "Authorization: Bearer $PROMPTIX_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "inception/mercury-3", "messages": [ {"role": "user", "content": "Hello! What can you do?"} ] }'Pricing
In TND per 1M tokens. VAT and the platform fee are added at top-up.
Input tokens
0.387 TNDper 1M tokens
Output tokens
1.355 TNDper 1M tokens
1,000 requests with 1K input and 500 output tokens cost about 1.065 TND.
Specifications
- Provider
- Inception
- Context window
- 1,000,000 tokens
- Input modality
- Text
- Added
- Oct 16, 2026
- Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstemperature