inception
Inception: Mercury 3
inception/mercury-3
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...
Prices updated: 10/22/2026
Input
11
credits / 1M tokens
Output
39
credits / 1M tokens
Context
1000k
tokens
Messages per $1 USD
≈ 3,300
typical message: 1k tokens in + 500 out
Prices in credits per million tokens. 1 credit = $0.01 USD. Final price, billed in MXN at the exchange rate on payment day + VAT (CFDI). Subject to change without notice.
Additional prices
Cache (read): 1.1 /1M
Spec sheet
- Inputs
- text
- Outputs
- text
- Max output tokens
- 131,072
- Knowledge cutoff
- —
- Tokenizer
- Other
Capabilities
Text / LLM
Tools
JSON
Reasoning
Use it in your code
One OpenAI-compatible endpoint. Switch models by changing one line.
curl https://api.deployalo.com/ai/gateway/v1/chat/completions \
-H "Authorization: Bearer $DEPLOYALO_AI_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"inception/mercury-3","messages":[{"role":"user","content":"Hola"}]}'More models from inception
Ready to use it?
Top up a credit pack, create your API key with a spend cap and start in minutes.