Mercury 3 pricing
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... Below you will find 1 current row with input and output dollars per million. Right now the lowest input is $0.100 and the lowest output is $0.350.
Pricing across providers
Use this table to read Mercury 3 list prices. We show 1 source right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
O Openrouter | $0.100 | $0.350 | — | — |
Input vs output · 1M tokens
Cost calculator
The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Mercury 3 cost scales with traffic.
0.010000¢ / req
0.017500¢ / req
Model specifications
These fields describe Mercury 3 as we store it (source: Inception). They sit next to price so buyers can check limits and tools in one place.
- Context window
- 1,000,000 tokens
- Max output
- 131,072 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Oct 2026
- Primary provider
- Inception
- Model family
- N/A
Compare Mercury 3
These links open full side by side pages for Mercury 3. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular Mercury 3 comparisons
- Mercury 3 vs GPT-4o
Compare pricing side by side
- Mercury 3 vs Claude Sonnet 4.6
Compare pricing side by side
- Mercury 3 vs Gemini 2.0 Flash
Compare pricing side by side
- Mercury 3 vs Llama 3.1 70B
Compare pricing side by side
- Mercury 3 vs Mistral 7B
Compare pricing side by side
- Mercury 3 vs GLM 4.7
Compare pricing side by side
Frequently asked questions
Answers pull from the same numbers you see on this page. The short model note from our index: 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...
Related models
Models close to Mercury 3 by family, provider, and context window — each with live pricing in our catalog.