Mercury 3: Inception diffusion LLM API
Mercury 3 is Inception's diffusion LLM. Launch price is $0.10 per 1M input tokens and $0.35 per 1M output. Chat context is 1 million tokens.
Key features
- Answers chat requests with a 1 million token context window
- Calls tools and returns structured outputs
- Writes up to 131,072 tokens in one response
- Charges $0.10 per 1M input tokens and $0.35 per 1M output at launch
- Lists pre-discount rates of $0.20 input and $0.70 output per 1M tokens
- Prices cached input at $0.01 per 1M tokens at launch, from a listed $0.02
- Includes 100 million free tokens with a new API key
- Works with OpenAI-compatible clients
- Category
- LLM APIs
- Who it's for
- Developers who call a diffusion language model from an API.
- Tags
- apillmllm-api
- Website
- inceptionlabs.ai
- Listed
- 2026-10-20
Frequently asked questions
What is Mercury 3 used for?
Inception's diffusion LLM for chat. Launch price is $0.10 per 1M input tokens and $0.35 per 1M output. Typical uses: answers chat requests with a 1 million token context window; calls tools and returns structured outputs; writes up to 131,072 tokens in one response.
Related in LLM APIs
See all →- Amazon Bedrock AWS API for foundation models, including Anthropic and Amazon models.
- Anthropic Console Console and API for Claude models.
- Azure OpenAI OpenAI models hosted on Microsoft Azure.
- Cohere API for Cohere's command and embed models.
- DeepInfra Hosted inference API for open models.
- DeepSeek DeepSeek's models and API.
