> ## Documentation Index
> Fetch the complete documentation index at: https://docs.venice.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Mercury 2 API

> Mercury 2 API on Venice: 128K context, $0.3125 input and $0.9375 output per 1M tokens. Anonymized access without your identity.

> [accordion] Plain-text specification
>
> ## Mercury 2 API
>
> Mercury 2 is a large language model by Inception, available on the Venice API as `mercury-2`. Requests are anonymized, so the provider never sees your identity.
>
> Mercury 2 is a diffusion-based reasoning LLM from Inception, delivering over 1,000 tokens per second — 5x faster than leading speed-optimized models — with strong reasoning, tool use, and structured output capabilities.
>
> ### Mercury 2 API pricing
>
> | Model ID | Variant | Privacy | Price |
> | - | - | - | - |
> | `mercury-2` | Standard | Anonymized | $0.3125 / $0.9375 per 1M |
>
> ### Mercury 2 specifications
>
> | Spec | Value |
> | - | - |
> | Provider | Inception |
> | Released | Feb 20, 2026 |
> | Privacy | Anonymized |
> | Status | Stable |
> | Context window | 128K tokens |
> | Max output | 50K tokens |
> | Reasoning effort | none, low, medium, high |
>
> ### How to use the Mercury 2 API
>
> Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "mercury-2"` and your API key.
>
> ```bash theme={"system"}
> curl https://api.venice.ai/api/v1/chat/completions \
>   -H "Authorization: Bearer $VENICE_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "mercury-2",
>     "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
>     "reasoning_effort": "high"
>   }'
> ```
>
> ### Related models
>
> * [Mercury 3 API](https://docs.venice.ai/models/mercury-3.md): $0.10 / $0.35 per 1M
> * [Mercury 2.5 API](https://docs.venice.ai/models/mercury-2-5.md): $0.25 / $0.9375 per 1M
> * [MiniMax M2.5 API](https://docs.venice.ai/models/minimax-m2-5.md): $0.27 / $0.95 per 1M
> * [Qwen3 VL 30B A3B API](https://docs.venice.ai/models/qwen3-vl-30b-a3b.md): $0.25 / $0.90 per 1M
> * [GPT-5.6 Luna API](https://docs.venice.ai/models/gpt-5-6-luna.md): $0.20 / $1.20 per 1M
> * [GPT-5.6 Luna Pro API](https://docs.venice.ai/models/gpt-5-6-luna-pro.md): $0.20 / $1.20 per 1M


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.