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	$0.31 input /$ 0.94 output per 1M tokens

Mercury 2 specifications

Spec	Value
Provider	Inception
Released	Feb 20, 2026
Privacy	Anonymized
Context window	125K 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.

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"
  }'

Mercury 2 API FAQ

How much does the Mercury 2 API cost?

0.31 per 1M input tokens and

0.94 per 1M output tokens, with cached input at $0.031 per 1M. Prices are in USD and can be paid in DIEM at parity.

What is the Mercury 2 model ID?

Use mercury-2 as the model parameter.

Is the Mercury 2 API private?

Mercury 2 is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

What is the context window of Mercury 2?

125K tokens of context, with up to 50K output tokens per response.

What does Mercury 2 support?

Mercury 2 supports function calling, structured outputs, reasoning, web search and prompt caching. Reasoning effort is adjustable with reasoning_effort: none, low, medium and high (default high).

Which endpoint does the Mercury 2 API use?

Call POST /chat/completions. /responses (Alpha) is also supported.

Related models

Mercury 2.5 API: $0.05 input /$ 0.19 output per 1M tokens
MiniMax M2.5 API: $0.27 input /$ 0.95 output per 1M tokens
Qwen 3.5 35B A3B API: $0.31 input /$ 1.25 output per 1M tokens
Qwen3 VL 30B A3B API: $0.25 input /$ 0.90 output per 1M tokens
MiniMax M3 Preview API: $0.30 input /$ 1.20 output per 1M tokens

Explore

By modality