Mercury 2 API

Inception's Mercury 2, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send mercury-2 as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: mercury-2
Maker: Inception
Context window: 128K tokens
Input price: $0.250 per million tokens
Output price: $0.750 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.250 input and $0.750 output per million tokens, $0.025 cache read per million tokens, 128K tokens of context

Scores

HLE: 17.1, #127 of 273
GPQA: 77.0, #120 of 250
AA-LCR: 43.7, #178 of 237
SciCode: 37.7, #104 of 123
Terminal-Bench Hard: 26.5, #66 of 166
τ²-Bench: 70.8, #80 of 169
IFBench: 69.8, #42 of 178

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mercury-2",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Mercury 2?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Mercury 2 cost?: Offers now ask $0.250 per million input tokens and $0.750 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Mercury 2?: The largest offer takes 128,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Mercury 2 do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Mercury 2 support?: Text → Text.
Which providers serve Mercury 2?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Mercury 2?: Send "mercury-2" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Mercury 2 listed?: The exchange first listed it on 10/8/2026. This is not its release date.