GeniusRelay
EN中文Sign upConsole

Inception: Mercury Coder Small

mercury-coder-small

CompareAPIGet an API keyGet an API key

Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.

Modalities

Text → Text

Input / output price

$0.325 / $1.30 per 1M

Context

33K · max output 16K

Capabilities

Coding

Pricing

Billed per token actually used and deducted from your credits.

ItemUSD per 1M tokens
Input$0.325
Output$1.30
Cached input$0.163

Calculator

Drag the sliders to estimate what this model will cost.

Per request
$0.00201
Per day
$1.01
Per month (30 days)
$30.22

Mercury Coder Small: input $0.325/M · output $1.3/M · cached input $0.1625/M

Request with these settings
curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mercury-coder-small", "max_tokens": 800,
       "messages": [{"role": "user", "content": "…"}]}'

Code samples

OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to mercury-coder-small.

curl https://api.geniusrelaygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mercury-coder-small",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Use it in a client: Cursor · Cline · SillyTavern · Codex

Parameters

Common OpenAI parameters can be passed as-is.

temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseed

FAQ

How is Mercury Coder Small billed?
Input is $0.325 and output is $1.30 per million tokens; cached input is $0.163. The charge for every request is listed in Usage Logs in the console.
How long is the context window?
33K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
Does it support streaming?
Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.