Mercury Coder Small Beta

inception/mercury-coder-small

A chat model with a 32K-token context window, at $0.2625 per million input tokens and $1.05 per million output tokens.

Details

Maker: inception
Kind: Chat
Context window: 32,000 tokens
Max output: 16,384 tokens
Input: $0.2625 per million tokens
Output: $1.05 per million tokens
Capabilities: Tool use
Takes: Text
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2025-02-26
Newer model: inception/mercury-2.5Released later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Mercury Coder Small is ideal for code generation, debugging, and refactoring tasks with minimal latency.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "inception/mercury-coder-small",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model