Mercury 2

openrouter/inception/mercury-2 · family mercury · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.38Blended $/1M (3:1)

$0.25Input $/1M

$0.75Output $/1M

$1.001M in + 1M out

$0.025 −90%Cache read $/1M

#1887 of 5,000Cheapest rank

Provider: OpenRouter (openrouter)
Context: 128,000 tokens
Max output: 50,000 tokens
Capabilities: toolsreasoningtext

Same model, other providers

“Mercury 2” is offered by 5 providers — cheapest-effective first. This one (OpenRouter) is the cheapest.

Provider	Input	Output	Blended	Context
OpenRouter (this)	$0.25	$0.75	$0.38	128k
NanoGPT	$0.25	$0.75	$0.38	128k
Inception	$0.25	$0.75	$0.38	128k
Vercel AI Gateway	$0.25	$0.75	$0.38	128k
Venice AI	$0.3125	$0.9375	$0.47	128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at OpenRouter and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"inception/mercury-2","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):