jishie

Mercury 2.5 Preview

nano-gpt/inception/mercury-2.5-preview · family mercury · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.07
Blended $/1M (3:1)
$0.04
Input $/1M
$0.15
Output $/1M
$0.19
1M in + 1M out
$0.004 −90%
Cache read $/1M
#730 of 6,998
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
260,000 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text

Same model, other providers

“Mercury 2.5 Preview” is offered by 2 providers — cheapest-effective first. This one (NanoGPT) is the cheapest.

ProviderInputOutputBlendedContext
NanoGPT (this)$0.04$0.15$0.07260k
OpenRouter$0.04$0.15$0.07260k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at NanoGPT 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-2.5-preview","messages":[{"role":"user","content":"hello"}]}'

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

← all NanoGPT models · model index · JSON