jishie

Trinity Large Thinking

nano-gpt/arcee-ai/trinity-large-thinking · family trinity · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.41
Blended $/1M (3:1)
$0.25
Input $/1M
$0.9
Output $/1M
$1.15
1M in + 1M out
$0.125 −50%
Cache read $/1M
#2513 of 7,708
Cheapest rank
Provider
NanoGPT (nano-gpt)
Kind
text (outputs text)
Context
262,144 tokens
Max output
80,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“Trinity Large Thinking” is offered by 5 providers — cheapest-effective first. Kilo Gateway is the cheapest at $0.39 blended.

ProviderInputOutputBlendedContext
Kilo Gateway$0.25$0.8$0.39262k
OpenRouter$0.25$0.8$0.39262k
Arcee$0.25$0.8$0.39262k
NanoGPT (this)$0.25$0.9$0.41262k
Vercel AI Gateway$0.25$0.9$0.41262k

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":"arcee-ai/trinity-large-thinking","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