ArliAI

ArliAI

ID
34 models available

Models served by ArliAI

ModelContextInput /MOutput /MLatencyThroughput
262k$0.19/M$0.19/M27.5s23.5 tps
262k$0.19/M$0.19/M47.9s44.4 tps
262k$0.19/M$0.19/MN/AN/A
262k$0.19/M$0.19/M7.5s33.5 tps
262k$0.19/M$0.19/MN/AN/A
262k$0.19/M$0.19/M22.4s28.6 tps
262k$0.19/M$0.19/M27.9s38.5 tps
262k$0.19/M$0.19/M22.1s33.7 tps
262k$0.19/M$0.19/M35.7s20.6 tps
262k$0.19/M$0.19/M13.1s43 tps
262k$0.19/M$0.19/M15.9s21.6 tps
262k$0.19/M$0.19/M27.5s23.5 tps
262k$0.19/M$0.19/M47.9s44.4 tps
262k$0.19/M$0.19/M18s26 tps
262k$0.19/M$0.19/M22.9s32.1 tps
262k$0.19/M$0.19/M35.6s24.9 tps
262k$0.19/M$0.19/M22.5s55.9 tps
262k$0.19/M$0.19/M40.8s27.5 tps
262k$0.19/M$0.19/MN/AN/A
262k$0.19/M$0.19/M17.2s23 tps
262k$0.19/M$0.19/M55.6s20.6 tps
262k$0.19/M$0.19/M39.2s11.5 tps
262k$0.19/M$0.19/MN/A11.6 tps
262k$0.19/M$0.19/M30.2s24.1 tps
262k$0.19/M$0.19/M38.2s34.1 tps
131k$0.25/M$0.93/M13.3s24.4 tps
262k$0.19/M$0.19/M20.3s16.2 tps
262k$0.19/M$0.19/MN/AN/A
262k$0.19/M$0.19/M44.5s8.6 tps
262k$0.19/M$0.19/M22.9s5.2 tps
262k$0.19/M$0.19/M10.5s17.4 tps
262k$0.19/M$0.19/M19.5s18.3 tps
262k$0.19/M$0.19/M5.8s21.6 tps
262k$0.19/M$0.19/M9.5s14.1 tps

Prices are per million tokens. Selectable routes include the applicable provider-selection markup; fixed routes show the standard model price. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using ArliAI via the API

For models with provider selection, append :arliai to the model ID, set "provider": "arliai" in the request body, or send an X-Provider: arliai header. Explicit provider selection adds a route-specific markup over that provider's base price; the prices in the table above already include it. Models without provider selection use the displayed model ID without a provider suffix or selection surcharge.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemma-4-31b-it-darkidol:arliai",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.