ArliAI

34 models available

Data handling can vary by model and deployment. The privacy badge above shows the more conservative of the provider-wide fallback and the policies for routes on this page; each model page shows the policy for that specific route.

Models served by ArliAI

34 models

Model	Context	Input /M	Output /M	TTFT	Throughput
DarkIdol	262k	$0.19/M	$0.19/M	23.3s	15.1 tps
Fabled	262k	$0.19/M	$0.19/M	47.5s	17.8 tps
Garnet	262k	$0.19/M	$0.19/M	20.1s	14.6 tps
Gembrain	262k	$0.19/M	$0.19/M	4.3s	12.1 tps
Gemma 4 31B	262k	$0.19/M	$0.19/M	6.7s	12.4 tps
Gemma 4 31B Agares v1	262k	$0.19/M	$0.19/M	N/A	N/A
Gemma 4 31B Animus V14.1	262k	$0.19/M	$0.19/M	64.3s	17.7 tps
Gemma 4 31B AssGuard	262k	$0.19/M	$0.19/M	14.9s	N/A
Gemma 4 31B Claude 4.6 Opus Reasoning Distilled	262k	$0.19/M	$0.19/M	30.2s	19.2 tps
Gemma 4 31B Cognitive Unshackled	262k	$0.19/M	$0.19/M	53.5s	12 tps
Gemma 4 31B Dark Gemistry	262k	$0.19/M	$0.19/M	15.7s	7.7 tps
Gemma 4 31B DarkIdol	262k	$0.19/M	$0.19/M	23.3s	15.1 tps
Gemma 4 31B Fabled	262k	$0.19/M	$0.19/M	31.6s	13.6 tps
Gemma 4 31B GarnetV2	262k	$0.19/M	$0.19/M	N/A	N/A
Gemma 4 31B Gembrain uncensored heretic	262k	$0.19/M	$0.19/M	14s	11.1 tps
Gemma 4 31B Gembrain X Core	262k	$0.19/M	$0.19/M	85.5s	16.2 tps
Gemma 4 31B Isometry RP	262k	$0.19/M	$0.19/M	22.5s	12.9 tps
Gemma 4 31B K1 v5	262k	$0.19/M	$0.19/M	7.2s	10.7 tps
Gemma 4 31B MeroMero	262k	$0.19/M	$0.19/M	26.9s	14.8 tps
Gemma 4 31B MeroMero v2	262k	$0.19/M	$0.19/M	27.5s	9.8 tps
Gemma 4 31B MeroMero v2 Thinking	262k	$0.19/M	$0.19/M	27.5s	9.8 tps
Gemma 4 31B Novelist	262k	$0.19/M	$0.19/M	30.4s	11.3 tps
Gemma 4 31B Queen	262k	$0.19/M	$0.19/M	22s	16.8 tps
Gemma 4 31B SDFT Heretic RP	262k	$0.19/M	$0.19/M	23.7s	20.6 tps
Gemma 4 31B StyleTune	262k	$0.19/M	$0.19/M	23.3s	22.2 tps
GLM 4.6 Derestricted v5	131k	$0.25/M	$0.93/M	18.4s	30.7 tps
Isometry	262k	$0.19/M	$0.19/M	22.5s	10.4 tps
Musica	262k	$0.19/M	$0.19/M	N/A	N/A
Novelist	262k	$0.19/M	$0.19/M	38.5s	12.3 tps
Qwen3.5 27B Blossom V6.4 Derestricted	262k	$0.19/M	$0.19/M	16.4s	21.9 tps
Qwen3.5 27B BlueStar v3 Derestricted	262k	$0.19/M	$0.19/M	8.6s	23.6 tps
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted	262k	$0.19/M	$0.19/M	6.2s	24.5 tps
Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite	262k	$0.19/M	$0.19/M	7.3s	30.9 tps
Qwen3.5 27B Queen Derestricted	262k	$0.19/M	$0.19/M	6.7s	23.2 tps

DarkIdol

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 23.3s
Throughput: 15.1 tps

Fabled

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 47.5s
Throughput: 17.8 tps

Garnet

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 20.1s
Throughput: 14.6 tps

Gembrain

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 4.3s
Throughput: 12.1 tps

Gemma 4 31B

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 6.7s
Throughput: 12.4 tps

Gemma 4 31B Agares v1

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B Animus V14.1

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 64.3s
Throughput: 17.7 tps

Gemma 4 31B AssGuard

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 14.9s
Throughput: N/A

Gemma 4 31B Claude 4.6 Opus Reasoning Distilled

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 30.2s
Throughput: 19.2 tps

Gemma 4 31B Cognitive Unshackled

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 53.5s
Throughput: 12 tps

Gemma 4 31B Dark Gemistry

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 15.7s
Throughput: 7.7 tps

Gemma 4 31B DarkIdol

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 23.3s
Throughput: 15.1 tps

Gemma 4 31B Fabled

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 31.6s
Throughput: 13.6 tps

Gemma 4 31B GarnetV2

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: N/A
Throughput: N/A

Gemma 4 31B Gembrain uncensored heretic

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 14s
Throughput: 11.1 tps

Gemma 4 31B Gembrain X Core

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 85.5s
Throughput: 16.2 tps

Gemma 4 31B Isometry RP

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 22.5s
Throughput: 12.9 tps

Gemma 4 31B K1 v5

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 7.2s
Throughput: 10.7 tps

Gemma 4 31B MeroMero

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 26.9s
Throughput: 14.8 tps

Gemma 4 31B MeroMero v2

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 27.5s
Throughput: 9.8 tps

Gemma 4 31B MeroMero v2 Thinking

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 27.5s
Throughput: 9.8 tps

Gemma 4 31B Novelist

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 30.4s
Throughput: 11.3 tps

Gemma 4 31B Queen

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 22s
Throughput: 16.8 tps

Gemma 4 31B SDFT Heretic RP

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 23.7s
Throughput: 20.6 tps

Gemma 4 31B StyleTune

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 23.3s
Throughput: 22.2 tps

GLM 4.6 Derestricted v5

Context: 131k
Input /M: $0.25/M
Output /M: $0.93/M
TTFT: 18.4s
Throughput: 30.7 tps

Isometry

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 22.5s
Throughput: 10.4 tps

Musica

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: N/A
Throughput: N/A

Novelist

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 38.5s
Throughput: 12.3 tps

Qwen3.5 27B Blossom V6.4 Derestricted

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 16.4s
Throughput: 21.9 tps

Qwen3.5 27B BlueStar v3 Derestricted

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 8.6s
Throughput: 23.6 tps

Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 6.2s
Throughput: 24.5 tps

Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 7.3s
Throughput: 30.9 tps

Qwen3.5 27B Queen Derestricted

Context: 262k
Input /M: $0.19/M
Output /M: $0.19/M
TTFT: 6.7s
Throughput: 23.2 tps

Prices are per million tokens. TTFT is the observed time to first token. 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

Call a model served by ArliAI using its displayed model ID, including the provider suffix when selection is supported.

cURL

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"}]
  }'

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.

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

ArliAI terms of use ArliAI privacy policy