CrofAI

42 models available

Models served by CrofAI

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
DeepSeek V3.2 Q6_K	163k	$0.19/M	$0.37/M	$0.04/M	N/A	65 tps
DeepSeek V3.2 (Thinking) Q6_K	163k	$0.19/M	$0.37/M	$0.04/M	N/A	65 tps
DeepSeek V4 Flash Q4_0	1.0M	$0.13/M	$0.22/M	$0.0032/M	N/A	38 tps
DeepSeek V4 Flash (Thinking) Q4_0	1.0M	$0.13/M	$0.22/M	$0.0032/M	N/A	38 tps
DeepSeek V4 Flash 0731 Q4_0	1M	$0.08/M	$0.11/M	$0.0032/M	N/A	66 tps
DeepSeek V4 Flash 0731 (Thinking) Q4_0	1M	$0.08/M	$0.11/M	$0.0032/M	N/A	66 tps
DeepSeek V4 Pro Q8_0	1.0M	$0.63/M	$1.89/M	$0.03/M	N/A	140 tps
DeepSeek V4 Pro (Thinking) Q8_0	1.0M	$0.63/M	$1.89/M	$0.03/M	N/A	140 tps
DeepSeek V4 Pro 0813 Q8_0	1.0M	$0.37/M	$0.84/M	$0.0032/M	N/A	140 tps
DeepSeek V4 Pro 0813 (Thinking) Q8_0	1.0M	$0.37/M	$0.84/M	$0.0032/M	N/A	140 tps
Gemma 4 31B Q4_0	262k	$0.11/M	$0.31/M	$0.02/M	N/A	66 tps
Gemma 4 31B (Thinking) Q4_0	262k	$0.11/M	$0.31/M	$0.02/M	N/A	66 tps
GLM 4.7 Q8_0	200k	$0.26/M	$1.16/M	$0.05/M	N/A	N/A
GLM 4.7 (Thinking) Q8_0	200k	$0.26/M	$1.16/M	$0.05/M	N/A	N/A
GLM 4.7 Flash FP8	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 4.7 Flash (Thinking) FP8	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 4.7 Flash Original FP8	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 4.7 Flash Original (Thinking) FP8	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 5 Q4_0	200k	$0.50/M	$2.00/M	$0.11/M	N/A	N/A
GLM 5.1 Q8_0	200k	$0.47/M	$2.26/M	$0.08/M	N/A	45 tps
GLM 5.1 (Thinking) Q8_0	200k	$0.47/M	$2.26/M	$0.08/M	N/A	45 tps
GLM 5.2 Q8_0	1.0M	$0.31/M	$1.10/M	$0.05/M	N/A	118 tps
GLM 5.2 (Thinking) Q8_0	1.0M	$0.31/M	$1.10/M	$0.05/M	N/A	118 tps
GLM 5.3	1.0M	$0.42/M	$1.47/M	$0.06/M	N/A	48 tps
GLM 5.3 (Thinking)	1.0M	$0.42/M	$1.47/M	$0.06/M	N/A	48 tps
GLM 5.3 Flash Q8_0	1M	$0.07/M	$0.23/M	$0.01/M	N/A	168 tps
Greg 2 Super INT4	229k	$1.57/M	$5.25/M	$0.26/M	N/A	57 tps
Greg 2 Ultra INT4	229k	$3.15/M	$10.50/M	$0.53/M	N/A	67 tps
Kimi K2.6 INT4	256k	$0.53/M	$2.09/M	$0.05/M	N/A	77 tps
Kimi K2.6 Thinking INT4	256k	$0.53/M	$2.09/M	$0.05/M	N/A	77 tps
Kimi K2.7 Code	262k	$0.58/M	$2.36/M	$0.05/M	N/A	138 tps
Kimi K3 MXFP4	1M	$2.10/M	$8.40/M	$0.26/M	N/A	50 tps
MiMo V2.5 Pro Q8_0	1.0M	$0.42/M	$0.84/M	$0.0032/M	N/A	138 tps
MiMo V2.5 Pro Thinking Q8_0	1.0M	$0.42/M	$0.84/M	$0.0032/M	N/A	138 tps
MiniMax M2.5 AWQ	205k	$0.12/M	$1.00/M	$0.02/M	N/A	N/A
Qwen 3.6 27B Q4_0	260k	$0.21/M	$1.57/M	$0.04/M	N/A	65 tps
Qwen 3.6 27B Thinking Q4_0	260k	$0.21/M	$1.57/M	$0.04/M	N/A	65 tps
Qwen3.5 397B Q4_0	258k	$0.37/M	$1.84/M	$0.07/M	N/A	98 tps
Qwen3.5 397B Thinking Q4_0	258k	$0.37/M	$1.84/M	$0.07/M	N/A	98 tps
Qwen3.5 9B FP8	256k	$0.04/M	$0.16/M	$0.0084/M	N/A	89 tps
Qwen3.8 27B Q4_0	262k	$0.09/M	$0.31/M	$0.01/M	N/A	112 tps
Qwen3.8 27B Thinking Q4_0	262k	$0.09/M	$0.31/M	$0.01/M	N/A	112 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using CrofAI via the API

Append :crofai to the model ID, set "provider": "crofai" in the request body, or send an X-Provider: crofai header. Explicit provider selection adds a 5% markup over that provider's base price; the prices in the table above already include it.

curl https://nano-gpt.com/api/v1/chat/completions \
  -H "Authorization: Bearer $NANOGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3.2:crofai",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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

CrofAI privacy policy