CrofAI

Models served by CrofAI

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
DeepSeek V4 Flash 0731 Q4_0 deepseek/deepseek-v4-flash-0731:crofai	1M	$0.08/M	$0.11/M	$0.0032/M	N/A	137 tps
DeepSeek V4 Flash 0731 (Thinking) Q4_0 deepseek/deepseek-v4-flash-0731:thinking:crofai	1M	$0.08/M	$0.11/M	$0.0032/M	N/A	137 tps
DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp:crofai	1.0M	$0.08/M	$0.21/M	$0.0073/M	N/A	96 tps
Gemma 4 31B Q4_0 google/gemma-4-31b-it:crofai	262k	$0.11/M	$0.31/M	$0.02/M	N/A	105 tps
Gemma 4 31B (Thinking) Q4_0 google/gemma-4-31b-it:thinking:crofai	262k	$0.11/M	$0.31/M	$0.02/M	N/A	105 tps
GLM 4.7 Q8_0 z-ai/glm-4.7:crofai	200k	$0.26/M	$1.16/M	$0.05/M	N/A	N/A
GLM 4.7 (Thinking) Q8_0 z-ai/glm-4.7:thinking:crofai	200k	$0.26/M	$1.16/M	$0.05/M	N/A	N/A
GLM 4.7 Flash FP8 z-ai/glm-4.7-flash:crofai	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 4.7 Flash (Thinking) FP8 z-ai/glm-4.7-flash:thinking:crofai	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 4.7 Flash Original FP8 z-ai/glm-4.7-flash-original:crofai	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 4.7 Flash Original (Thinking) FP8 z-ai/glm-4.7-flash-original:thinking:crofai	200k	$0.04/M	$0.31/M	$0.0084/M	N/A	N/A
GLM 5 Q4_0 z-ai/glm-5:crofai	200k	$0.50/M	$2.00/M	$0.11/M	N/A	N/A
GLM 5.2 Q8_0 z-ai/glm-5.2:crofai	1.0M	$0.31/M	$1.10/M	$0.05/M	N/A	163 tps
GLM 5.2 (Thinking) Q8_0 z-ai/glm-5.2:thinking:crofai	1.0M	$0.31/M	$1.10/M	$0.05/M	N/A	163 tps
GLM 5.3 z-ai/glm-5.3:crofai	1.0M	$0.42/M	$1.47/M	$0.06/M	N/A	97 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:crofai	1.0M	$0.42/M	$1.47/M	$0.06/M	N/A	97 tps
GLM 5.3 Flash Q8_0 z-ai/glm-5.3-flash:crofai	1M	$0.07/M	$0.23/M	$0.01/M	N/A	143 tps
Greg 2 Super INT4 crofai/greg-2-super:crofai	229k	$1.57/M	$5.25/M	$0.26/M	N/A	63 tps
Greg 2 Ultra INT4 crofai/greg-2-ultra:crofai	229k	$3.15/M	$10.50/M	$0.53/M	N/A	99 tps
Kimi K2.6 INT4 moonshotai/kimi-k2.6:crofai	256k	$0.53/M	$2.09/M	$0.05/M	N/A	160 tps
Kimi K2.6 Thinking INT4 moonshotai/kimi-k2.6:thinking:crofai	256k	$0.53/M	$2.09/M	$0.05/M	N/A	160 tps
Kimi K2.7 Code moonshotai/kimi-k2.7-code:crofai	262k	$0.58/M	$2.36/M	$0.05/M	N/A	139 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:crofai	1M	$2.10/M	$8.40/M	$0.26/M	N/A	93 tps
MiMo V2.5 Pro Q8_0 xiaomi/mimo-v2.5-pro:crofai	1.0M	$0.42/M	$0.84/M	$0.0032/M	N/A	153 tps
MiMo V2.5 Pro Thinking Q8_0 xiaomi/mimo-v2.5-pro:thinking:crofai	1.0M	$0.42/M	$0.84/M	$0.0032/M	N/A	153 tps
MiniMax M2.5 AWQ minimax/minimax-m2.5:crofai	205k	$0.12/M	$1.00/M	$0.02/M	N/A	N/A
Qwen3.5 9B FP8 qwen/qwen3.5-9b:crofai	256k	$0.04/M	$0.16/M	$0.0084/M	N/A	67 tps
Qwen3.8 27B Q4_0 qwen3.8-27b:crofai	262k	$0.09/M	$0.31/M	$0.01/M	N/A	124 tps
Qwen3.8 27B Thinking Q4_0 qwen3.8-27b:thinking:crofai	262k	$0.09/M	$0.31/M	$0.01/M	N/A	124 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-v4-flash-0731:crofai",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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