GMICloud

Models served by GMICloud

Model	Context	Input /M	Output /M	Cache read /M	Cache write /M	Cache hit	Latency	Throughput
DeepSeek V3 0324 FP8 deepseek-v3-0324:gmicloud	128k	$0.30/M	$1.20/M	$0.12/M	N/A	78.1%	2.6s	26 tps
DeepSeek V3.2 FP8 deepseek/deepseek-v3.2:gmicloud	163k	$0.22/M	$0.33/M	$0.02/M	N/A	86.5%	1.8s	3 tps
DeepSeek V3.2 (Thinking) FP8 deepseek/deepseek-v3.2:thinking:gmicloud	163k	$0.22/M	$0.33/M	$0.02/M	N/A	94.7%	1.8s	3 tps
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:gmicloud	1.0M	$0.12/M	$0.24/M	$0.02/M	N/A	N/A	1.8s	52 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:gmicloud	1.0M	$0.12/M	$0.24/M	$0.02/M	N/A	N/A	1.8s	52 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:gmicloud	1.0M	$0.37/M	$1.11/M	$0.01/M	N/A	N/A	1.7s	88 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:gmicloud	1.0M	$0.37/M	$1.11/M	$0.01/M	N/A	N/A	1.7s	88 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:gmicloud	1.0M	$1.46/M	$2.92/M	$0.12/M	N/A	N/A	2.7s	28 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:gmicloud	1.0M	$1.46/M	$2.92/M	$0.12/M	N/A	N/A	2.7s	28 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:gmicloud	1.0M	$1.18/M	$3.53/M	$0.04/M	N/A	N/A	3s	51 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:gmicloud	1.0M	$1.18/M	$3.53/M	$0.04/M	N/A	N/A	3s	51 tps
GLM 5.2 FP8 z-ai/glm-5.2:gmicloud	1.0M	$1.10/M	$3.47/M	$0.20/M	N/A	N/A	1.7s	55 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:gmicloud	1.0M	$1.10/M	$3.47/M	$0.20/M	N/A	0%	1.7s	55 tps
GLM 5.3 FP8 z-ai/glm-5.3:gmicloud	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	N/A	1.8s	74 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:gmicloud	1.0M	$1.47/M	$4.62/M	$0.27/M	N/A	N/A	1.8s	74 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:gmicloud	1.0M	$0.08/M	$0.26/M	$0.02/M	N/A	67.3%	6.6s	19 tps
Kimi K2.6 FP8 moonshotai/kimi-k2.6:gmicloud	262k	$0.90/M	$3.78/M	$0.15/M	N/A	N/A	3.3s	108.5 tps
Kimi K2.6 Thinking FP8 moonshotai/kimi-k2.6:thinking:gmicloud	262k	$0.90/M	$3.78/M	$0.15/M	N/A	N/A	3.3s	108.5 tps
Kimi K2.7 Code FP8 moonshotai/kimi-k2.7-code:gmicloud	262k	$1.00/M	$4.20/M	$0.20/M	N/A	N/A	2.6s	46.5 tps
MiMo V2.5 FP8 xiaomi/mimo-v2.5:gmicloud	1.0M	$0.12/M	$0.25/M	$0.0027/M	N/A	0%	3.9s	2 tps
MiMo V2.5 Pro BF16 xiaomi/mimo-v2.5-pro:gmicloud	1.0M	$0.32/M	$0.64/M	$0.0029/M	Free	N/A	4.2s	33 tps
MiMo V2.5 Pro Thinking BF16 xiaomi/mimo-v2.5-pro:thinking:gmicloud	1.0M	$0.32/M	$0.64/M	$0.0029/M	Free	N/A	4.2s	33 tps
MiMo V2.5 Thinking FP8 xiaomi/mimo-v2.5:thinking:gmicloud	1.0M	$0.12/M	$0.25/M	$0.0027/M	N/A	92.9%	3.9s	2 tps
MiniMax M2.7 FP8 minimax/minimax-m2.7:gmicloud	205k	$0.31/M	$1.26/M	$0.06/M	N/A	N/A	2.1s	40 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:gmicloud	512k	$0.50/M	$2.02/M	$0.10/M	N/A	N/A	1.2s	35 tps
>512k tokens		$1.01/M	$4.03/M	$0.20/M	N/A
Nvidia Nemotron 3 Nano Omni nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:gmicloud	256k	$0.11/M	$0.42/M	N/A	N/A	N/A	N/A	N/A
Qwen 3.6 Plus FP8 qwen-3.6-plus:gmicloud	992k	$0.53/M	$3.15/M	Free	Free	N/A	N/A	N/A
Qwen3 235B A22B FP8 qwen/qwen3-235b-a22b:gmicloud	262k	$0.09/M	$0.37/M	$0.02/M	N/A	39.2%	1.3s	20 tps
Qwen3.5 397B FP8 qwen/qwen3.5-397b-a17b:gmicloud	258k	$0.63/M	$3.78/M	N/A	N/A	N/A	2s	62 tps
Qwen3.5 397B Thinking FP8 qwen/qwen3.5-397b-a17b-thinking:gmicloud	258k	$0.63/M	$3.78/M	N/A	N/A	N/A	2s	62 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 GMICloud via the API

Append :gmicloud to the model ID, set "provider": "gmicloud" in the request body, or send an X-Provider: gmicloud 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-v3-0324:gmicloud",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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