AtlasCloud

42 models available

Models served by AtlasCloud

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
DeepSeek V3.1 FP8	128k	$0.31/M	$1.00/M	$0.14/M	1.7s	25 tps
DeepSeek V3.1 Terminus FP8	128k	$0.31/M	$1.00/M	$0.14/M	1.8s	53 tps
DeepSeek V3.1 Terminus (Thinking) FP8	128k	$0.31/M	$1.00/M	$0.14/M	1.8s	53 tps
DeepSeek V3.2 FP8	163k	$0.27/M	$0.40/M	$0.14/M	1.2s	23 tps
DeepSeek V3.2 (Thinking) FP8	163k	$0.27/M	$0.40/M	$0.14/M	1.2s	23 tps
DeepSeek V4 Flash FP4	1.0M	$0.15/M	$0.29/M	$0.03/M	1.1s	39 tps
DeepSeek V4 Flash (Thinking) FP4	1.0M	$0.15/M	$0.29/M	$0.03/M	1.1s	39 tps
DeepSeek V4 Flash 0731 FP4	262k	$0.46/M	$1.39/M	$0.03/M	1.8s	52 tps
DeepSeek V4 Flash 0731 (Thinking) FP4	262k	$0.46/M	$1.39/M	$0.03/M	1.8s	52 tps
DeepSeek V4 Flash Vision Exp FP8	1.0M	$0.46/M	$1.39/M	$0.03/M	1.2s	61 tps
DeepSeek V4 Pro FP4	1.0M	$1.76/M	$3.55/M	$0.14/M	1.4s	35 tps
DeepSeek V4 Pro (Thinking) FP4	1.0M	$1.76/M	$3.55/M	$0.14/M	1.4s	35 tps
GLM 4.6 FP8	200k	$0.63/M	$2.31/M	$0.12/M	0.9s	41.5 tps
GLM 4.6 (Thinking) FP8	200k	$0.63/M	$2.31/M	$0.12/M	0.9s	41.5 tps
GLM 4.7 FP8	200k	$0.55/M	$1.94/M	$0.13/M	0.6s	48 tps
GLM 4.7 (Thinking) FP8	200k	$0.55/M	$1.94/M	$0.13/M	0.6s	48 tps
GLM 5.1 FP8	200k	$1.32/M	$4.16/M	$0.25/M	1.2s	60 tps
GLM 5.1 (Thinking) FP8	200k	$1.32/M	$4.16/M	$0.25/M	1.2s	60 tps
GLM 5.2 (Thinking) FP8	1.0M	$1.47/M	$4.62/M	$0.27/M	2s	40 tps
GLM 5.3 FP8	262k	$1.47/M	$4.62/M	$0.27/M	1.2s	49 tps
GLM 5.3 (Thinking) FP8	262k	$1.47/M	$4.62/M	$0.27/M	1.2s	49 tps
Kimi K2.5 INT4	256k	$0.51/M	$2.63/M	$0.21/M	0.9s	26 tps
Kimi K2.5 Thinking INT4	256k	$0.51/M	$2.63/M	$0.21/M	0.9s	26 tps
LongCat 2.0	1.0M	$0.79/M	$3.15/M	$0.02/M	N/A	N/A
LongCat 2.0 Thinking	1.0M	$0.79/M	$3.15/M	$0.02/M	N/A	N/A
MiMo V2.5 Pro FP8	1.0M	$0.46/M	$0.91/M	$0.0038/M	2.3s	25 tps
MiMo V2.5 Pro Thinking FP8	1.0M	$0.46/M	$0.91/M	$0.0038/M	2.3s	25 tps
MiniMax M2.5 FP8	205k	$0.31/M	$1.26/M	$0.06/M	1.5s	29.5 tps
MiniMax M2.7 FP8	205k	$0.31/M	$1.26/M	$0.06/M	3.2s	25 tps
MiniMax M3 FP8	512k	$0.31/M	$1.26/M	$0.06/M	1s	16 tps
MiniMax M3 Thinking FP8	512k	$0.31/M	$1.26/M	$0.06/M	1s	16 tps
Qwen 3.6 35B A3B FP8	262k	$0.20/M	$1.17/M	$0.20/M	1.1s	144 tps
Qwen 3.6 35B A3B Thinking FP8	262k	$0.20/M	$1.17/M	$0.20/M	1.1s	144 tps
Qwen3 235B A22B FP8	262k	$0.21/M	$0.92/M	$0.21/M	1s	31 tps
Qwen3.5 122B A10B	131k	$0.31/M	$2.52/M	$0.31/M	N/A	N/A
Qwen3.5 122B A10B Thinking	131k	$0.31/M	$2.52/M	$0.31/M	N/A	N/A
Qwen3.5 27B	260k	$0.28/M	$2.27/M	$0.28/M	N/A	N/A
Qwen3.5 27B Thinking	260k	$0.28/M	$2.27/M	$0.28/M	N/A	N/A
Qwen3.5 35B A3B	260k	$0.24/M	$1.89/M	$0.24/M	N/A	N/A
Qwen3.5 35B A3B Thinking	260k	$0.24/M	$1.89/M	$0.24/M	N/A	N/A
Qwen3.5 397B FP8	258k	$0.58/M	$3.68/M	$0.58/M	1.5s	76.5 tps
Qwen3.5 397B Thinking FP8	258k	$0.58/M	$3.68/M	$0.58/M	1.5s	76.5 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 AtlasCloud via the API

Append :atlascloud to the model ID, set "provider": "atlascloud" in the request body, or send an X-Provider: atlascloud 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-ai/DeepSeek-V3.1:atlascloud",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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

AtlasCloud privacy policy