AtlasCloud

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 AtlasCloud

Model name

37 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V3.2 FP8 deepseek/deepseek-v3.2:atlascloud	164k	$0.273/M	$0.399/M	$0.136/M	N/A	3.2s	23 tps
DeepSeek V3.2 (Thinking) FP8 deepseek/deepseek-v3.2:thinking:atlascloud	164k	$0.273/M	$0.399/M	$0.136/M	N/A	3.2s	23 tps
DeepSeek V4 Flash FP4 deepseek/deepseek-v4-flash:atlascloud	1.0M	$0.147/M	$0.294/M	$0.0294/M	N/A	2.7s	44 tps
DeepSeek V4 Flash (Thinking) FP4 deepseek/deepseek-v4-flash:thinking:atlascloud	1.0M	$0.147/M	$0.294/M	$0.0294/M	N/A	2.7s	44 tps
DeepSeek V4 Flash 0731 FP4 deepseek/deepseek-v4-flash-0731:atlascloud	1.0M	$0.462/M	$1.39/M	$0.0294/M	N/A	2.4s	60 tps
DeepSeek V4 Flash 0731 (Thinking) FP4 deepseek/deepseek-v4-flash-0731:thinking:atlascloud	1.0M	$0.462/M	$1.39/M	$0.0294/M	N/A	2.4s	60 tps
DeepSeek V4 Pro FP4 deepseek/deepseek-v4-pro:atlascloud	1.0M	$1.76/M	$3.55/M	$0.136/M	N/A	1.8s	32 tps
DeepSeek V4 Pro (Thinking) FP4 deepseek/deepseek-v4-pro:thinking:atlascloud	1.0M	$1.76/M	$3.55/M	$0.136/M	N/A	1.8s	32 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:atlascloud	1.0M	$1.39/M	$4.16/M	$0.139/M	N/A	1.2s	36 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:atlascloud	1.0M	$1.39/M	$4.16/M	$0.139/M	N/A	1.2s	36 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:atlascloud	1.0M	$0.142/M	$0.567/M	$0.0142/M	N/A	0.8s	90 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:atlascloud	1.0M	$0.142/M	$0.567/M	$0.0142/M	N/A	0.8s	90 tps
DeepSeek V4.1 Flash 1017 FP8 deepseek/deepseek-v4.1-flash-1017:atlascloud	1.0M	$0.205/M	$0.819/M	$0.0041/M	N/A	1.2s	85 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP8 deepseek/deepseek-v4.1-flash-1017:thinking:atlascloud	1.0M	$0.205/M	$0.819/M	$0.0041/M	96.7%	1.2s	85 tps
GLM 5.1 FP8 z-ai/glm-5.1:atlascloud	203k	$1.32/M	$4.16/M	$0.246/M	23.9%	1s	63 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:atlascloud	203k	$1.32/M	$4.16/M	$0.246/M	23.9%	1s	63 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:atlascloud	1.0M	$1.47/M	$4.62/M	$0.273/M	N/A	2.2s	40 tps
GLM 5.3 FP8 z-ai/glm-5.3:atlascloud	1.0M	$1.47/M	$4.62/M	$0.273/M	N/A	2s	40 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:atlascloud	1.0M	$1.47/M	$4.62/M	$0.273/M	34.2%	2s	40 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:atlascloud	1.0M	$0.157/M	$0.525/M	$0.0315/M	N/A	4.4s	45 tps
Kimi K2.5 INT4 moonshotai/kimi-k2.5:atlascloud	262k	$0.514/M	$2.63/M	$0.21/M	N/A	0.7s	38 tps
Kimi K2.5 Thinking INT4 moonshotai/kimi-k2.5:thinking:atlascloud	262k	$0.514/M	$2.63/M	$0.21/M	N/A	0.7s	38 tps
MiniMax M2.5 FP8 minimax/minimax-m2.5:atlascloud	197k	$0.31/M	$1.26/M	$0.063/M	N/A	1.4s	49 tps
MiniMax M2.7 FP8 minimax/minimax-m2.7:atlascloud	197k	$0.315/M	$1.26/M	$0.063/M	N/A	1.4s	43 tps
MiniMax M3 FP8 minimax/minimax-m3:atlascloud	524k	$0.315/M	$1.26/M	$0.063/M	N/A	1.5s	163 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:atlascloud	524k	$0.315/M	$1.26/M	$0.063/M	N/A	1.5s	163 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:atlascloud	262k	$0.263/M	$1.31/M	$0.263/M	N/A	0.7s	43 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:atlascloud	262k	$0.263/M	$1.31/M	$0.263/M	N/A	0.7s	43 tps
Qwen3.5 122B A10B FP8 qwen3.5-122b-a10b:atlascloud	262k	$0.315/M	$2.52/M	$0.315/M	0%	1.2s	64 tps
Qwen3.5 122B A10B Thinking FP8 qwen3.5-122b-a10b:thinking:atlascloud	262k	$0.315/M	$2.52/M	$0.315/M	0%	1.2s	64 tps
Qwen3.5 27B FP8 qwen3.5-27b:atlascloud	262k	$0.284/M	$2.27/M	$0.284/M	N/A	3.8s	30 tps
Qwen3.5 27B Thinking FP8 qwen3.5-27b:thinking:atlascloud	262k	$0.284/M	$2.27/M	$0.284/M	N/A	3.8s	30 tps
Qwen3.5 35B A3B FP8 qwen3.5-35b-a3b:atlascloud	262k	$0.236/M	$1.89/M	$0.236/M	N/A	1.2s	47 tps
Qwen3.5 35B A3B Thinking FP8 qwen3.5-35b-a3b:thinking:atlascloud	262k	$0.236/M	$1.89/M	$0.236/M	N/A	1.2s	47 tps
Qwen3.5 397B FP8 qwen/qwen3.5-397b-a17b:atlascloud	262k	$0.578/M	$3.68/M	$0.578/M	N/A	1.1s	36 tps
Qwen3.5 397B Thinking FP8 qwen/qwen3.5-397b-a17b-thinking:atlascloud	262k	$0.578/M	$3.68/M	$0.578/M	N/A	1.1s	36 tps
Tencent Hy4 Preview FP8 tencent/hy4-preview:atlascloud	1.0M	$0.90/M	$2.70/M	$0.045/M	N/A	2.3s	43 tps

DeepSeek V3.2

FP8

deepseek/deepseek-v3.2:atlascloud

Context

164k

Input /M

$0.273/M

Output /M

$0.399/M

Cache read /M

$0.136/M

Cache hit

N/A

TTFT

3.2s

Throughput

23 tps

DeepSeek V3.2 (Thinking)

FP8

deepseek/deepseek-v3.2:thinking:atlascloud

Context

164k

Input /M

$0.273/M

Output /M

$0.399/M

Cache read /M

$0.136/M

Cache hit

N/A

TTFT

3.2s

Throughput

23 tps

DeepSeek V4 Flash

FP4

deepseek/deepseek-v4-flash:atlascloud

Context

1.0M

Input /M

$0.147/M

Output /M

$0.294/M

Cache read /M

$0.0294/M

Cache hit

N/A

TTFT

2.7s

Throughput

44 tps

DeepSeek V4 Flash (Thinking)

FP4

deepseek/deepseek-v4-flash:thinking:atlascloud

Context

1.0M

Input /M

$0.147/M

Output /M

$0.294/M

Cache read /M

$0.0294/M

Cache hit

N/A

TTFT

2.7s

Throughput

44 tps

DeepSeek V4 Flash 0731

FP4

deepseek/deepseek-v4-flash-0731:atlascloud

Context

1.0M

Input /M

$0.462/M

Output /M

$1.39/M

Cache read /M

$0.0294/M

Cache hit

N/A

TTFT

2.4s

Throughput

60 tps

DeepSeek V4 Flash 0731 (Thinking)

FP4

deepseek/deepseek-v4-flash-0731:thinking:atlascloud

Context

1.0M

Input /M

$0.462/M

Output /M

$1.39/M

Cache read /M

$0.0294/M

Cache hit

N/A

TTFT

2.4s

Throughput

60 tps

DeepSeek V4 Pro

FP4

deepseek/deepseek-v4-pro:atlascloud

Context

1.0M

Input /M

$1.76/M

Output /M

$3.55/M

Cache read /M

$0.136/M

Cache hit

N/A

TTFT

1.8s

Throughput

32 tps

DeepSeek V4 Pro (Thinking)

FP4

deepseek/deepseek-v4-pro:thinking:atlascloud

Context

1.0M

Input /M

$1.76/M

Output /M

$3.55/M

Cache read /M

$0.136/M

Cache hit

N/A

TTFT

1.8s

Throughput

32 tps

DeepSeek V4 Pro 0813

FP8

deepseek/deepseek-v4-pro-0813:atlascloud

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.139/M

Cache hit

N/A

TTFT

1.2s

Throughput

36 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

deepseek/deepseek-v4-pro-0813:thinking:atlascloud

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.139/M

Cache hit

N/A

TTFT

1.2s

Throughput

36 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:atlascloud

Context

1.0M

Input /M

$0.142/M

Output /M

$0.567/M

Cache read /M

$0.0142/M

Cache hit

N/A

TTFT

0.8s

Throughput

90 tps

DeepSeek V4.1 Flash (Thinking)

FP8

deepseek/deepseek-v4.1-flash:thinking:atlascloud

Context

1.0M

Input /M

$0.142/M

Output /M

$0.567/M

Cache read /M

$0.0142/M

Cache hit

N/A

TTFT

0.8s

Throughput

90 tps

DeepSeek V4.1 Flash 1017

FP8

deepseek/deepseek-v4.1-flash-1017:atlascloud

Context

1.0M

Input /M

$0.205/M

Output /M

$0.819/M

Cache read /M

$0.0041/M

Cache hit

N/A

TTFT

1.2s

Throughput

85 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

deepseek/deepseek-v4.1-flash-1017:thinking:atlascloud

Context

1.0M

Input /M

$0.205/M

Output /M

$0.819/M

Cache read /M

$0.0041/M

Cache hit

96.7%

TTFT

1.2s

Throughput

85 tps

GLM 5.1

FP8

z-ai/glm-5.1:atlascloud

Context

203k

Input /M

$1.32/M

Output /M

$4.16/M

Cache read /M

$0.246/M

Cache hit

23.9%

TTFT

1s

Throughput

63 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:atlascloud

Context

203k

Input /M

$1.32/M

Output /M

$4.16/M

Cache read /M

$0.246/M

Cache hit

23.9%

TTFT

1s

Throughput

63 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:atlascloud

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.273/M

Cache hit

N/A

TTFT

2.2s

Throughput

40 tps

GLM 5.3

FP8

z-ai/glm-5.3:atlascloud

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.273/M

Cache hit

N/A

TTFT

2s

Throughput

40 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:atlascloud

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.273/M

Cache hit

34.2%

TTFT

2s

Throughput

40 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:atlascloud

Context

1.0M

Input /M

$0.157/M

Output /M

$0.525/M

Cache read /M

$0.0315/M

Cache hit

N/A

TTFT

4.4s

Throughput

45 tps

Kimi K2.5

INT4

moonshotai/kimi-k2.5:atlascloud

Context

262k

Input /M

$0.514/M

Output /M

$2.63/M

Cache read /M

$0.21/M

Cache hit

N/A

TTFT

0.7s

Throughput

38 tps

Kimi K2.5 Thinking

INT4

moonshotai/kimi-k2.5:thinking:atlascloud

Context

262k

Input /M

$0.514/M

Output /M

$2.63/M

Cache read /M

$0.21/M

Cache hit

N/A

TTFT

0.7s

Throughput

38 tps

MiniMax M2.5

FP8

minimax/minimax-m2.5:atlascloud

Context

197k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.063/M

Cache hit

N/A

TTFT

1.4s

Throughput

49 tps

MiniMax M2.7

FP8

minimax/minimax-m2.7:atlascloud

Context

197k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.063/M

Cache hit

N/A

TTFT

1.4s

Throughput

43 tps

MiniMax M3

FP8

minimax/minimax-m3:atlascloud

Context

524k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.063/M

Cache hit

N/A

TTFT

1.5s

Throughput

163 tps

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:atlascloud

Context

524k

Input /M

$0.315/M

Output /M

$1.26/M

Cache read /M

$0.063/M

Cache hit

N/A

TTFT

1.5s

Throughput

163 tps

Qwen 3.6 35B A3B

FP8

Qwen/Qwen3.6-35B-A3B:atlascloud

Context

262k

Input /M

$0.263/M

Output /M

$1.31/M

Cache read /M

$0.263/M

Cache hit

N/A

TTFT

0.7s

Throughput

43 tps

Qwen 3.6 35B A3B Thinking

FP8

Qwen/Qwen3.6-35B-A3B:thinking:atlascloud

Context

262k

Input /M

$0.263/M

Output /M

$1.31/M

Cache read /M

$0.263/M

Cache hit

N/A

TTFT

0.7s

Throughput

43 tps

Qwen3.5 122B A10B

FP8

qwen3.5-122b-a10b:atlascloud

Context

262k

Input /M

$0.315/M

Output /M

$2.52/M

Cache read /M

$0.315/M

Cache hit

0%

TTFT

1.2s

Throughput

64 tps

Qwen3.5 122B A10B Thinking

FP8

qwen3.5-122b-a10b:thinking:atlascloud

Context

262k

Input /M

$0.315/M

Output /M

$2.52/M

Cache read /M

$0.315/M

Cache hit

0%

TTFT

1.2s

Throughput

64 tps

Qwen3.5 27B

FP8

qwen3.5-27b:atlascloud

Context

262k

Input /M

$0.284/M

Output /M

$2.27/M

Cache read /M

$0.284/M

Cache hit

N/A

TTFT

3.8s

Throughput

30 tps

Qwen3.5 27B Thinking

FP8

qwen3.5-27b:thinking:atlascloud

Context

262k

Input /M

$0.284/M

Output /M

$2.27/M

Cache read /M

$0.284/M

Cache hit

N/A

TTFT

3.8s

Throughput

30 tps

Qwen3.5 35B A3B

FP8

qwen3.5-35b-a3b:atlascloud

Context

262k

Input /M

$0.236/M

Output /M

$1.89/M

Cache read /M

$0.236/M

Cache hit

N/A

TTFT

1.2s

Throughput

47 tps

Qwen3.5 35B A3B Thinking

FP8

qwen3.5-35b-a3b:thinking:atlascloud

Context

262k

Input /M

$0.236/M

Output /M

$1.89/M

Cache read /M

$0.236/M

Cache hit

N/A

TTFT

1.2s

Throughput

47 tps

Qwen3.5 397B

FP8

qwen/qwen3.5-397b-a17b:atlascloud

Context

262k

Input /M

$0.578/M

Output /M

$3.68/M

Cache read /M

$0.578/M

Cache hit

N/A

TTFT

1.1s

Throughput

36 tps

Qwen3.5 397B Thinking

FP8

qwen/qwen3.5-397b-a17b-thinking:atlascloud

Context

262k

Input /M

$0.578/M

Output /M

$3.68/M

Cache read /M

$0.578/M

Cache hit

N/A

TTFT

1.1s

Throughput

36 tps

Tencent Hy4 Preview

FP8

tencent/hy4-preview:atlascloud

Context

1.0M

Input /M

$0.90/M

Output /M

$2.70/M

Cache read /M

$0.045/M

Cache hit

N/A

TTFT

2.3s

Throughput

43 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 AtlasCloud via the API

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

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:atlascloud",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, 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 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.