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

34 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V3.2 FP8 deepseek/deepseek-v3.2:atlascloud	164k	$0.27/M	$0.40/M	$0.14/M	1.1s	36 tps
DeepSeek V3.2 (Thinking) FP8 deepseek/deepseek-v3.2:thinking:atlascloud	164k	$0.27/M	$0.40/M	$0.14/M	1.1s	36 tps
DeepSeek V4 Flash FP4 deepseek/deepseek-v4-flash:atlascloud	1.0M	$0.15/M	$0.29/M	$0.03/M	1.7s	76 tps
DeepSeek V4 Flash (Thinking) FP4 deepseek/deepseek-v4-flash:thinking:atlascloud	1.0M	$0.15/M	$0.29/M	$0.03/M	1.7s	76 tps
DeepSeek V4 Flash 0731 FP4 deepseek/deepseek-v4-flash-0731:atlascloud	1.0M	$0.46/M	$1.39/M	$0.03/M	2.6s	66 tps
DeepSeek V4 Flash 0731 (Thinking) FP4 deepseek/deepseek-v4-flash-0731:thinking:atlascloud	1.0M	$0.46/M	$1.39/M	$0.03/M	2.6s	66 tps
DeepSeek V4 Pro FP4 deepseek/deepseek-v4-pro:atlascloud	1.0M	$1.76/M	$3.55/M	$0.14/M	1.6s	45 tps
DeepSeek V4 Pro (Thinking) FP4 deepseek/deepseek-v4-pro:thinking:atlascloud	1.0M	$1.76/M	$3.55/M	$0.14/M	1.6s	45 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:atlascloud	1.0M	$1.39/M	$4.16/M	$0.14/M	1.1s	73 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:atlascloud	1.0M	$1.39/M	$4.16/M	$0.14/M	1.1s	73 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:atlascloud	1.0M	$0.31/M	$1.26/M	$0.03/M	1.2s	117.5 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:atlascloud	1.0M	$0.31/M	$1.26/M	$0.03/M	1.2s	117.5 tps
GLM 5.1 FP8 z-ai/glm-5.1:atlascloud	203k	$1.32/M	$4.16/M	$0.25/M	2.7s	36.5 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:atlascloud	203k	$1.32/M	$4.16/M	$0.25/M	2.7s	36.5 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:atlascloud	1.0M	$1.47/M	$4.62/M	$0.27/M	1.2s	32 tps
GLM 5.3 FP8 z-ai/glm-5.3:atlascloud	1.0M	$1.47/M	$4.62/M	$0.27/M	1.1s	51 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:atlascloud	1.0M	$1.47/M	$4.62/M	$0.27/M	1.1s	51 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:atlascloud	1.0M	$0.16/M	$0.53/M	$0.03/M	2.7s	47.5 tps
Kimi K2.5 INT4 moonshotai/kimi-k2.5:atlascloud	262k	$0.51/M	$2.63/M	$0.21/M	1s	46 tps
Kimi K2.5 Thinking INT4 moonshotai/kimi-k2.5:thinking:atlascloud	262k	$0.51/M	$2.63/M	$0.21/M	1s	46 tps
MiniMax M2.5 FP8 minimax/minimax-m2.5:atlascloud	197k	$0.31/M	$1.26/M	$0.06/M	1.6s	81 tps
MiniMax M2.7 FP8 minimax/minimax-m2.7:atlascloud	197k	$0.31/M	$1.26/M	$0.06/M	2.7s	34 tps
MiniMax M3 FP8 minimax/minimax-m3:atlascloud	524k	$0.31/M	$1.26/M	$0.06/M	2s	63 tps
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:atlascloud	524k	$0.31/M	$1.26/M	$0.06/M	2s	63 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:atlascloud	262k	$0.20/M	$1.17/M	$0.20/M	1.3s	90 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:atlascloud	262k	$0.20/M	$1.17/M	$0.20/M	1.3s	90 tps
Qwen3.5 122B A10B FP8 qwen3.5-122b-a10b:atlascloud	262k	$0.31/M	$2.52/M	$0.31/M	2.1s	35 tps
Qwen3.5 122B A10B Thinking FP8 qwen3.5-122b-a10b:thinking:atlascloud	262k	$0.31/M	$2.52/M	$0.31/M	2.1s	35 tps
Qwen3.5 27B FP8 qwen3.5-27b:atlascloud	262k	$0.28/M	$2.27/M	$0.28/M	3s	21 tps
Qwen3.5 27B Thinking FP8 qwen3.5-27b:thinking:atlascloud	262k	$0.28/M	$2.27/M	$0.28/M	3s	21 tps
Qwen3.5 35B A3B FP8 qwen3.5-35b-a3b:atlascloud	262k	$0.24/M	$1.89/M	$0.24/M	1.5s	73 tps
Qwen3.5 35B A3B Thinking FP8 qwen3.5-35b-a3b:thinking:atlascloud	262k	$0.24/M	$1.89/M	$0.24/M	1.5s	73 tps
Qwen3.5 397B FP8 qwen/qwen3.5-397b-a17b:atlascloud	262k	$0.58/M	$3.68/M	$0.58/M	1.3s	68 tps
Qwen3.5 397B Thinking FP8 qwen/qwen3.5-397b-a17b-thinking:atlascloud	262k	$0.58/M	$3.68/M	$0.58/M	1.3s	68 tps

DeepSeek V3.2

FP8

deepseek/deepseek-v3.2:atlascloud

Context

164k

Input /M

$0.27/M

Output /M

$0.40/M

Cache read /M

$0.14/M

TTFT

1.1s

Throughput

36 tps

DeepSeek V3.2 (Thinking)

FP8

deepseek/deepseek-v3.2:thinking:atlascloud

Context

164k

Input /M

$0.27/M

Output /M

$0.40/M

Cache read /M

$0.14/M

TTFT

1.1s

Throughput

36 tps

DeepSeek V4 Flash

FP4

deepseek/deepseek-v4-flash:atlascloud

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

1.7s

Throughput

76 tps

DeepSeek V4 Flash (Thinking)

FP4

deepseek/deepseek-v4-flash:thinking:atlascloud

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

1.7s

Throughput

76 tps

DeepSeek V4 Flash 0731

FP4

deepseek/deepseek-v4-flash-0731:atlascloud

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.03/M

TTFT

2.6s

Throughput

66 tps

DeepSeek V4 Flash 0731 (Thinking)

FP4

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

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.03/M

TTFT

2.6s

Throughput

66 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

$0.14/M

TTFT

1.6s

Throughput

45 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

$0.14/M

TTFT

1.6s

Throughput

45 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

$0.14/M

TTFT

1.1s

Throughput

73 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

$0.14/M

TTFT

1.1s

Throughput

73 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:atlascloud

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.03/M

TTFT

1.2s

Throughput

117.5 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.03/M

TTFT

1.2s

Throughput

117.5 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

$0.25/M

TTFT

2.7s

Throughput

36.5 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

$0.25/M

TTFT

2.7s

Throughput

36.5 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

$0.27/M

TTFT

1.2s

Throughput

32 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

$0.27/M

TTFT

1.1s

Throughput

51 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

$0.27/M

TTFT

1.1s

Throughput

51 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:atlascloud

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

TTFT

2.7s

Throughput

47.5 tps

Kimi K2.5

INT4

moonshotai/kimi-k2.5:atlascloud

Context

262k

Input /M

$0.51/M

Output /M

$2.63/M

Cache read /M

$0.21/M

TTFT

1s

Throughput

46 tps

Kimi K2.5 Thinking

INT4

moonshotai/kimi-k2.5:thinking:atlascloud

Context

262k

Input /M

$0.51/M

Output /M

$2.63/M

Cache read /M

$0.21/M

TTFT

1s

Throughput

46 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

$0.06/M

TTFT

1.6s

Throughput

81 tps

MiniMax M2.7

FP8

minimax/minimax-m2.7:atlascloud

Context

197k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

2.7s

Throughput

34 tps

MiniMax M3

FP8

minimax/minimax-m3:atlascloud

Context

524k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

2s

Throughput

63 tps

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:atlascloud

Context

524k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.06/M

TTFT

2s

Throughput

63 tps

Qwen 3.6 35B A3B

FP8

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

Context

262k

Input /M

$0.20/M

Output /M

$1.17/M

Cache read /M

$0.20/M

TTFT

1.3s

Throughput

90 tps

Qwen 3.6 35B A3B Thinking

FP8

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

Context

262k

Input /M

$0.20/M

Output /M

$1.17/M

Cache read /M

$0.20/M

TTFT

1.3s

Throughput

90 tps

Qwen3.5 122B A10B

FP8

qwen3.5-122b-a10b:atlascloud

Context

262k

Input /M

$0.31/M

Output /M

$2.52/M

Cache read /M

$0.31/M

TTFT

2.1s

Throughput

35 tps

Qwen3.5 122B A10B Thinking

FP8

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

Context

262k

Input /M

$0.31/M

Output /M

$2.52/M

Cache read /M

$0.31/M

TTFT

2.1s

Throughput

35 tps

Qwen3.5 27B

FP8

qwen3.5-27b:atlascloud

Context

262k

Input /M

$0.28/M

Output /M

$2.27/M

Cache read /M

$0.28/M

TTFT

3s

Throughput

21 tps

Qwen3.5 27B Thinking

FP8

qwen3.5-27b:thinking:atlascloud

Context

262k

Input /M

$0.28/M

Output /M

$2.27/M

Cache read /M

$0.28/M

TTFT

3s

Throughput

21 tps

Qwen3.5 35B A3B

FP8

qwen3.5-35b-a3b:atlascloud

Context

262k

Input /M

$0.24/M

Output /M

$1.89/M

Cache read /M

$0.24/M

TTFT

1.5s

Throughput

73 tps

Qwen3.5 35B A3B Thinking

FP8

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

Context

262k

Input /M

$0.24/M

Output /M

$1.89/M

Cache read /M

$0.24/M

TTFT

1.5s

Throughput

73 tps

Qwen3.5 397B

FP8

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

Context

262k

Input /M

$0.58/M

Output /M

$3.68/M

Cache read /M

$0.58/M

TTFT

1.3s

Throughput

68 tps

Qwen3.5 397B Thinking

FP8

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

Context

262k

Input /M

$0.58/M

Output /M

$3.68/M

Cache read /M

$0.58/M

TTFT

1.3s

Throughput

68 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.