Nube

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 Nube

Model name

17 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash deepseek/deepseek-v4-flash:nube	1M	$0.12/M	$0.35/M	$0.0037/M	N/A	N/A	N/A
DeepSeek V4 Flash (Thinking) deepseek/deepseek-v4-flash:thinking:nube	1M	$0.12/M	$0.35/M	$0.0037/M	N/A	N/A	N/A
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:nube	1M	$0.14/M	$0.57/M	$0.0028/M	74.2%	6.2s	188.4 tps
GLM 5.1 z-ai/glm-5.1:nube	205k	$0.79/M	$2.73/M	$0.16/M	N/A	N/A	N/A
GLM 5.1 (Thinking) z-ai/glm-5.1:thinking:nube	205k	$0.79/M	$2.73/M	$0.16/M	58.8%	8.4s	69.2 tps
GLM 5.2 z-ai/glm-5.2:nube	131k	$0.51/M	$1.62/M	$0.10/M	N/A	N/A	N/A
GLM 5.2 (Thinking) z-ai/glm-5.2:thinking:nube	131k	$0.51/M	$1.62/M	$0.10/M	3.7%	9s	54.1 tps
GLM 5.3 z-ai/glm-5.3:nube	1M	$0.66/M	$2.08/M	$0.12/M	2.1%	11.1s	47.1 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:nube	1M	$0.66/M	$2.08/M	$0.12/M	44.1%	9.5s	60.7 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:nube	1M	$0.09/M	$0.29/M	$0.02/M	40.1%	15.1s	129.2 tps
Kimi K2.5 moonshotai/kimi-k2.5:nube	262k	$0.22/M	$1.10/M	$0.04/M	0%	10.4s	45 tps
Kimi K2.5 Thinking moonshotai/kimi-k2.5:thinking:nube	262k	$0.22/M	$1.10/M	$0.04/M	80.4%	5.2s	62.2 tps
Kimi K2.6 moonshotai/kimi-k2.6:nube	262k	$0.35/M	$1.47/M	$0.06/M	N/A	6.4s	199.7 tps
Kimi K2.6 Thinking moonshotai/kimi-k2.6:thinking:nube	262k	$0.35/M	$1.47/M	$0.06/M	0%	8.8s	27.6 tps
Kimi K3 moonshotai/kimi-k3:nube	1M	$2.05/M	$10.24/M	$0.20/M	43.3%	9.7s	34.9 tps
Qwen3.8 27B qwen3.8-27b:nube	262k	$0.31/M	$1.89/M	$0.06/M	N/A	N/A	N/A
Qwen3.8 27B Thinking qwen3.8-27b:thinking:nube	262k	$0.31/M	$1.89/M	$0.06/M	N/A	N/A	N/A

DeepSeek V4 Flash

deepseek/deepseek-v4-flash:nube

Context

1M

Input /M

$0.12/M

Output /M

$0.35/M

Cache read /M

$0.0037/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash (Thinking)

deepseek/deepseek-v4-flash:thinking:nube

Context

1M

Input /M

$0.12/M

Output /M

$0.35/M

Cache read /M

$0.0037/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

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

Context

1M

Input /M

$0.14/M

Output /M

$0.57/M

Cache read /M

$0.0028/M

Cache hit

74.2%

TTFT

6.2s

Throughput

188.4 tps

GLM 5.1

z-ai/glm-5.1:nube

Context

205k

Input /M

$0.79/M

Output /M

$2.73/M

Cache read /M

$0.16/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 5.1 (Thinking)

z-ai/glm-5.1:thinking:nube

Context

205k

Input /M

$0.79/M

Output /M

$2.73/M

Cache read /M

$0.16/M

Cache hit

58.8%

TTFT

8.4s

Throughput

69.2 tps

GLM 5.2

z-ai/glm-5.2:nube

Context

131k

Input /M

$0.51/M

Output /M

$1.62/M

Cache read /M

$0.10/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 5.2 (Thinking)

z-ai/glm-5.2:thinking:nube

Context

131k

Input /M

$0.51/M

Output /M

$1.62/M

Cache read /M

$0.10/M

Cache hit

3.7%

TTFT

9s

Throughput

54.1 tps

GLM 5.3

z-ai/glm-5.3:nube

Context

1M

Input /M

$0.66/M

Output /M

$2.08/M

Cache read /M

$0.12/M

Cache hit

2.1%

TTFT

11.1s

Throughput

47.1 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:nube

Context

1M

Input /M

$0.66/M

Output /M

$2.08/M

Cache read /M

$0.12/M

Cache hit

44.1%

TTFT

9.5s

Throughput

60.7 tps

GLM 5.3 Flash

z-ai/glm-5.3-flash:nube

Context

1M

Input /M

$0.09/M

Output /M

$0.29/M

Cache read /M

$0.02/M

Cache hit

40.1%

TTFT

15.1s

Throughput

129.2 tps

Kimi K2.5

moonshotai/kimi-k2.5:nube

Context

262k

Input /M

$0.22/M

Output /M

$1.10/M

Cache read /M

$0.04/M

Cache hit

0%

TTFT

10.4s

Throughput

45 tps

Kimi K2.5 Thinking

moonshotai/kimi-k2.5:thinking:nube

Context

262k

Input /M

$0.22/M

Output /M

$1.10/M

Cache read /M

$0.04/M

Cache hit

80.4%

TTFT

5.2s

Throughput

62.2 tps

Kimi K2.6

moonshotai/kimi-k2.6:nube

Context

262k

Input /M

$0.35/M

Output /M

$1.47/M

Cache read /M

$0.06/M

Cache hit

N/A

TTFT

6.4s

Throughput

199.7 tps

Kimi K2.6 Thinking

moonshotai/kimi-k2.6:thinking:nube

Context

262k

Input /M

$0.35/M

Output /M

$1.47/M

Cache read /M

$0.06/M

Cache hit

0%

TTFT

8.8s

Throughput

27.6 tps

Kimi K3

moonshotai/kimi-k3:nube

Context

1M

Input /M

$2.05/M

Output /M

$10.24/M

Cache read /M

$0.20/M

Cache hit

43.3%

TTFT

9.7s

Throughput

34.9 tps

Qwen3.8 27B

qwen3.8-27b:nube

Context

262k

Input /M

$0.31/M

Output /M

$1.89/M

Cache read /M

$0.06/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

qwen3.8-27b:thinking:nube

Context

262k

Input /M

$0.31/M

Output /M

$1.89/M

Cache read /M

$0.06/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

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 Nube via the API

Call a model served by Nube 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-v4-flash:nube",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, append :nube to the model ID, set "provider": "nube" in the request body, or send an X-Provider: nube 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.