Inceptron

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 Inceptron

Model name

10 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 FP4 deepseek/deepseek-v4-flash-0731:inceptron	1.0M	$0.05/M	$0.68/M	$0.03/M	N/A	0.7s	69 tps
DeepSeek V4 Flash 0731 (Thinking) FP4 deepseek/deepseek-v4-flash-0731:thinking:inceptron	1.0M	$0.05/M	$0.68/M	$0.03/M	N/A	0.7s	69 tps
GLM 5.2 FP4 z-ai/glm-5.2:inceptron	1.0M	$1.46/M	$4.61/M	$0.26/M	N/A	0.3s	114 tps
GLM 5.2 (Thinking) FP4 z-ai/glm-5.2:thinking:inceptron	1.0M	$1.46/M	$4.61/M	$0.26/M	N/A	0.3s	114 tps
GLM 5.3 FP4 z-ai/glm-5.3:inceptron	1.0M	$0.63/M	$3.56/M	$0.21/M	N/A	0.9s	104 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:inceptron	1.0M	$0.63/M	$3.56/M	$0.21/M	N/A	0.9s	104 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:inceptron	1.0M	$0.24/M	$0.63/M	$0.09/M	80%	0.6s	88 tps
Kimi K2.6 INT4 moonshotai/kimi-k2.6:inceptron	262k	$0.46/M	$2.57/M	$0.13/M	2.8%	0.5s	58 tps
Kimi K2.6 Thinking INT4 moonshotai/kimi-k2.6:thinking:inceptron	262k	$0.46/M	$2.57/M	$0.13/M	0%	0.5s	58 tps
Kimi K2.7 Code INT4 moonshotai/kimi-k2.7-code:inceptron	262k	$0.70/M	$3.52/M	$0.19/M	50.2%	0.8s	67 tps

DeepSeek V4 Flash 0731

FP4

deepseek/deepseek-v4-flash-0731:inceptron

Context

1.0M

Input /M

$0.05/M

Output /M

$0.68/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

0.7s

Throughput

69 tps

DeepSeek V4 Flash 0731 (Thinking)

FP4

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

Context

1.0M

Input /M

$0.05/M

Output /M

$0.68/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

0.7s

Throughput

69 tps

GLM 5.2

FP4

z-ai/glm-5.2:inceptron

Context

1.0M

Input /M

$1.46/M

Output /M

$4.61/M

Cache read /M

$0.26/M

Cache hit

N/A

TTFT

0.3s

Throughput

114 tps

GLM 5.2 (Thinking)

FP4

z-ai/glm-5.2:thinking:inceptron

Context

1.0M

Input /M

$1.46/M

Output /M

$4.61/M

Cache read /M

$0.26/M

Cache hit

N/A

TTFT

0.3s

Throughput

114 tps

GLM 5.3

FP4

z-ai/glm-5.3:inceptron

Context

1.0M

Input /M

$0.63/M

Output /M

$3.56/M

Cache read /M

$0.21/M

Cache hit

N/A

TTFT

0.9s

Throughput

104 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:inceptron

Context

1.0M

Input /M

$0.63/M

Output /M

$3.56/M

Cache read /M

$0.21/M

Cache hit

N/A

TTFT

0.9s

Throughput

104 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:inceptron

Context

1.0M

Input /M

$0.24/M

Output /M

$0.63/M

Cache read /M

$0.09/M

Cache hit

80%

TTFT

0.6s

Throughput

88 tps

Kimi K2.6

INT4

moonshotai/kimi-k2.6:inceptron

Context

262k

Input /M

$0.46/M

Output /M

$2.57/M

Cache read /M

$0.13/M

Cache hit

2.8%

TTFT

0.5s

Throughput

58 tps

Kimi K2.6 Thinking

INT4

moonshotai/kimi-k2.6:thinking:inceptron

Context

262k

Input /M

$0.46/M

Output /M

$2.57/M

Cache read /M

$0.13/M

Cache hit

0%

TTFT

0.5s

Throughput

58 tps

Kimi K2.7 Code

INT4

moonshotai/kimi-k2.7-code:inceptron

Context

262k

Input /M

$0.70/M

Output /M

$3.52/M

Cache read /M

$0.19/M

Cache hit

50.2%

TTFT

0.8s

Throughput

67 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 Inceptron via the API

Call a model served by Inceptron 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-0731:inceptron",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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