Decart

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 Decart

Model name

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4.1 Flash FP4 deepseek/deepseek-v4.1-flash:decart	1.0M	$0.09/M	$0.19/M	$0.02/M	80.2%	0.9s	55 tps
DeepSeek V4.1 Flash (Thinking) FP4 deepseek/deepseek-v4.1-flash:thinking:decart	1.0M	$0.09/M	$0.19/M	$0.02/M	87.1%	0.9s	55 tps
GLM 5.2 FP4 z-ai/glm-5.2:decart	1.0M	$2.89/M	$10.50/M	$0.63/M	83.3%	0.6s	203 tps
GLM 5.2 (Thinking) FP4 z-ai/glm-5.2:thinking:decart	1.0M	$2.89/M	$10.50/M	$0.63/M	27%	0.6s	203 tps
GLM 5.3 FP4 z-ai/glm-5.3:decart	1.0M	$0.88/M	$2.78/M	$0.21/M	0.7%	0.8s	135 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:decart	1.0M	$0.88/M	$2.78/M	$0.21/M	21.2%	0.8s	135 tps
GLM 5.3 Flash FP4 z-ai/glm-5.3-flash:decart	1.0M	$0.10/M	$0.33/M	$0.02/M	0%	3.2s	29 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:decart	1.0M	$2.17/M	$10.87/M	$0.22/M	52.5%	40.4s	9 tps

DeepSeek V4.1 Flash

FP4

deepseek/deepseek-v4.1-flash:decart

Context

1.0M

Input /M

$0.09/M

Output /M

$0.19/M

Cache read /M

$0.02/M

Cache hit

80.2%

TTFT

0.9s

Throughput

55 tps

DeepSeek V4.1 Flash (Thinking)

FP4

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

Context

1.0M

Input /M

$0.09/M

Output /M

$0.19/M

Cache read /M

$0.02/M

Cache hit

87.1%

TTFT

0.9s

Throughput

55 tps

GLM 5.2

FP4

z-ai/glm-5.2:decart

Context

1.0M

Input /M

$2.89/M

Output /M

$10.50/M

Cache read /M

$0.63/M

Cache hit

83.3%

TTFT

0.6s

Throughput

203 tps

GLM 5.2 (Thinking)

FP4

z-ai/glm-5.2:thinking:decart

Context

1.0M

Input /M

$2.89/M

Output /M

$10.50/M

Cache read /M

$0.63/M

Cache hit

27%

TTFT

0.6s

Throughput

203 tps

GLM 5.3

FP4

z-ai/glm-5.3:decart

Context

1.0M

Input /M

$0.88/M

Output /M

$2.78/M

Cache read /M

$0.21/M

Cache hit

0.7%

TTFT

0.8s

Throughput

135 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:decart

Context

1.0M

Input /M

$0.88/M

Output /M

$2.78/M

Cache read /M

$0.21/M

Cache hit

21.2%

TTFT

0.8s

Throughput

135 tps

GLM 5.3 Flash

FP4

z-ai/glm-5.3-flash:decart

Context

1.0M

Input /M

$0.10/M

Output /M

$0.33/M

Cache read /M

$0.02/M

Cache hit

0%

TTFT

3.2s

Throughput

29 tps

Kimi K3

MXFP4

moonshotai/kimi-k3:decart

Context

1.0M

Input /M

$2.17/M

Output /M

$10.87/M

Cache read /M

$0.22/M

Cache hit

52.5%

TTFT

40.4s

Throughput

9 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 Decart via the API

Call a model served by Decart 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-v4.1-flash:decart",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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