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	TTFT	Throughput
DeepSeek V4.1 Flash FP4 deepseek/deepseek-v4.1-flash:decart	1.0M	$0.09/M	$0.19/M	$0.02/M	0.8s	34 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	0.8s	34 tps
GLM 5.2 FP4 z-ai/glm-5.2:decart	1.0M	$2.63/M	$9.45/M	$0.57/M	1.3s	215 tps
GLM 5.2 (Thinking) FP4 z-ai/glm-5.2:thinking:decart	1.0M	$2.63/M	$9.45/M	$0.57/M	1.3s	215 tps
GLM 5.3 FP4 z-ai/glm-5.3:decart	1.0M	$0.97/M	$3.07/M	$0.22/M	17.4s	17 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:decart	1.0M	$0.97/M	$3.07/M	$0.22/M	17.4s	17 tps
GLM 5.3 Flash FP4 z-ai/glm-5.3-flash:decart	1.0M	$0.10/M	$0.33/M	$0.02/M	1.3s	63 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:decart	1.0M	$2.21/M	$11.03/M	$0.22/M	1.5s	52 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

TTFT

0.8s

Throughput

34 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

TTFT

0.8s

Throughput

34 tps

GLM 5.2

FP4

z-ai/glm-5.2:decart

Context

1.0M

Input /M

$2.63/M

Output /M

$9.45/M

Cache read /M

$0.57/M

TTFT

1.3s

Throughput

215 tps

GLM 5.2 (Thinking)

FP4

z-ai/glm-5.2:thinking:decart

Context

1.0M

Input /M

$2.63/M

Output /M

$9.45/M

Cache read /M

$0.57/M

TTFT

1.3s

Throughput

215 tps

GLM 5.3

FP4

z-ai/glm-5.3:decart

Context

1.0M

Input /M

$0.97/M

Output /M

$3.07/M

Cache read /M

$0.22/M

TTFT

17.4s

Throughput

17 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:decart

Context

1.0M

Input /M

$0.97/M

Output /M

$3.07/M

Cache read /M

$0.22/M

TTFT

17.4s

Throughput

17 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

TTFT

1.3s

Throughput

63 tps

Kimi K3

MXFP4

moonshotai/kimi-k3:decart

Context

1.0M

Input /M

$2.21/M

Output /M

$11.03/M

Cache read /M

$0.22/M

TTFT

1.5s

Throughput

52 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.