Entrim

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 Entrim

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:entrim	1M	$0.20/M	$0.60/M	$0.0049/M	N/A	N/A
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:entrim	1M	$0.20/M	$0.60/M	$0.0049/M	N/A	N/A
GLM 5.3 Flash NVFP4 z-ai/glm-5.3-flash:entrim	1M	$0.10/M	$0.35/M	$0.02/M	N/A	N/A
Qwen3.8 27B FP8 qwen3.8-27b:entrim	262k	$0.10/M	$0.40/M	$0.04/M	N/A	N/A
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:entrim	262k	$0.10/M	$0.40/M	$0.04/M	N/A	N/A

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:entrim

Context

1M

Input /M

$0.20/M

Output /M

$0.60/M

Cache read /M

$0.0049/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1M

Input /M

$0.20/M

Output /M

$0.60/M

Cache read /M

$0.0049/M

TTFT

N/A

Throughput

N/A

GLM 5.3 Flash

NVFP4

z-ai/glm-5.3-flash:entrim

Context

1M

Input /M

$0.10/M

Output /M

$0.35/M

Cache read /M

$0.02/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

FP8

qwen3.8-27b:entrim

Context

262k

Input /M

$0.10/M

Output /M

$0.40/M

Cache read /M

$0.04/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

FP8

qwen3.8-27b:thinking:entrim

Context

262k

Input /M

$0.10/M

Output /M

$0.40/M

Cache read /M

$0.04/M

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 Entrim via the API

Call a model served by Entrim 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:entrim",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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