Entrim

Models served by Entrim

Model name

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4.1 Flash 1017 FP8 ZDR deepseek/deepseek-v4.1-flash-1017:entrim	1.0M	$0.21/M	$0.63/M	$0.00525/M	47.5%	8.1s	30 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP8 ZDR deepseek/deepseek-v4.1-flash-1017:thinking:entrim	1.0M	$0.21/M	$0.63/M	$0.00525/M	61.9%	1.3s	147.7 tps
GLM 5.3 Flash NVFP4 ZDR z-ai/glm-5.3-flash:entrim	1M	$0.0998/M	$0.347/M	$0.0168/M	83%	6.2s	341.6 tps
GLM 5.3 Uncensored ZDR z-ai/glm-5.3-uncensored:entrim	1.0M	$1.05/M	$2.10/M	$0.263/M	93.6%	8.3s	246.6 tps
Qwen3.8 27B FP8 ZDR qwen3.8-27b:entrim	262k	$0.0998/M	$0.399/M	$0.0399/M	N/A	N/A	N/A
Qwen3.8 27B Thinking FP8 ZDR qwen3.8-27b:thinking:entrim	262k	$0.0998/M	$0.399/M	$0.0399/M	N/A	N/A	N/A

DeepSeek V4.1 Flash 1017

FP8

ZDR

deepseek/deepseek-v4.1-flash-1017:entrim

Context

1.0M

Input /M

$0.21/M

Output /M

$0.63/M

Cache read /M

$0.00525/M

Cache hit

47.5%

TTFT

8.1s

Throughput

30 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

ZDR

deepseek/deepseek-v4.1-flash-1017:thinking:entrim

Context

1.0M

Input /M

$0.21/M

Output /M

$0.63/M

Cache read /M

$0.00525/M

Cache hit

61.9%

TTFT

1.3s

Throughput

147.7 tps

GLM 5.3 Flash

NVFP4

ZDR

z-ai/glm-5.3-flash:entrim

Context

1M

Input /M

$0.0998/M

Output /M

$0.347/M

Cache read /M

$0.0168/M

Cache hit

83%

TTFT

6.2s

Throughput

341.6 tps

GLM 5.3 Uncensored

ZDR

z-ai/glm-5.3-uncensored:entrim

Context

1.0M

Input /M

$1.05/M

Output /M

$2.10/M

Cache read /M

$0.263/M

Cache hit

93.6%

TTFT

8.3s

Throughput

246.6 tps

Qwen3.8 27B

FP8

ZDR

qwen3.8-27b:entrim

Context

262k

Input /M

$0.0998/M

Output /M

$0.399/M

Cache read /M

$0.0399/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

FP8

ZDR

qwen3.8-27b:thinking:entrim

Context

262k

Input /M

$0.0998/M

Output /M

$0.399/M

Cache read /M

$0.0399/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 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-1017: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.