EngyAI

EngyAI states that its current provider fleet uses TEE-backed or controlled infrastructure and advertises zero-data retention for allowlisted routes. NanoGPT does not independently verify provider attestations.

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 EngyAI

Model name

14 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:engy	1.0M	$0.05/M	$0.09/M	$0.0095/M	76.7%	4.3s	240.7 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:engy	1.0M	$0.05/M	$0.09/M	$0.0095/M	31.2%	3.5s	160 tps
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:engy	262k	$0.04/M	$0.08/M	$0.0084/M	74.6%	3.7s	70.1 tps
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:engy	262k	$0.04/M	$0.08/M	$0.0084/M	46.3%	11.9s	41.4 tps
GLM 5.2 z-ai/glm-5.2:engy	262k	$0.71/M	$1.57/M	$0.19/M	N/A	N/A	N/A
GLM 5.2 (Thinking) z-ai/glm-5.2:thinking:engy	262k	$0.71/M	$1.57/M	$0.19/M	N/A	N/A	N/A
GLM 5.3 z-ai/glm-5.3:engy	328k	$1.03/M	$3.23/M	$0.19/M	N/A	1.1s	39.8 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:engy	328k	$1.03/M	$3.23/M	$0.19/M	N/A	1.1s	39.8 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:engy	328k	$0.14/M	$0.47/M	$0.03/M	N/A	N/A	N/A
Kimi K3 moonshotai/kimi-k3:engy	1.1M	$2.05/M	$10.24/M	$0.20/M	28.2%	2s	116.3 tps
Qwen 3.6 35B A3B Qwen/Qwen3.6-35B-A3B:engy	208k	$0.05/M	$0.31/M	$0.02/M	0%	3s	127.4 tps
Qwen 3.6 35B A3B Thinking Qwen/Qwen3.6-35B-A3B:thinking:engy	208k	$0.05/M	$0.31/M	$0.02/M	0%	4s	111.5 tps
Qwen3.8 27B qwen3.8-27b:engy	1.0M	$0.05/M	$0.34/M	$0.02/M	88.9%	2s	77.8 tps
Qwen3.8 27B Thinking qwen3.8-27b:thinking:engy	1.0M	$0.05/M	$0.34/M	$0.02/M	46.5%	1.8s	118 tps

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731:engy

Context

1.0M

Input /M

$0.05/M

Output /M

$0.09/M

Cache read /M

$0.0095/M

Cache hit

76.7%

TTFT

4.3s

Throughput

240.7 tps

DeepSeek V4 Flash 0731 (Thinking)

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

Context

1.0M

Input /M

$0.05/M

Output /M

$0.09/M

Cache read /M

$0.0095/M

Cache hit

31.2%

TTFT

3.5s

Throughput

160 tps

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash:engy

Context

262k

Input /M

$0.04/M

Output /M

$0.08/M

Cache read /M

$0.0084/M

Cache hit

74.6%

TTFT

3.7s

Throughput

70.1 tps

DeepSeek V4.1 Flash (Thinking)

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

Context

262k

Input /M

$0.04/M

Output /M

$0.08/M

Cache read /M

$0.0084/M

Cache hit

46.3%

TTFT

11.9s

Throughput

41.4 tps

GLM 5.2

z-ai/glm-5.2:engy

Context

262k

Input /M

$0.71/M

Output /M

$1.57/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 5.2 (Thinking)

z-ai/glm-5.2:thinking:engy

Context

262k

Input /M

$0.71/M

Output /M

$1.57/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

GLM 5.3

z-ai/glm-5.3:engy

Context

328k

Input /M

$1.03/M

Output /M

$3.23/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

1.1s

Throughput

39.8 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:engy

Context

328k

Input /M

$1.03/M

Output /M

$3.23/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

1.1s

Throughput

39.8 tps

GLM 5.3 Flash

z-ai/glm-5.3-flash:engy

Context

328k

Input /M

$0.14/M

Output /M

$0.47/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K3

moonshotai/kimi-k3:engy

Context

1.1M

Input /M

$2.05/M

Output /M

$10.24/M

Cache read /M

$0.20/M

Cache hit

28.2%

TTFT

2s

Throughput

116.3 tps

Qwen 3.6 35B A3B

Qwen/Qwen3.6-35B-A3B:engy

Context

208k

Input /M

$0.05/M

Output /M

$0.31/M

Cache read /M

$0.02/M

Cache hit

0%

TTFT

3s

Throughput

127.4 tps

Qwen 3.6 35B A3B Thinking

Qwen/Qwen3.6-35B-A3B:thinking:engy

Context

208k

Input /M

$0.05/M

Output /M

$0.31/M

Cache read /M

$0.02/M

Cache hit

0%

TTFT

4s

Throughput

111.5 tps

Qwen3.8 27B

qwen3.8-27b:engy

Context

1.0M

Input /M

$0.05/M

Output /M

$0.34/M

Cache read /M

$0.02/M

Cache hit

88.9%

TTFT

2s

Throughput

77.8 tps

Qwen3.8 27B Thinking

qwen3.8-27b:thinking:engy

Context

1.0M

Input /M

$0.05/M

Output /M

$0.34/M

Cache read /M

$0.02/M

Cache hit

46.5%

TTFT

1.8s

Throughput

118 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 EngyAI via the API

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

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