NeuralWatt

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 NeuralWatt

Model name

21 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4 Flash deepseek/deepseek-v4-flash:neuralwatt	1.0M	$0.15/M	$0.29/M	$0.03/M	N/A	N/A
DeepSeek V4 Flash (Thinking) deepseek/deepseek-v4-flash:thinking:neuralwatt	1.0M	$0.15/M	$0.29/M	$0.03/M	N/A	N/A
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:neuralwatt	1.0M	$0.15/M	$0.29/M	$0.03/M	N/A	N/A
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:neuralwatt	1.0M	$0.15/M	$0.29/M	$0.03/M	N/A	N/A
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:neuralwatt	1.0M	$0.16/M	$0.63/M	$0.02/M	N/A	N/A
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:neuralwatt	1.0M	$0.16/M	$0.63/M	$0.02/M	N/A	N/A
Gemma 4 31B FP4 google/gemma-4-31b-it:neuralwatt	262k	$0.15/M	$0.44/M	$0.02/M	N/A	N/A
Gemma 4 31B (Thinking) FP4 google/gemma-4-31b-it:thinking:neuralwatt	262k	$0.15/M	$0.44/M	$0.02/M	N/A	N/A
GLM 5.3 z-ai/glm-5.3:neuralwatt	1.0M	$1.52/M	$4.72/M	$0.15/M	N/A	N/A
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:neuralwatt	1.0M	$1.52/M	$4.72/M	$0.15/M	N/A	N/A
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:neuralwatt	1.0M	$0.16/M	$0.53/M	$0.03/M	N/A	N/A
Kimi K2.7 Code moonshotai/kimi-k2.7-code:neuralwatt	262k	$1.00/M	$4.20/M	$0.10/M	N/A	N/A
Kimi K2.7 Code Fast moonshotai/kimi-k2.7-code:neuralwatt-fast	262k	$1.00/M	$4.20/M	$0.10/M	N/A	N/A
Kimi K3 moonshotai/kimi-k3:neuralwatt	1.0M	$3.15/M	$15.75/M	$0.31/M	N/A	N/A
Kimi K3 Fast moonshotai/kimi-k3:neuralwatt-fast	1.0M	$3.15/M	$15.75/M	$0.31/M	N/A	N/A
MiMo V2.6 Pro xiaomi/mimo-v2.6-pro:neuralwatt	1.0M	$0.91/M	$1.83/M	$0.04/M	N/A	N/A
MiMo V2.6 Pro Flex xiaomi/mimo-v2.6-pro:neuralwatt-flex	1.0M	$0.59/M	$1.19/M	$0.02/M	N/A	N/A
Qwen 3.6 35B A3B Qwen/Qwen3.6-35B-A3B:neuralwatt	262k	$0.30/M	$1.21/M	$0.03/M	N/A	N/A
Qwen 3.6 35B A3B Thinking Qwen/Qwen3.6-35B-A3B:thinking:neuralwatt	262k	$0.30/M	$1.21/M	$0.03/M	N/A	N/A
Qwen3.8 27B FP8 qwen3.8-27b:neuralwatt	262k	$0.47/M	$3.36/M	$0.26/M	N/A	N/A
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:neuralwatt	262k	$0.47/M	$3.36/M	$0.26/M	N/A	N/A

DeepSeek V4 Flash

deepseek/deepseek-v4-flash:neuralwatt

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash (Thinking)

deepseek/deepseek-v4-flash:thinking:neuralwatt

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731:neuralwatt

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731 (Thinking)

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

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash:neuralwatt

Context

1.0M

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.02/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

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

Context

1.0M

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.02/M

TTFT

N/A

Throughput

N/A

Gemma 4 31B

FP4

google/gemma-4-31b-it:neuralwatt

Context

262k

Input /M

$0.15/M

Output /M

$0.44/M

Cache read /M

$0.02/M

TTFT

N/A

Throughput

N/A

Gemma 4 31B (Thinking)

FP4

google/gemma-4-31b-it:thinking:neuralwatt

Context

262k

Input /M

$0.15/M

Output /M

$0.44/M

Cache read /M

$0.02/M

TTFT

N/A

Throughput

N/A

GLM 5.3

z-ai/glm-5.3:neuralwatt

Context

1.0M

Input /M

$1.52/M

Output /M

$4.72/M

Cache read /M

$0.15/M

TTFT

N/A

Throughput

N/A

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:neuralwatt

Context

1.0M

Input /M

$1.52/M

Output /M

$4.72/M

Cache read /M

$0.15/M

TTFT

N/A

Throughput

N/A

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:neuralwatt

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

Kimi K2.7 Code

moonshotai/kimi-k2.7-code:neuralwatt

Context

262k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

$0.10/M

TTFT

N/A

Throughput

N/A

Kimi K2.7 Code

Fast

moonshotai/kimi-k2.7-code:neuralwatt-fast

Context

262k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

$0.10/M

TTFT

N/A

Throughput

N/A

Kimi K3

moonshotai/kimi-k3:neuralwatt

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.31/M

TTFT

N/A

Throughput

N/A

Kimi K3

Fast

moonshotai/kimi-k3:neuralwatt-fast

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.31/M

TTFT

N/A

Throughput

N/A

MiMo V2.6 Pro

xiaomi/mimo-v2.6-pro:neuralwatt

Context

1.0M

Input /M

$0.91/M

Output /M

$1.83/M

Cache read /M

$0.04/M

TTFT

N/A

Throughput

N/A

MiMo V2.6 Pro

Flex

xiaomi/mimo-v2.6-pro:neuralwatt-flex

Context

1.0M

Input /M

$0.59/M

Output /M

$1.19/M

Cache read /M

$0.02/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B

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

Context

262k

Input /M

$0.30/M

Output /M

$1.21/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

Qwen 3.6 35B A3B Thinking

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

Context

262k

Input /M

$0.30/M

Output /M

$1.21/M

Cache read /M

$0.03/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

FP8

qwen3.8-27b:neuralwatt

Context

262k

Input /M

$0.47/M

Output /M

$3.36/M

Cache read /M

$0.26/M

TTFT

N/A

Throughput

N/A

Qwen3.8 27B Thinking

FP8

qwen3.8-27b:thinking:neuralwatt

Context

262k

Input /M

$0.47/M

Output /M

$3.36/M

Cache read /M

$0.26/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 NeuralWatt via the API

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

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

NeuralWatt offers multiple service lanes, each pinned with its own id: neuralwatt, neuralwatt-fast (Fast), neuralwatt-flex (Flex). The table shows which lane serves each row.

See the API documentation for provider preferences, price-aware routing, and error behavior.