OpenScale

OpenScale is not a zero-retention provider in NanoGPT; zero-retention requests do not use it pending its signed Supplier Data Addendum. OpenScale states that inference runs on its own GPUs at iForte and RunPod, with its gateway and database on Google Cloud, and that its infrastructure providers do not see request content. OpenScale states that content is not retained or used for training; its published policy keeps request metadata for 30 days.

Models served by OpenScale

Model name

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4.1 Flash 1017 Unverified deepseek/deepseek-v4.1-flash-1017:openscale	1.0M	$0.063/M	$0.252/M	$0.0032/M	N/A	N/A
DeepSeek V4.1 Flash 1017 (Thinking) Unverified deepseek/deepseek-v4.1-flash-1017:thinking:openscale	1.0M	$0.063/M	$0.252/M	$0.0032/M	N/A	N/A
GLM 5.3 Flash Unverified z-ai/glm-5.3-flash:openscale	1.0M	$0.126/M	$0.42/M	$0.0252/M	N/A	N/A

DeepSeek V4.1 Flash 1017

Unverified

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

Context

1.0M

Input /M

$0.063/M

Output /M

$0.252/M

Cache read /M

$0.0032/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash 1017 (Thinking)

Unverified

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

Context

1.0M

Input /M

$0.063/M

Output /M

$0.252/M

Cache read /M

$0.0032/M

TTFT

N/A

Throughput

N/A

GLM 5.3 Flash

Unverified

z-ai/glm-5.3-flash:openscale

Context

1.0M

Input /M

$0.126/M

Output /M

$0.42/M

Cache read /M

$0.0252/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 OpenScale via the API

Call a model served by OpenScale using its displayed model ID, including the provider suffix when selection is supported.

curl https://api.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:openscale",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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