Modal

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 Modal

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:modal	1.0M	$0.31/M	$1.26/M	$0.03/M	0.9s	115 tps
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:modal	1.0M	$0.31/M	$1.26/M	$0.03/M	0.9s	115 tps
GLM 5.3 z-ai/glm-5.3:modal	1.0M	$1.47/M	$4.62/M	$0.27/M	0.6s	98 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:modal	1.0M	$1.47/M	$4.62/M	$0.27/M	0.6s	98 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:modal	1.0M	$0.47/M	$1.57/M	$0.09/M	0.3s	56 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:modal	1.0M	$3.15/M	$15.75/M	$0.31/M	1.4s	58 tps
Qwen3.8 Max qwen3.8-max:modal	1M	$2.10/M	$6.30/M	$0.26/M	0.8s	59.5 tps
Qwen3.8 Max Thinking qwen3.8-max:thinking:modal	1M	$2.10/M	$6.30/M	$0.26/M	0.8s	59.5 tps

Prices are per million tokens. 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 Modal via the API

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

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:modal",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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