Ambient

Models served by Ambient

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
DeepSeek V4 Flash 0731 FP4 deepseek/deepseek-v4-flash-0731:ambient	1.0M	$0.08/M	$0.19/M	$0.02/M	N/A	0.8s	85 tps
DeepSeek V4 Flash 0731 (Thinking) FP4 deepseek/deepseek-v4-flash-0731:thinking:ambient	1.0M	$0.08/M	$0.19/M	$0.02/M	N/A	0.8s	85 tps
GLM 5.2 FP8 zai-org/glm-5.2:ambient	1.0M	$0.63/M	$2.10/M	$0.16/M	N/A	2.6s	20 tps
GLM 5.2 (Thinking) FP8 zai-org/glm-5.2:thinking:ambient	1.0M	$0.63/M	$2.10/M	$0.16/M	N/A	2.6s	20 tps
Kimi K2.7 Code moonshotai/kimi-k2.7-code:ambient	262k	$0.72/M	$3.66/M	$0.15/M	0%	0.9s	69 tps

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using Ambient via the API

Append :ambient to the model ID, set "provider": "ambient" in the request body, or send an X-Provider: ambient header. Explicit provider selection adds a 5% markup over that provider's base price; the prices in the table above already include it.

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

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