Morph

Models served by Morph

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
DeepSeek V4 Flash 0731 BF16 deepseek/deepseek-v4-flash-0731:morph	1.0M	$0.10/M	$0.29/M	$0.03/M	N/A	1.1s	29 tps
DeepSeek V4 Flash 0731 (Thinking) BF16 deepseek/deepseek-v4-flash-0731:thinking:morph	1.0M	$0.10/M	$0.29/M	$0.03/M	N/A	1.1s	29 tps
GLM 5.3 FP4 zai-org/glm-5.3:morph	1.0M	$1.47/M	$4.62/M	$0.27/M	0%	5.7s	3 tps
GLM 5.3 (Thinking) FP4 zai-org/glm-5.3:thinking:morph	1.0M	$1.47/M	$4.62/M	$0.27/M	21.4%	5.7s	3 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:morph	1.0M	$0.16/M	$0.53/M	$0.03/M	0%	3.1s	18 tps
Kimi K3 FP4 moonshotai/kimi-k3:morph	1.0M	$6.30/M	$23.63/M	$0.63/M	N/A	3.1s	10 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 Morph via the API

Append :morph to the model ID, set "provider": "morph" in the request body, or send an X-Provider: morph 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:morph",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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