Morph

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 Morph

Model name

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:morph	1.0M	$0.06/M	$0.63/M	$0.01/M	52.1%	0.7s	71 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:morph	1.0M	$0.06/M	$0.63/M	$0.01/M	40.3%	0.7s	71 tps
GLM 5.2 FP8 z-ai/glm-5.2:morph	1.0M	$0.29/M	$3.93/M	$0.14/M	N/A	0.8s	38 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:morph	1.0M	$0.29/M	$3.93/M	$0.14/M	52.1%	0.8s	38 tps
GLM 5.3 FP8 z-ai/glm-5.3:morph	1.0M	$0.22/M	$3.93/M	$0.11/M	0%	1.4s	32 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:morph	1.0M	$0.22/M	$3.93/M	$0.11/M	0%	1.4s	32 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:morph	1.0M	$0.16/M	$0.73/M	$0.04/M	N/A	1.1s	68 tps
Kimi K3 FP8 moonshotai/kimi-k3:morph	1.0M	$1.30/M	$14.70/M	$0.30/M	71.7%	1.7s	49 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:morph

Context

1.0M

Input /M

$0.06/M

Output /M

$0.63/M

Cache read /M

$0.01/M

Cache hit

52.1%

TTFT

0.7s

Throughput

71 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.06/M

Output /M

$0.63/M

Cache read /M

$0.01/M

Cache hit

40.3%

TTFT

0.7s

Throughput

71 tps

GLM 5.2

FP8

z-ai/glm-5.2:morph

Context

1.0M

Input /M

$0.29/M

Output /M

$3.93/M

Cache read /M

$0.14/M

Cache hit

N/A

TTFT

0.8s

Throughput

38 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:morph

Context

1.0M

Input /M

$0.29/M

Output /M

$3.93/M

Cache read /M

$0.14/M

Cache hit

52.1%

TTFT

0.8s

Throughput

38 tps

GLM 5.3

FP8

z-ai/glm-5.3:morph

Context

1.0M

Input /M

$0.22/M

Output /M

$3.93/M

Cache read /M

$0.11/M

Cache hit

0%

TTFT

1.4s

Throughput

32 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:morph

Context

1.0M

Input /M

$0.22/M

Output /M

$3.93/M

Cache read /M

$0.11/M

Cache hit

0%

TTFT

1.4s

Throughput

32 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:morph

Context

1.0M

Input /M

$0.16/M

Output /M

$0.73/M

Cache read /M

$0.04/M

Cache hit

N/A

TTFT

1.1s

Throughput

68 tps

Kimi K3

FP8

moonshotai/kimi-k3:morph

Context

1.0M

Input /M

$1.30/M

Output /M

$14.70/M

Cache read /M

$0.30/M

Cache hit

71.7%

TTFT

1.7s

Throughput

49 tps

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 Morph via the API

Call a model served by Morph 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-v4.1-flash:morph",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

For models with provider selection, 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 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.