SCX (Global)

SCX directly confirmed zero data retention across its inference catalogue.

Models served by SCX (Global)

Model name

17 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4.1 Flash FP8 ZDR deepseek/deepseek-v4.1-flash:scx	1.0M	$0.157/M	$0.63/M	$0.0105/M	N/A	N/A	N/A
DeepSeek V4.1 Flash (Thinking) FP8 ZDR deepseek/deepseek-v4.1-flash:thinking:scx	1.0M	$0.157/M	$0.63/M	$0.0105/M	N/A	N/A	N/A
Gemma 4 31B BF16 ZDR google/gemma-4-31b-it:scx	131k	$0.315/M	$0.956/M	N/A	0%	3.5s	269.4 tps
Gemma 4 31B (Thinking) BF16 ZDR google/gemma-4-31b-it:thinking:scx	131k	$0.315/M	$0.956/M	N/A	0%	3.5s	269.4 tps
GLM 5.2 BF16 ZDR z-ai/glm-5.2:scx	1.0M	$0.635/M	$2.23/M	$0.162/M	76.1%	4s	60.5 tps
GLM 5.2 (Thinking) BF16 ZDR z-ai/glm-5.2:thinking:scx	1.0M	$0.635/M	$2.23/M	$0.162/M	76.1%	6.1s	55.6 tps
GLM 5.3 BF16 ZDR z-ai/glm-5.3:scx	1.0M	$0.97/M	$3.05/M	$0.18/M	4%	2.8s	55.4 tps
GLM 5.3 (Thinking) BF16 ZDR z-ai/glm-5.3:thinking:scx	1.0M	$0.97/M	$3.05/M	$0.18/M	59.8%	3.6s	86.2 tps
GLM 5.3 Flash FP8 ZDR z-ai/glm-5.3-flash:scx	1.0M	$0.0924/M	$0.263/M	$0.0263/M	88.6%	7.8s	86.4 tps
GPT OSS 120B FP8 ZDR openai/gpt-oss-120b:scx	131k	$0.179/M	$0.578/M	N/A	N/A	N/A	N/A
Kimi K2.7 Code FP8 ZDR moonshotai/kimi-k2.7-code:scx	262k	$0.774/M	$3.23/M	$0.15/M	N/A	N/A	N/A
Kimi K3 FP8 ZDR moonshotai/kimi-k3:scx	1.0M	$3.29/M	$16.46/M	$0.335/M	N/A	N/A	N/A
Llama 4 Maverick FP8 ZDR meta-llama/llama-4-maverick:scx	131k	$0.556/M	$1.70/M	N/A	N/A	N/A	N/A
MiniMax M2.7 FP8 ZDR minimax/minimax-m2.7:scx	192k	$0.504/M	$1.88/M	$0.0525/M	N/A	N/A	N/A
Qwen3 32B BF16 ZDR qwen/qwen3-32b:scx	33k	$0.378/M	$0.913/M	N/A	N/A	N/A	N/A
Qwen3.8 Max ZDR qwen3.8-max:scx	1M	$1.62/M	$4.86/M	$0.208/M	N/A	N/A	N/A
Qwen3.8 Max Thinking ZDR qwen3.8-max:thinking:scx	1M	$1.62/M	$4.86/M	$0.208/M	N/A	N/A	N/A

DeepSeek V4.1 Flash

FP8

ZDR

deepseek/deepseek-v4.1-flash:scx

Context

1.0M

Input /M

$0.157/M

Output /M

$0.63/M

Cache read /M

$0.0105/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

FP8

ZDR

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

Context

1.0M

Input /M

$0.157/M

Output /M

$0.63/M

Cache read /M

$0.0105/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Gemma 4 31B

BF16

ZDR

google/gemma-4-31b-it:scx

Context

131k

Input /M

$0.315/M

Output /M

$0.956/M

Cache read /M

N/A

Cache hit

0%

TTFT

3.5s

Throughput

269.4 tps

Gemma 4 31B (Thinking)

BF16

ZDR

google/gemma-4-31b-it:thinking:scx

Context

131k

Input /M

$0.315/M

Output /M

$0.956/M

Cache read /M

N/A

Cache hit

0%

TTFT

3.5s

Throughput

269.4 tps

GLM 5.2

BF16

ZDR

z-ai/glm-5.2:scx

Context

1.0M

Input /M

$0.635/M

Output /M

$2.23/M

Cache read /M

$0.162/M

Cache hit

76.1%

TTFT

4s

Throughput

60.5 tps

GLM 5.2 (Thinking)

BF16

ZDR

z-ai/glm-5.2:thinking:scx

Context

1.0M

Input /M

$0.635/M

Output /M

$2.23/M

Cache read /M

$0.162/M

Cache hit

76.1%

TTFT

6.1s

Throughput

55.6 tps

GLM 5.3

BF16

ZDR

z-ai/glm-5.3:scx

Context

1.0M

Input /M

$0.97/M

Output /M

$3.05/M

Cache read /M

$0.18/M

Cache hit

4%

TTFT

2.8s

Throughput

55.4 tps

GLM 5.3 (Thinking)

BF16

ZDR

z-ai/glm-5.3:thinking:scx

Context

1.0M

Input /M

$0.97/M

Output /M

$3.05/M

Cache read /M

$0.18/M

Cache hit

59.8%

TTFT

3.6s

Throughput

86.2 tps

GLM 5.3 Flash

FP8

ZDR

z-ai/glm-5.3-flash:scx

Context

1.0M

Input /M

$0.0924/M

Output /M

$0.263/M

Cache read /M

$0.0263/M

Cache hit

88.6%

TTFT

7.8s

Throughput

86.4 tps

GPT OSS 120B

FP8

ZDR

openai/gpt-oss-120b:scx

Context

131k

Input /M

$0.179/M

Output /M

$0.578/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K2.7 Code

FP8

ZDR

moonshotai/kimi-k2.7-code:scx

Context

262k

Input /M

$0.774/M

Output /M

$3.23/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K3

FP8

ZDR

moonshotai/kimi-k3:scx

Context

1.0M

Input /M

$3.29/M

Output /M

$16.46/M

Cache read /M

$0.335/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Llama 4 Maverick

FP8

ZDR

meta-llama/llama-4-maverick:scx

Context

131k

Input /M

$0.556/M

Output /M

$1.70/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

MiniMax M2.7

FP8

ZDR

minimax/minimax-m2.7:scx

Context

192k

Input /M

$0.504/M

Output /M

$1.88/M

Cache read /M

$0.0525/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3 32B

BF16

ZDR

qwen/qwen3-32b:scx

Context

33k

Input /M

$0.378/M

Output /M

$0.913/M

Cache read /M

N/A

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 Max

ZDR

qwen3.8-max:scx

Context

1M

Input /M

$1.62/M

Output /M

$4.86/M

Cache read /M

$0.208/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 Max Thinking

ZDR

qwen3.8-max:thinking:scx

Context

1M

Input /M

$1.62/M

Output /M

$4.86/M

Cache read /M

$0.208/M

Cache hit

N/A

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 SCX (Global) via the API

Call a model served by SCX (Global) 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:scx",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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