Relace

Models served by Relace

Model name

19 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash FP4 Unverified deepseek/deepseek-v4-flash:relace	1.0M	$0.0498/M	$0.472/M	$0.0498/M	18.4%	0.6s	96 tps
DeepSeek V4 Flash (Thinking) FP4 Unverified deepseek/deepseek-v4-flash:thinking:relace	1.0M	$0.0498/M	$0.472/M	$0.0498/M	18.4%	0.6s	96 tps
DeepSeek V4 Flash 0731 FP4 Unverified deepseek/deepseek-v4-flash-0731:relace	1.0M	$0.0735/M	$0.147/M	$0.0147/M	N/A	0.5s	54 tps
DeepSeek V4 Flash 0731 (Thinking) FP4 Unverified deepseek/deepseek-v4-flash-0731:thinking:relace	1.0M	$0.0735/M	$0.147/M	$0.0147/M	N/A	0.5s	54 tps
DeepSeek V4 Pro FP4 Unverified deepseek/deepseek-v4-pro:relace	1.0M	$0.735/M	$1.47/M	$0.0735/M	40.7%	0.8s	87 tps
DeepSeek V4 Pro (Thinking) FP4 Unverified deepseek/deepseek-v4-pro:thinking:relace	1.0M	$0.735/M	$1.47/M	$0.0735/M	40.7%	0.8s	87 tps
DeepSeek V4 Pro 0813 FP4 Unverified deepseek/deepseek-v4-pro-0813:relace	1.0M	$0.109/M	$8.40/M	$0.105/M	97.9%	1.6s	41 tps
DeepSeek V4 Pro 0813 (Thinking) FP4 Unverified deepseek/deepseek-v4-pro-0813:thinking:relace	1.0M	$0.109/M	$8.40/M	$0.105/M	94%	1.6s	41 tps
DeepSeek V4.1 Flash FP4 Unverified deepseek/deepseek-v4.1-flash:relace	1.0M	$0.0368/M	$0.525/M	$0.00525/M	38.6%	0.4s	133 tps
DeepSeek V4.1 Flash (Thinking) FP4 Unverified deepseek/deepseek-v4.1-flash:thinking:relace	1.0M	$0.0368/M	$0.525/M	$0.00525/M	94.5%	0.4s	133 tps
DeepSeek V4.1 Flash 1017 FP4 Unverified deepseek/deepseek-v4.1-flash-1017:relace	1.0M	$0.0368/M	$0.525/M	$0.00525/M	19%	0.7s	103 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP4 Unverified deepseek/deepseek-v4.1-flash-1017:thinking:relace	1.0M	$0.0368/M	$0.525/M	$0.00525/M	19%	0.7s	103 tps
GLM 5.2 FP4 Unverified z-ai/glm-5.2:relace	1.0M	$0.00683/M	$8.30/M	$0.00683/M	41.2%	1.7s	25 tps
GLM 5.2 (Thinking) FP4 Unverified z-ai/glm-5.2:thinking:relace	1.0M	$0.00683/M	$8.30/M	$0.00683/M	37.3%	1.7s	25 tps
GLM 5.3 FP4 Unverified z-ai/glm-5.3:relace	1.0M	$0.0738/M	$4.60/M	$0.0738/M	50.4%	0.8s	79 tps
GLM 5.3 (Thinking) FP4 Unverified z-ai/glm-5.3:thinking:relace	1.0M	$0.0738/M	$4.60/M	$0.0738/M	70.3%	0.8s	79 tps
GLM 5.3 Flash FP4 Unverified z-ai/glm-5.3-flash:relace	1.0M	$0.0282/M	$0.105/M	$0.0282/M	N/A	0.7s	70 tps
Kimi K3 FP4 Unverified moonshotai/kimi-k3:relace	1.0M	$0.162/M	$11.08/M	$0.157/M	29.8%	1.2s	66 tps
MiniMax M3.1 Flash FP4 Unverified minimax/minimax-m3.1-flash:relace	1M	$0.0945/M	$0.525/M	$0.0105/M	N/A	N/A	N/A

DeepSeek V4 Flash

FP4

Unverified

deepseek/deepseek-v4-flash:relace

Context

1.0M

Input /M

$0.0498/M

Output /M

$0.472/M

Cache read /M

$0.0498/M

Cache hit

18.4%

TTFT

0.6s

Throughput

96 tps

DeepSeek V4 Flash (Thinking)

FP4

Unverified

deepseek/deepseek-v4-flash:thinking:relace

Context

1.0M

Input /M

$0.0498/M

Output /M

$0.472/M

Cache read /M

$0.0498/M

Cache hit

18.4%

TTFT

0.6s

Throughput

96 tps

DeepSeek V4 Flash 0731

FP4

Unverified

deepseek/deepseek-v4-flash-0731:relace

Context

1.0M

Input /M

$0.0735/M

Output /M

$0.147/M

Cache read /M

$0.0147/M

Cache hit

N/A

TTFT

0.5s

Throughput

54 tps

DeepSeek V4 Flash 0731 (Thinking)

FP4

Unverified

deepseek/deepseek-v4-flash-0731:thinking:relace

Context

1.0M

Input /M

$0.0735/M

Output /M

$0.147/M

Cache read /M

$0.0147/M

Cache hit

N/A

TTFT

0.5s

Throughput

54 tps

DeepSeek V4 Pro

FP4

Unverified

deepseek/deepseek-v4-pro:relace

Context

1.0M

Input /M

$0.735/M

Output /M

$1.47/M

Cache read /M

$0.0735/M

Cache hit

40.7%

TTFT

0.8s

Throughput

87 tps

DeepSeek V4 Pro (Thinking)

FP4

Unverified

deepseek/deepseek-v4-pro:thinking:relace

Context

1.0M

Input /M

$0.735/M

Output /M

$1.47/M

Cache read /M

$0.0735/M

Cache hit

40.7%

TTFT

0.8s

Throughput

87 tps

DeepSeek V4 Pro 0813

FP4

Unverified

deepseek/deepseek-v4-pro-0813:relace

Context

1.0M

Input /M

$0.109/M

Output /M

$8.40/M

Cache read /M

$0.105/M

Cache hit

97.9%

TTFT

1.6s

Throughput

41 tps

DeepSeek V4 Pro 0813 (Thinking)

FP4

Unverified

deepseek/deepseek-v4-pro-0813:thinking:relace

Context

1.0M

Input /M

$0.109/M

Output /M

$8.40/M

Cache read /M

$0.105/M

Cache hit

94%

TTFT

1.6s

Throughput

41 tps

DeepSeek V4.1 Flash

FP4

Unverified

deepseek/deepseek-v4.1-flash:relace

Context

1.0M

Input /M

$0.0368/M

Output /M

$0.525/M

Cache read /M

$0.00525/M

Cache hit

38.6%

TTFT

0.4s

Throughput

133 tps

DeepSeek V4.1 Flash (Thinking)

FP4

Unverified

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

Context

1.0M

Input /M

$0.0368/M

Output /M

$0.525/M

Cache read /M

$0.00525/M

Cache hit

94.5%

TTFT

0.4s

Throughput

133 tps

DeepSeek V4.1 Flash 1017

FP4

Unverified

deepseek/deepseek-v4.1-flash-1017:relace

Context

1.0M

Input /M

$0.0368/M

Output /M

$0.525/M

Cache read /M

$0.00525/M

Cache hit

19%

TTFT

0.7s

Throughput

103 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP4

Unverified

deepseek/deepseek-v4.1-flash-1017:thinking:relace

Context

1.0M

Input /M

$0.0368/M

Output /M

$0.525/M

Cache read /M

$0.00525/M

Cache hit

19%

TTFT

0.7s

Throughput

103 tps

GLM 5.2

FP4

Unverified

z-ai/glm-5.2:relace

Context

1.0M

Input /M

$0.00683/M

Output /M

$8.30/M

Cache read /M

$0.00683/M

Cache hit

41.2%

TTFT

1.7s

Throughput

25 tps

GLM 5.2 (Thinking)

FP4

Unverified

z-ai/glm-5.2:thinking:relace

Context

1.0M

Input /M

$0.00683/M

Output /M

$8.30/M

Cache read /M

$0.00683/M

Cache hit

37.3%

TTFT

1.7s

Throughput

25 tps

GLM 5.3

FP4

Unverified

z-ai/glm-5.3:relace

Context

1.0M

Input /M

$0.0738/M

Output /M

$4.60/M

Cache read /M

$0.0738/M

Cache hit

50.4%

TTFT

0.8s

Throughput

79 tps

GLM 5.3 (Thinking)

FP4

Unverified

z-ai/glm-5.3:thinking:relace

Context

1.0M

Input /M

$0.0738/M

Output /M

$4.60/M

Cache read /M

$0.0738/M

Cache hit

70.3%

TTFT

0.8s

Throughput

79 tps

GLM 5.3 Flash

FP4

Unverified

z-ai/glm-5.3-flash:relace

Context

1.0M

Input /M

$0.0282/M

Output /M

$0.105/M

Cache read /M

$0.0282/M

Cache hit

N/A

TTFT

0.7s

Throughput

70 tps

Kimi K3

FP4

Unverified

moonshotai/kimi-k3:relace

Context

1.0M

Input /M

$0.162/M

Output /M

$11.08/M

Cache read /M

$0.157/M

Cache hit

29.8%

TTFT

1.2s

Throughput

66 tps

MiniMax M3.1 Flash

FP4

Unverified

minimax/minimax-m3.1-flash:relace

Context

1M

Input /M

$0.0945/M

Output /M

$0.525/M

Cache read /M

$0.0105/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 Relace via the API

Call a model served by Relace 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-flash:relace",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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