Wafer

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 Wafer

Model name

21 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash MXFP4 deepseek/deepseek-v4-flash:wafer	1.0M	$0.136/M	$0.242/M	$0.0294/M	0%	0.7s	94 tps
DeepSeek V4 Flash (Thinking) MXFP4 deepseek/deepseek-v4-flash:thinking:wafer	1.0M	$0.136/M	$0.242/M	$0.0294/M	0%	0.7s	94 tps
DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash-0423:wafer	1.0M	$0.147/M	$0.294/M	$0.0294/M	N/A	N/A	N/A
DeepSeek V4 Flash 0423 (Thinking) deepseek/deepseek-v4-flash-0423:thinking:wafer	1.0M	$0.147/M	$0.294/M	$0.0294/M	N/A	N/A	N/A
DeepSeek V4 Flash 0731 NVFP4 deepseek/deepseek-v4-flash-0731:wafer	1.0M	$0.105/M	$0.242/M	$0.0998/M	N/A	0.3s	161 tps
DeepSeek V4 Flash 0731 (Thinking) NVFP4 deepseek/deepseek-v4-flash-0731:thinking:wafer	1.0M	$0.105/M	$0.242/M	$0.0998/M	N/A	0.3s	161 tps
DeepSeek V4 Pro 0813 MXFP4 deepseek/deepseek-v4-pro-0813:wafer	1.0M	$0.294/M	$4.16/M	$0.0462/M	4.1%	0.7s	85.5 tps
DeepSeek V4 Pro 0813 (Thinking) MXFP4 deepseek/deepseek-v4-pro-0813:thinking:wafer	1.0M	$0.294/M	$4.16/M	$0.0462/M	4.1%	0.7s	85.5 tps
DeepSeek V4.1 Flash MXFP4 deepseek/deepseek-v4.1-flash:wafer	1.0M	$0.20/M	$0.682/M	$0.0063/M	8.5%	0.3s	179 tps
DeepSeek V4.1 Flash (Thinking) MXFP4 deepseek/deepseek-v4.1-flash:thinking:wafer	1.0M	$0.20/M	$0.682/M	$0.0063/M	34.2%	0.3s	179 tps
DeepSeek V4.1 Flash 1017 MXFP4 deepseek/deepseek-v4.1-flash-1017:wafer	1.0M	$0.136/M	$0.525/M	$0.0032/M	53%	0.4s	154 tps
DeepSeek V4.1 Flash 1017 (Thinking) MXFP4 deepseek/deepseek-v4.1-flash-1017:thinking:wafer	1.0M	$0.136/M	$0.525/M	$0.0032/M	61.5%	0.4s	154 tps
GLM 5.2 FP4 z-ai/glm-5.2:wafer	1.0M	$0.20/M	$8.40/M	$0.189/M	41.9%	1.2s	114.8 tps
GLM 5.2 (Thinking) FP4 z-ai/glm-5.2:thinking:wafer	1.0M	$0.20/M	$8.40/M	$0.189/M	57.9%	1.2s	114.8 tps
GLM 5.3 FP4 z-ai/glm-5.3:wafer	1.0M	$0.188/M	$1.47/M	$0.187/M	66.6%	0.4s	119 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:wafer	1.0M	$0.188/M	$1.47/M	$0.187/M	15.6%	0.4s	119 tps
GLM 5.3 Flash NVFP4 z-ai/glm-5.3-flash:wafer	1.0M	$0.0525/M	$0.21/M	$0.0315/M	0%	0.4s	108 tps
Kimi K3 MXFP4 moonshotai/kimi-k3:wafer	1.0M	$0.347/M	$12.49/M	$0.345/M	39.6%	0.5s	108 tps
MiniMax M3.1 Flash minimax/minimax-m3.1-flash:wafer	1.0M	$0.157/M	$0.63/M	$0.0158/M	N/A	N/A	N/A
Qwen3.8 27B FP8 qwen3.8-27b:wafer	262k	$0.063/M	$2.42/M	$0.0525/M	N/A	0.7s	98 tps
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:wafer	262k	$0.063/M	$2.42/M	$0.0525/M	N/A	0.7s	98 tps

DeepSeek V4 Flash

MXFP4

deepseek/deepseek-v4-flash:wafer

Context

1.0M

Input /M

$0.136/M

Output /M

$0.242/M

Cache read /M

$0.0294/M

Cache hit

0%

TTFT

0.7s

Throughput

94 tps

DeepSeek V4 Flash (Thinking)

MXFP4

deepseek/deepseek-v4-flash:thinking:wafer

Context

1.0M

Input /M

$0.136/M

Output /M

$0.242/M

Cache read /M

$0.0294/M

Cache hit

0%

TTFT

0.7s

Throughput

94 tps

DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash-0423:wafer

Context

1.0M

Input /M

$0.147/M

Output /M

$0.294/M

Cache read /M

$0.0294/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0423 (Thinking)

deepseek/deepseek-v4-flash-0423:thinking:wafer

Context

1.0M

Input /M

$0.147/M

Output /M

$0.294/M

Cache read /M

$0.0294/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731

NVFP4

deepseek/deepseek-v4-flash-0731:wafer

Context

1.0M

Input /M

$0.105/M

Output /M

$0.242/M

Cache read /M

$0.0998/M

Cache hit

N/A

TTFT

0.3s

Throughput

161 tps

DeepSeek V4 Flash 0731 (Thinking)

NVFP4

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

Context

1.0M

Input /M

$0.105/M

Output /M

$0.242/M

Cache read /M

$0.0998/M

Cache hit

N/A

TTFT

0.3s

Throughput

161 tps

DeepSeek V4 Pro 0813

MXFP4

deepseek/deepseek-v4-pro-0813:wafer

Context

1.0M

Input /M

$0.294/M

Output /M

$4.16/M

Cache read /M

$0.0462/M

Cache hit

4.1%

TTFT

0.7s

Throughput

85.5 tps

DeepSeek V4 Pro 0813 (Thinking)

MXFP4

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

Context

1.0M

Input /M

$0.294/M

Output /M

$4.16/M

Cache read /M

$0.0462/M

Cache hit

4.1%

TTFT

0.7s

Throughput

85.5 tps

DeepSeek V4.1 Flash

MXFP4

deepseek/deepseek-v4.1-flash:wafer

Context

1.0M

Input /M

$0.20/M

Output /M

$0.682/M

Cache read /M

$0.0063/M

Cache hit

8.5%

TTFT

0.3s

Throughput

179 tps

DeepSeek V4.1 Flash (Thinking)

MXFP4

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

Context

1.0M

Input /M

$0.20/M

Output /M

$0.682/M

Cache read /M

$0.0063/M

Cache hit

34.2%

TTFT

0.3s

Throughput

179 tps

DeepSeek V4.1 Flash 1017

MXFP4

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

Context

1.0M

Input /M

$0.136/M

Output /M

$0.525/M

Cache read /M

$0.0032/M

Cache hit

53%

TTFT

0.4s

Throughput

154 tps

DeepSeek V4.1 Flash 1017 (Thinking)

MXFP4

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

Context

1.0M

Input /M

$0.136/M

Output /M

$0.525/M

Cache read /M

$0.0032/M

Cache hit

61.5%

TTFT

0.4s

Throughput

154 tps

GLM 5.2

FP4

z-ai/glm-5.2:wafer

Context

1.0M

Input /M

$0.20/M

Output /M

$8.40/M

Cache read /M

$0.189/M

Cache hit

41.9%

TTFT

1.2s

Throughput

114.8 tps

GLM 5.2 (Thinking)

FP4

z-ai/glm-5.2:thinking:wafer

Context

1.0M

Input /M

$0.20/M

Output /M

$8.40/M

Cache read /M

$0.189/M

Cache hit

57.9%

TTFT

1.2s

Throughput

114.8 tps

GLM 5.3

FP4

z-ai/glm-5.3:wafer

Context

1.0M

Input /M

$0.188/M

Output /M

$1.47/M

Cache read /M

$0.187/M

Cache hit

66.6%

TTFT

0.4s

Throughput

119 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:wafer

Context

1.0M

Input /M

$0.188/M

Output /M

$1.47/M

Cache read /M

$0.187/M

Cache hit

15.6%

TTFT

0.4s

Throughput

119 tps

GLM 5.3 Flash

NVFP4

z-ai/glm-5.3-flash:wafer

Context

1.0M

Input /M

$0.0525/M

Output /M

$0.21/M

Cache read /M

$0.0315/M

Cache hit

0%

TTFT

0.4s

Throughput

108 tps

Kimi K3

MXFP4

moonshotai/kimi-k3:wafer

Context

1.0M

Input /M

$0.347/M

Output /M

$12.49/M

Cache read /M

$0.345/M

Cache hit

39.6%

TTFT

0.5s

Throughput

108 tps

MiniMax M3.1 Flash

minimax/minimax-m3.1-flash:wafer

Context

1.0M

Input /M

$0.157/M

Output /M

$0.63/M

Cache read /M

$0.0158/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

FP8

qwen3.8-27b:wafer

Context

262k

Input /M

$0.063/M

Output /M

$2.42/M

Cache read /M

$0.0525/M

Cache hit

N/A

TTFT

0.7s

Throughput

98 tps

Qwen3.8 27B Thinking

FP8

qwen3.8-27b:thinking:wafer

Context

262k

Input /M

$0.063/M

Output /M

$2.42/M

Cache read /M

$0.0525/M

Cache hit

N/A

TTFT

0.7s

Throughput

98 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 Wafer via the API

Call a model served by Wafer 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:wafer",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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