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

20 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash deepseek/deepseek-v4-flash:wafer	1.0M	$0.15/M	$0.29/M	$0.03/M	0%	1s	36 tps
DeepSeek V4 Flash (Thinking) deepseek/deepseek-v4-flash:thinking:wafer	1.0M	$0.15/M	$0.29/M	$0.03/M	0%	1s	36 tps
DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash-0423:wafer	1.0M	$0.15/M	$0.29/M	$0.03/M	N/A	N/A	N/A
DeepSeek V4 Flash 0423 (Thinking) deepseek/deepseek-v4-flash-0423:thinking:wafer	1.0M	$0.15/M	$0.29/M	$0.03/M	N/A	N/A	N/A
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731:wafer	1.0M	$0.14/M	$0.24/M	$0.13/M	0%	1.2s	79 tps
DeepSeek V4 Flash 0731 (Thinking) deepseek/deepseek-v4-flash-0731:thinking:wafer	1.0M	$0.14/M	$0.24/M	$0.13/M	0%	1.2s	79 tps
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:wafer	1.0M	$0.23/M	$4.20/M	$0.23/M	24%	0.6s	116.5 tps
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:wafer	1.0M	$0.23/M	$4.20/M	$0.23/M	6.5%	0.6s	116.5 tps
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:wafer	1.0M	$0.05/M	$1.26/M	$0.05/M	6.2%	0.9s	63 tps
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:wafer	1.0M	$0.05/M	$1.26/M	$0.05/M	6.2%	0.9s	63 tps
GLM 5.2 z-ai/glm-5.2:wafer	1.0M	$0.20/M	$8.40/M	$0.19/M	18.2%	0.5s	114 tps
GLM 5.2 (Thinking) z-ai/glm-5.2:thinking:wafer	1.0M	$0.20/M	$8.40/M	$0.19/M	23.1%	0.5s	114 tps
GLM 5.3 z-ai/glm-5.3:wafer	1.0M	$0.18/M	$5.04/M	$0.17/M	0%	0.8s	80 tps
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:wafer	1.0M	$0.18/M	$5.04/M	$0.17/M	0%	0.8s	80 tps
GLM 5.3 Flash z-ai/glm-5.3-flash:wafer	1.0M	$0.07/M	$0.53/M	$0.03/M	N/A	0.9s	41 tps
Kimi K3 moonshotai/kimi-k3:wafer	1.0M	$0.53/M	$15.75/M	$0.47/M	0.4%	1s	44 tps
Nvidia Nemotron 3.5 Lightning nvidia/nemotron-3.5-lightning:wafer	262k	$0.05/M	$0.21/M	$0.03/M	N/A	N/A	N/A
Nvidia Nemotron 3.5 Lightning Thinking nvidia/nemotron-3.5-lightning:thinking:wafer	262k	$0.05/M	$0.21/M	$0.03/M	N/A	N/A	N/A
Qwen3.8 27B qwen3.8-27b:wafer	262k	$0.05/M	$2.42/M	$0.02/M	N/A	0.8s	71 tps
Qwen3.8 27B Thinking qwen3.8-27b:thinking:wafer	262k	$0.05/M	$2.42/M	$0.02/M	N/A	0.8s	71 tps

DeepSeek V4 Flash

deepseek/deepseek-v4-flash:wafer

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

1s

Throughput

36 tps

DeepSeek V4 Flash (Thinking)

deepseek/deepseek-v4-flash:thinking:wafer

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

1s

Throughput

36 tps

DeepSeek V4 Flash 0423

deepseek/deepseek-v4-flash-0423:wafer

Context

1.0M

Input /M

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/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

$0.15/M

Output /M

$0.29/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731:wafer

Context

1.0M

Input /M

$0.14/M

Output /M

$0.24/M

Cache read /M

$0.13/M

Cache hit

0%

TTFT

1.2s

Throughput

79 tps

DeepSeek V4 Flash 0731 (Thinking)

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

Context

1.0M

Input /M

$0.14/M

Output /M

$0.24/M

Cache read /M

$0.13/M

Cache hit

0%

TTFT

1.2s

Throughput

79 tps

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:wafer

Context

1.0M

Input /M

$0.23/M

Output /M

$4.20/M

Cache read /M

$0.23/M

Cache hit

24%

TTFT

0.6s

Throughput

116.5 tps

DeepSeek V4 Pro 0813 (Thinking)

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

Context

1.0M

Input /M

$0.23/M

Output /M

$4.20/M

Cache read /M

$0.23/M

Cache hit

6.5%

TTFT

0.6s

Throughput

116.5 tps

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash:wafer

Context

1.0M

Input /M

$0.05/M

Output /M

$1.26/M

Cache read /M

$0.05/M

Cache hit

6.2%

TTFT

0.9s

Throughput

63 tps

DeepSeek V4.1 Flash (Thinking)

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

Context

1.0M

Input /M

$0.05/M

Output /M

$1.26/M

Cache read /M

$0.05/M

Cache hit

6.2%

TTFT

0.9s

Throughput

63 tps

GLM 5.2

z-ai/glm-5.2:wafer

Context

1.0M

Input /M

$0.20/M

Output /M

$8.40/M

Cache read /M

$0.19/M

Cache hit

18.2%

TTFT

0.5s

Throughput

114 tps

GLM 5.2 (Thinking)

z-ai/glm-5.2:thinking:wafer

Context

1.0M

Input /M

$0.20/M

Output /M

$8.40/M

Cache read /M

$0.19/M

Cache hit

23.1%

TTFT

0.5s

Throughput

114 tps

GLM 5.3

z-ai/glm-5.3:wafer

Context

1.0M

Input /M

$0.18/M

Output /M

$5.04/M

Cache read /M

$0.17/M

Cache hit

0%

TTFT

0.8s

Throughput

80 tps

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:wafer

Context

1.0M

Input /M

$0.18/M

Output /M

$5.04/M

Cache read /M

$0.17/M

Cache hit

0%

TTFT

0.8s

Throughput

80 tps

GLM 5.3 Flash

z-ai/glm-5.3-flash:wafer

Context

1.0M

Input /M

$0.07/M

Output /M

$0.53/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

0.9s

Throughput

41 tps

Kimi K3

moonshotai/kimi-k3:wafer

Context

1.0M

Input /M

$0.53/M

Output /M

$15.75/M

Cache read /M

$0.47/M

Cache hit

0.4%

TTFT

1s

Throughput

44 tps

Nvidia Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning:wafer

Context

262k

Input /M

$0.05/M

Output /M

$0.21/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Nvidia Nemotron 3.5 Lightning Thinking

nvidia/nemotron-3.5-lightning:thinking:wafer

Context

262k

Input /M

$0.05/M

Output /M

$0.21/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen3.8 27B

qwen3.8-27b:wafer

Context

262k

Input /M

$0.05/M

Output /M

$2.42/M

Cache read /M

$0.02/M

Cache hit

N/A

TTFT

0.8s

Throughput

71 tps

Qwen3.8 27B Thinking

qwen3.8-27b:thinking:wafer

Context

262k

Input /M

$0.05/M

Output /M

$2.42/M

Cache read /M

$0.02/M

Cache hit

N/A

TTFT

0.8s

Throughput

71 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.