SiliconFlow

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 SiliconFlow

Model name

56 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek R1-0528 FP8 deepseek-ai/DeepSeek-R1-0528:siliconflow	164k	$0.53/M	$2.29/M	N/A	46.4%	1.9s	23 tps
DeepSeek V3 0324 FP8 deepseek-v3-0324:siliconflow	164k	$0.26/M	$1.05/M	N/A	66.4%	1.8s	23 tps
DeepSeek V3.1 FP8 deepseek-ai/DeepSeek-V3.1:siliconflow	164k	$0.28/M	$1.05/M	N/A	10.7%	2s	19 tps
DeepSeek V3.1 Terminus FP8 deepseek-ai/DeepSeek-V3.1-Terminus:siliconflow	164k	$0.28/M	$1.05/M	N/A	70.5%	2s	19 tps
DeepSeek V3.1 Terminus (Thinking) FP8 deepseek-ai/DeepSeek-V3.1-Terminus:thinking:siliconflow	164k	$0.28/M	$1.05/M	N/A	92.4%	2s	19 tps
DeepSeek V3.2 FP8 deepseek/deepseek-v3.2:siliconflow	164k	$0.27/M	$0.44/M	$0.14/M	83.2%	2.1s	17 tps
DeepSeek V3.2 (Thinking) FP8 deepseek/deepseek-v3.2:thinking:siliconflow	164k	$0.27/M	$0.44/M	$0.14/M	44.8%	2.1s	17 tps
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:siliconflow	1.0M	$0.15/M	$0.29/M	$0.03/M	0%	1s	46 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:siliconflow	1.0M	$0.15/M	$0.29/M	$0.03/M	0%	1s	46 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:siliconflow	1.0M	$0.23/M	$0.69/M	$0.03/M	N/A	1.6s	40 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:siliconflow	1.0M	$0.23/M	$0.69/M	$0.03/M	N/A	1.6s	40 tps
DeepSeek V4 Flash Vision Exp FP8 deepseek/deepseek-v4-flash-vision-exp:siliconflow	1.0M	$0.46/M	$1.39/M	$0.03/M	0%	1s	104 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:siliconflow	1.0M	$1.83/M	$3.65/M	$0.15/M	N/A	1.5s	43.5 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:siliconflow	1.0M	$1.83/M	$3.65/M	$0.15/M	N/A	1.5s	43.5 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:siliconflow	1.0M	$1.39/M	$4.16/M	$0.05/M	N/A	1.5s	56 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:siliconflow	1.0M	$1.39/M	$4.16/M	$0.05/M	N/A	1.5s	56 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:siliconflow	1.0M	$0.31/M	$1.26/M	$0.0063/M	N/A	2.8s	73 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:siliconflow	1.0M	$0.31/M	$1.26/M	$0.0063/M	N/A	2.8s	73 tps
Gemma 4 26B A4B FP8 google/gemma-4-26b-a4b-it:siliconflow	262k	$0.15/M	$0.42/M	$0.05/M	N/A	1.3s	41 tps
Gemma 4 26B A4B (Thinking) FP8 google/gemma-4-26b-a4b-it:thinking:siliconflow	262k	$0.15/M	$0.42/M	$0.05/M	N/A	1.3s	41 tps
Gemma 4 31B FP8 google/gemma-4-31b-it:siliconflow	262k	$0.79/M	$1.05/M	$0.26/M	0%	4.2s	5 tps
Gemma 4 31B (Thinking) FP8 google/gemma-4-31b-it:thinking:siliconflow	262k	$0.79/M	$1.05/M	$0.26/M	0%	4.2s	5 tps
GLM 4.5 Air FP8 z-ai/GLM-4.5-Air:siliconflow	131k	$0.15/M	$0.90/M	N/A	N/A	1.1s	65 tps
GLM 4.5 Air (Thinking) FP8 z-ai/GLM-4.5-Air:thinking:siliconflow	131k	$0.15/M	$0.90/M	N/A	N/A	1.1s	65 tps
GLM 5 FP8 z-ai/glm-5:siliconflow	205k	$1.00/M	$2.68/M	$0.21/M	71.1%	2.7s	36 tps
GLM 5 (Thinking) FP8 z-ai/glm-5:thinking:siliconflow	205k	$1.00/M	$2.68/M	$0.21/M	2.7%	2.7s	36 tps
GLM 5.1 FP8 z-ai/glm-5.1:siliconflow	205k	$1.25/M	$3.93/M	$0.63/M	61.4%	1.8s	28 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:siliconflow	205k	$1.25/M	$3.93/M	$0.63/M	9.7%	1.8s	28 tps
GLM 5.2 FP8 z-ai/glm-5.2:siliconflow	1.0M	$1.25/M	$3.93/M	$0.23/M	44.2%	1s	93 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:siliconflow	1.0M	$1.25/M	$3.93/M	$0.23/M	44.2%	1s	93 tps
GLM 5.3 FP8 z-ai/glm-5.3:siliconflow	1.0M	$1.18/M	$3.70/M	$0.22/M	87.8%	1.9s	63 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:siliconflow	1.0M	$1.18/M	$3.70/M	$0.22/M	79.9%	1.9s	63 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:siliconflow	1.0M	$0.16/M	$0.53/M	$0.03/M	0%	2s	32 tps
GPT OSS 120B FP8 openai/gpt-oss-120b:siliconflow	131k	$0.16/M	$0.63/M	$0.08/M	N/A	1.1s	24 tps
GPT OSS 20B FP8 openai/gpt-oss-20b:siliconflow	131k	$0.04/M	$0.19/M	N/A	N/A	1.3s	27 tps
Kimi K2.5 INT4 moonshotai/kimi-k2.5:siliconflow	262k	$0.47/M	$2.36/M	$0.07/M	N/A	1.7s	24 tps
Kimi K2.5 Thinking INT4 moonshotai/kimi-k2.5:thinking:siliconflow	262k	$0.47/M	$2.36/M	$0.07/M	94.5%	1.7s	24 tps
Kimi K2.7 Code FP8 moonshotai/kimi-k2.7-code:siliconflow	262k	$0.90/M	$3.99/M	$0.19/M	N/A	2.1s	35 tps
MiniMax M3 FP8 minimax/minimax-m3:siliconflow	512k	$0.63/M	$2.52/M	$0.13/M	N/A	N/A	N/A
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:siliconflow	512k	$0.63/M	$2.52/M	$0.13/M	N/A	N/A	N/A
Qwen 3.6 27B FP8 alibaba/qwen3.6-27b:siliconflow	262k	$0.31/M	$3.36/M	N/A	N/A	1.1s	17 tps
Qwen 3.6 27B Thinking FP8 alibaba/qwen3.6-27b:thinking:siliconflow	262k	$0.31/M	$3.36/M	N/A	N/A	1.1s	17 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:siliconflow	262k	$0.25/M	$1.89/M	$0.16/M	N/A	2.9s	58 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:siliconflow	262k	$0.25/M	$1.89/M	$0.16/M	N/A	2.9s	58 tps
Qwen3 32B FP8 qwen/qwen3-32b:siliconflow	131k	$0.15/M	$0.60/M	N/A	N/A	1.1s	28 tps
Qwen3.5 122B A10B FP8 qwen3.5-122b-a10b:siliconflow	262k	$0.27/M	$2.18/M	N/A	N/A	1s	55 tps
Qwen3.5 122B A10B Thinking FP8 qwen3.5-122b-a10b:thinking:siliconflow	262k	$0.27/M	$2.18/M	N/A	N/A	1s	55 tps
Qwen3.5 27B FP8 qwen3.5-27b:siliconflow	262k	$0.26/M	$2.10/M	N/A	N/A	1.4s	22 tps
Qwen3.5 27B Thinking FP8 qwen3.5-27b:thinking:siliconflow	262k	$0.26/M	$2.10/M	N/A	N/A	1.4s	22 tps
Qwen3.5 35B A3B FP8 qwen3.5-35b-a3b:siliconflow	262k	$0.25/M	$1.89/M	$0.16/M	N/A	1.8s	60.5 tps
Qwen3.5 35B A3B Thinking FP8 qwen3.5-35b-a3b:thinking:siliconflow	262k	$0.25/M	$1.89/M	$0.16/M	N/A	1.8s	60.5 tps
Qwen3.5 9B FP8 qwen/qwen3.5-9b:siliconflow	262k	$0.10/M	$0.16/M	N/A	N/A	1.2s	34 tps
Qwen3.8 Max FP8 qwen3.8-max:siliconflow	1.0M	$2.10/M	$6.30/M	$0.26/M	N/A	3.7s	32 tps
Qwen3.8 Max Thinking FP8 qwen3.8-max:thinking:siliconflow	1.0M	$2.10/M	$6.30/M	$0.26/M	N/A	3.7s	32 tps
Tencent Hy3 tencent/hy3	262k	$0.07/M	$0.26/M	$0.03/M	N/A	N/A	N/A
Tencent Hy4 Preview FP8 tencent/hy4-preview:siliconflow	1.0M	$0.88/M	$2.63/M	$0.04/M	99.2%	1.6s	52 tps

DeepSeek R1-0528

FP8

deepseek-ai/DeepSeek-R1-0528:siliconflow

Context

164k

Input /M

$0.53/M

Output /M

$2.29/M

Cache read /M

N/A

Cache hit

46.4%

TTFT

1.9s

Throughput

23 tps

DeepSeek V3 0324

FP8

deepseek-v3-0324:siliconflow

Context

164k

Input /M

$0.26/M

Output /M

$1.05/M

Cache read /M

N/A

Cache hit

66.4%

TTFT

1.8s

Throughput

23 tps

DeepSeek V3.1

FP8

deepseek-ai/DeepSeek-V3.1:siliconflow

Context

164k

Input /M

$0.28/M

Output /M

$1.05/M

Cache read /M

N/A

Cache hit

10.7%

TTFT

2s

Throughput

19 tps

DeepSeek V3.1 Terminus

FP8

deepseek-ai/DeepSeek-V3.1-Terminus:siliconflow

Context

164k

Input /M

$0.28/M

Output /M

$1.05/M

Cache read /M

N/A

Cache hit

70.5%

TTFT

2s

Throughput

19 tps

DeepSeek V3.1 Terminus (Thinking)

FP8

deepseek-ai/DeepSeek-V3.1-Terminus:thinking:siliconflow

Context

164k

Input /M

$0.28/M

Output /M

$1.05/M

Cache read /M

N/A

Cache hit

92.4%

TTFT

2s

Throughput

19 tps

DeepSeek V3.2

FP8

deepseek/deepseek-v3.2:siliconflow

Context

164k

Input /M

$0.27/M

Output /M

$0.44/M

Cache read /M

$0.14/M

Cache hit

83.2%

TTFT

2.1s

Throughput

17 tps

DeepSeek V3.2 (Thinking)

FP8

deepseek/deepseek-v3.2:thinking:siliconflow

Context

164k

Input /M

$0.27/M

Output /M

$0.44/M

Cache read /M

$0.14/M

Cache hit

44.8%

TTFT

2.1s

Throughput

17 tps

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:siliconflow

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

46 tps

DeepSeek V4 Flash (Thinking)

FP8

deepseek/deepseek-v4-flash:thinking:siliconflow

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

46 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:siliconflow

Context

1.0M

Input /M

$0.23/M

Output /M

$0.69/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

1.6s

Throughput

40 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.23/M

Output /M

$0.69/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

1.6s

Throughput

40 tps

DeepSeek V4 Flash Vision Exp

FP8

deepseek/deepseek-v4-flash-vision-exp:siliconflow

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

1s

Throughput

104 tps

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:siliconflow

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

1.5s

Throughput

43.5 tps

DeepSeek V4 Pro (Thinking)

FP8

deepseek/deepseek-v4-pro:thinking:siliconflow

Context

1.0M

Input /M

$1.83/M

Output /M

$3.65/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

1.5s

Throughput

43.5 tps

DeepSeek V4 Pro 0813

FP8

deepseek/deepseek-v4-pro-0813:siliconflow

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.05/M

Cache hit

N/A

TTFT

1.5s

Throughput

56 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

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

Context

1.0M

Input /M

$1.39/M

Output /M

$4.16/M

Cache read /M

$0.05/M

Cache hit

N/A

TTFT

1.5s

Throughput

56 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:siliconflow

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0063/M

Cache hit

N/A

TTFT

2.8s

Throughput

73 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0063/M

Cache hit

N/A

TTFT

2.8s

Throughput

73 tps

Gemma 4 26B A4B

FP8

google/gemma-4-26b-a4b-it:siliconflow

Context

262k

Input /M

$0.15/M

Output /M

$0.42/M

Cache read /M

$0.05/M

Cache hit

N/A

TTFT

1.3s

Throughput

41 tps

Gemma 4 26B A4B (Thinking)

FP8

google/gemma-4-26b-a4b-it:thinking:siliconflow

Context

262k

Input /M

$0.15/M

Output /M

$0.42/M

Cache read /M

$0.05/M

Cache hit

N/A

TTFT

1.3s

Throughput

41 tps

Gemma 4 31B

FP8

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

Context

262k

Input /M

$0.79/M

Output /M

$1.05/M

Cache read /M

$0.26/M

Cache hit

0%

TTFT

4.2s

Throughput

5 tps

Gemma 4 31B (Thinking)

FP8

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

Context

262k

Input /M

$0.79/M

Output /M

$1.05/M

Cache read /M

$0.26/M

Cache hit

0%

TTFT

4.2s

Throughput

5 tps

GLM 4.5 Air

FP8

z-ai/GLM-4.5-Air:siliconflow

Context

131k

Input /M

$0.15/M

Output /M

$0.90/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.1s

Throughput

65 tps

GLM 4.5 Air (Thinking)

FP8

z-ai/GLM-4.5-Air:thinking:siliconflow

Context

131k

Input /M

$0.15/M

Output /M

$0.90/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.1s

Throughput

65 tps

GLM 5

FP8

z-ai/glm-5:siliconflow

Context

205k

Input /M

$1.00/M

Output /M

$2.68/M

Cache read /M

$0.21/M

Cache hit

71.1%

TTFT

2.7s

Throughput

36 tps

GLM 5 (Thinking)

FP8

z-ai/glm-5:thinking:siliconflow

Context

205k

Input /M

$1.00/M

Output /M

$2.68/M

Cache read /M

$0.21/M

Cache hit

2.7%

TTFT

2.7s

Throughput

36 tps

GLM 5.1

FP8

z-ai/glm-5.1:siliconflow

Context

205k

Input /M

$1.25/M

Output /M

$3.93/M

Cache read /M

$0.63/M

Cache hit

61.4%

TTFT

1.8s

Throughput

28 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:siliconflow

Context

205k

Input /M

$1.25/M

Output /M

$3.93/M

Cache read /M

$0.63/M

Cache hit

9.7%

TTFT

1.8s

Throughput

28 tps

GLM 5.2

FP8

z-ai/glm-5.2:siliconflow

Context

1.0M

Input /M

$1.25/M

Output /M

$3.93/M

Cache read /M

$0.23/M

Cache hit

44.2%

TTFT

1s

Throughput

93 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:siliconflow

Context

1.0M

Input /M

$1.25/M

Output /M

$3.93/M

Cache read /M

$0.23/M

Cache hit

44.2%

TTFT

1s

Throughput

93 tps

GLM 5.3

FP8

z-ai/glm-5.3:siliconflow

Context

1.0M

Input /M

$1.18/M

Output /M

$3.70/M

Cache read /M

$0.22/M

Cache hit

87.8%

TTFT

1.9s

Throughput

63 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:siliconflow

Context

1.0M

Input /M

$1.18/M

Output /M

$3.70/M

Cache read /M

$0.22/M

Cache hit

79.9%

TTFT

1.9s

Throughput

63 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:siliconflow

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

2s

Throughput

32 tps

GPT OSS 120B

FP8

openai/gpt-oss-120b:siliconflow

Context

131k

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.08/M

Cache hit

N/A

TTFT

1.1s

Throughput

24 tps

GPT OSS 20B

FP8

openai/gpt-oss-20b:siliconflow

Context

131k

Input /M

$0.04/M

Output /M

$0.19/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.3s

Throughput

27 tps

Kimi K2.5

INT4

moonshotai/kimi-k2.5:siliconflow

Context

262k

Input /M

$0.47/M

Output /M

$2.36/M

Cache read /M

$0.07/M

Cache hit

N/A

TTFT

1.7s

Throughput

24 tps

Kimi K2.5 Thinking

INT4

moonshotai/kimi-k2.5:thinking:siliconflow

Context

262k

Input /M

$0.47/M

Output /M

$2.36/M

Cache read /M

$0.07/M

Cache hit

94.5%

TTFT

1.7s

Throughput

24 tps

Kimi K2.7 Code

FP8

moonshotai/kimi-k2.7-code:siliconflow

Context

262k

Input /M

$0.90/M

Output /M

$3.99/M

Cache read /M

$0.19/M

Cache hit

N/A

TTFT

2.1s

Throughput

35 tps

MiniMax M3

FP8

minimax/minimax-m3:siliconflow

Context

512k

Input /M

$0.63/M

Output /M

$2.52/M

Cache read /M

$0.13/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:siliconflow

Context

512k

Input /M

$0.63/M

Output /M

$2.52/M

Cache read /M

$0.13/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Qwen 3.6 27B

FP8

alibaba/qwen3.6-27b:siliconflow

Context

262k

Input /M

$0.31/M

Output /M

$3.36/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.1s

Throughput

17 tps

Qwen 3.6 27B Thinking

FP8

alibaba/qwen3.6-27b:thinking:siliconflow

Context

262k

Input /M

$0.31/M

Output /M

$3.36/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.1s

Throughput

17 tps

Qwen 3.6 35B A3B

FP8

Qwen/Qwen3.6-35B-A3B:siliconflow

Context

262k

Input /M

$0.25/M

Output /M

$1.89/M

Cache read /M

$0.16/M

Cache hit

N/A

TTFT

2.9s

Throughput

58 tps

Qwen 3.6 35B A3B Thinking

FP8

Qwen/Qwen3.6-35B-A3B:thinking:siliconflow

Context

262k

Input /M

$0.25/M

Output /M

$1.89/M

Cache read /M

$0.16/M

Cache hit

N/A

TTFT

2.9s

Throughput

58 tps

Qwen3 32B

FP8

qwen/qwen3-32b:siliconflow

Context

131k

Input /M

$0.15/M

Output /M

$0.60/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.1s

Throughput

28 tps

Qwen3.5 122B A10B

FP8

qwen3.5-122b-a10b:siliconflow

Context

262k

Input /M

$0.27/M

Output /M

$2.18/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1s

Throughput

55 tps

Qwen3.5 122B A10B Thinking

FP8

qwen3.5-122b-a10b:thinking:siliconflow

Context

262k

Input /M

$0.27/M

Output /M

$2.18/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1s

Throughput

55 tps

Qwen3.5 27B

FP8

qwen3.5-27b:siliconflow

Context

262k

Input /M

$0.26/M

Output /M

$2.10/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.4s

Throughput

22 tps

Qwen3.5 27B Thinking

FP8

qwen3.5-27b:thinking:siliconflow

Context

262k

Input /M

$0.26/M

Output /M

$2.10/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.4s

Throughput

22 tps

Qwen3.5 35B A3B

FP8

qwen3.5-35b-a3b:siliconflow

Context

262k

Input /M

$0.25/M

Output /M

$1.89/M

Cache read /M

$0.16/M

Cache hit

N/A

TTFT

1.8s

Throughput

60.5 tps

Qwen3.5 35B A3B Thinking

FP8

qwen3.5-35b-a3b:thinking:siliconflow

Context

262k

Input /M

$0.25/M

Output /M

$1.89/M

Cache read /M

$0.16/M

Cache hit

N/A

TTFT

1.8s

Throughput

60.5 tps

Qwen3.5 9B

FP8

qwen/qwen3.5-9b:siliconflow

Context

262k

Input /M

$0.10/M

Output /M

$0.16/M

Cache read /M

N/A

Cache hit

N/A

TTFT

1.2s

Throughput

34 tps

Qwen3.8 Max

FP8

qwen3.8-max:siliconflow

Context

1.0M

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.26/M

Cache hit

N/A

TTFT

3.7s

Throughput

32 tps

Qwen3.8 Max Thinking

FP8

qwen3.8-max:thinking:siliconflow

Context

1.0M

Input /M

$2.10/M

Output /M

$6.30/M

Cache read /M

$0.26/M

Cache hit

N/A

TTFT

3.7s

Throughput

32 tps

Tencent Hy3

tencent/hy3

Context

262k

Input /M

$0.07/M

Output /M

$0.26/M

Cache read /M

$0.03/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Tencent Hy4 Preview

FP8

tencent/hy4-preview:siliconflow

Context

1.0M

Input /M

$0.88/M

Output /M

$2.63/M

Cache read /M

$0.04/M

Cache hit

99.2%

TTFT

1.6s

Throughput

52 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 SiliconFlow via the API

Call a model served by SiliconFlow 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-ai/DeepSeek-R1-0528:siliconflow",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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