Baidu

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 Baidu

Model name

24 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V3.2 FP8 deepseek/deepseek-v3.2:baidu	131k	$0.294/M	$0.441/M	$0.0294/M	43%	1.1s	35 tps
DeepSeek V3.2 (Thinking) FP8 deepseek/deepseek-v3.2:thinking:baidu	131k	$0.294/M	$0.441/M	$0.0294/M	52.8%	1.1s	35 tps
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:baidu	1.0M	$0.0497/M	$0.0994/M	$0.00994/M	14%	1.1s	70 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:baidu	1.0M	$0.0497/M	$0.0994/M	$0.00994/M	32.3%	1.1s	70 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:baidu	1.0M	$0.0564/M	$0.169/M	$0.0018/M	0.1%	0.8s	127 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:baidu	1.0M	$0.0564/M	$0.169/M	$0.0018/M	0.1%	0.8s	127 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:baidu	1.0M	$1.77/M	$3.55/M	$0.147/M	7.3%	1s	56 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:baidu	1.0M	$1.77/M	$3.55/M	$0.147/M	9.8%	1s	56 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:baidu	1.0M	$0.692/M	$2.07/M	$0.022/M	74.8%	1.1s	49 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:baidu	1.0M	$0.692/M	$2.07/M	$0.022/M	33.6%	1.1s	49 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:baidu	1.0M	$0.0469/M	$0.188/M	$0.00094/M	21%	1.2s	94 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:baidu	1.0M	$0.0469/M	$0.188/M	$0.00094/M	40.9%	1.2s	94 tps
DeepSeek V4.1 Flash 1017 FP8 deepseek/deepseek-v4.1-flash-1017:baidu	1.0M	$0.157/M	$0.635/M	$0.0034/M	N/A	1.7s	85 tps
DeepSeek V4.1 Flash 1017 (Thinking) FP8 deepseek/deepseek-v4.1-flash-1017:thinking:baidu	1.0M	$0.157/M	$0.635/M	$0.0034/M	N/A	1.7s	85 tps
GLM 5 FP8 z-ai/glm-5:baidu	203k	$0.735/M	$2.35/M	$0.147/M	20.2%	1s	61 tps
GLM 5 (Thinking) FP8 z-ai/glm-5:thinking:baidu	203k	$0.735/M	$2.35/M	$0.147/M	53.6%	1s	61 tps
GLM 5.1 FP8 z-ai/glm-5.1:baidu	203k	$1.47/M	$4.62/M	$0.273/M	56.6%	0.9s	63.5 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:baidu	203k	$1.47/M	$4.62/M	$0.273/M	53.1%	0.9s	63.5 tps
GLM 5.2 FP8 z-ai/glm-5.2:baidu	1.0M	$0.65/M	$2.04/M	$0.121/M	87.3%	0.8s	76 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:baidu	1.0M	$0.65/M	$2.04/M	$0.121/M	87.4%	0.8s	76 tps
GLM 5.3 FP8 z-ai/glm-5.3:baidu	1.0M	$0.294/M	$0.924/M	$0.0546/M	36.1%	1.4s	75 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:baidu	1.0M	$0.294/M	$0.924/M	$0.0546/M	2.2%	1.4s	75 tps
Kimi K2.6 FP4 moonshotai/kimi-k2.6:baidu	262k	$0.409/M	$1.72/M	$0.0689/M	58.5%	1.6s	36 tps
Kimi K2.6 Thinking FP4 moonshotai/kimi-k2.6:thinking:baidu	262k	$0.409/M	$1.72/M	$0.0689/M	50.2%	1.6s	36 tps

DeepSeek V3.2

FP8

deepseek/deepseek-v3.2:baidu

Context

131k

Input /M

$0.294/M

Output /M

$0.441/M

Cache read /M

$0.0294/M

Cache hit

43%

TTFT

1.1s

Throughput

35 tps

DeepSeek V3.2 (Thinking)

FP8

deepseek/deepseek-v3.2:thinking:baidu

Context

131k

Input /M

$0.294/M

Output /M

$0.441/M

Cache read /M

$0.0294/M

Cache hit

52.8%

TTFT

1.1s

Throughput

35 tps

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:baidu

Context

1.0M

Input /M

$0.0497/M

Output /M

$0.0994/M

Cache read /M

$0.00994/M

Cache hit

14%

TTFT

1.1s

Throughput

70 tps

DeepSeek V4 Flash (Thinking)

FP8

deepseek/deepseek-v4-flash:thinking:baidu

Context

1.0M

Input /M

$0.0497/M

Output /M

$0.0994/M

Cache read /M

$0.00994/M

Cache hit

32.3%

TTFT

1.1s

Throughput

70 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:baidu

Context

1.0M

Input /M

$0.0564/M

Output /M

$0.169/M

Cache read /M

$0.0018/M

Cache hit

0.1%

TTFT

0.8s

Throughput

127 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.0564/M

Output /M

$0.169/M

Cache read /M

$0.0018/M

Cache hit

0.1%

TTFT

0.8s

Throughput

127 tps

DeepSeek V4 Pro

FP8

deepseek/deepseek-v4-pro:baidu

Context

1.0M

Input /M

$1.77/M

Output /M

$3.55/M

Cache read /M

$0.147/M

Cache hit

7.3%

TTFT

1s

Throughput

56 tps

DeepSeek V4 Pro (Thinking)

FP8

deepseek/deepseek-v4-pro:thinking:baidu

Context

1.0M

Input /M

$1.77/M

Output /M

$3.55/M

Cache read /M

$0.147/M

Cache hit

9.8%

TTFT

1s

Throughput

56 tps

DeepSeek V4 Pro 0813

FP8

deepseek/deepseek-v4-pro-0813:baidu

Context

1.0M

Input /M

$0.692/M

Output /M

$2.07/M

Cache read /M

$0.022/M

Cache hit

74.8%

TTFT

1.1s

Throughput

49 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.692/M

Output /M

$2.07/M

Cache read /M

$0.022/M

Cache hit

33.6%

TTFT

1.1s

Throughput

49 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:baidu

Context

1.0M

Input /M

$0.0469/M

Output /M

$0.188/M

Cache read /M

$0.00094/M

Cache hit

21%

TTFT

1.2s

Throughput

94 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.0469/M

Output /M

$0.188/M

Cache read /M

$0.00094/M

Cache hit

40.9%

TTFT

1.2s

Throughput

94 tps

DeepSeek V4.1 Flash 1017

FP8

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

Context

1.0M

Input /M

$0.157/M

Output /M

$0.635/M

Cache read /M

$0.0034/M

Cache hit

N/A

TTFT

1.7s

Throughput

85 tps

DeepSeek V4.1 Flash 1017 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.157/M

Output /M

$0.635/M

Cache read /M

$0.0034/M

Cache hit

N/A

TTFT

1.7s

Throughput

85 tps

GLM 5

FP8

z-ai/glm-5:baidu

Context

203k

Input /M

$0.735/M

Output /M

$2.35/M

Cache read /M

$0.147/M

Cache hit

20.2%

TTFT

1s

Throughput

61 tps

GLM 5 (Thinking)

FP8

z-ai/glm-5:thinking:baidu

Context

203k

Input /M

$0.735/M

Output /M

$2.35/M

Cache read /M

$0.147/M

Cache hit

53.6%

TTFT

1s

Throughput

61 tps

GLM 5.1

FP8

z-ai/glm-5.1:baidu

Context

203k

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.273/M

Cache hit

56.6%

TTFT

0.9s

Throughput

63.5 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:baidu

Context

203k

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.273/M

Cache hit

53.1%

TTFT

0.9s

Throughput

63.5 tps

GLM 5.2

FP8

z-ai/glm-5.2:baidu

Context

1.0M

Input /M

$0.65/M

Output /M

$2.04/M

Cache read /M

$0.121/M

Cache hit

87.3%

TTFT

0.8s

Throughput

76 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:baidu

Context

1.0M

Input /M

$0.65/M

Output /M

$2.04/M

Cache read /M

$0.121/M

Cache hit

87.4%

TTFT

0.8s

Throughput

76 tps

GLM 5.3

FP8

z-ai/glm-5.3:baidu

Context

1.0M

Input /M

$0.294/M

Output /M

$0.924/M

Cache read /M

$0.0546/M

Cache hit

36.1%

TTFT

1.4s

Throughput

75 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:baidu

Context

1.0M

Input /M

$0.294/M

Output /M

$0.924/M

Cache read /M

$0.0546/M

Cache hit

2.2%

TTFT

1.4s

Throughput

75 tps

Kimi K2.6

FP4

moonshotai/kimi-k2.6:baidu

Context

262k

Input /M

$0.409/M

Output /M

$1.72/M

Cache read /M

$0.0689/M

Cache hit

58.5%

TTFT

1.6s

Throughput

36 tps

Kimi K2.6 Thinking

FP4

moonshotai/kimi-k2.6:thinking:baidu

Context

262k

Input /M

$0.409/M

Output /M

$1.72/M

Cache read /M

$0.0689/M

Cache hit

50.2%

TTFT

1.6s

Throughput

36 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 Baidu via the API

Call a model served by Baidu 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-v3.2:baidu",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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