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

22 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V3.2 FP8 deepseek/deepseek-v3.2:baidu	131k	$0.29/M	$0.44/M	$0.03/M	1.1s	35 tps
DeepSeek V3.2 (Thinking) FP8 deepseek/deepseek-v3.2:thinking:baidu	131k	$0.29/M	$0.44/M	$0.03/M	1.1s	35 tps
DeepSeek V4 Flash FP8 deepseek/deepseek-v4-flash:baidu	1.0M	$0.04/M	$0.08/M	$0.0081/M	0.8s	75 tps
DeepSeek V4 Flash (Thinking) FP8 deepseek/deepseek-v4-flash:thinking:baidu	1.0M	$0.04/M	$0.08/M	$0.0081/M	0.8s	75 tps
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:baidu	1.0M	$0.46/M	$1.39/M	$0.01/M	0.6s	139 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:baidu	1.0M	$0.46/M	$1.39/M	$0.01/M	0.6s	139 tps
DeepSeek V4 Pro FP8 deepseek/deepseek-v4-pro:baidu	1.0M	$1.77/M	$3.55/M	$0.15/M	0.8s	59 tps
DeepSeek V4 Pro (Thinking) FP8 deepseek/deepseek-v4-pro:thinking:baidu	1.0M	$1.77/M	$3.55/M	$0.15/M	0.8s	59 tps
DeepSeek V4 Pro 0813 FP8 deepseek/deepseek-v4-pro-0813:baidu	1.0M	$0.15/M	$0.46/M	$0.0049/M	1s	42 tps
DeepSeek V4 Pro 0813 (Thinking) FP8 deepseek/deepseek-v4-pro-0813:thinking:baidu	1.0M	$0.15/M	$0.46/M	$0.0049/M	1s	42 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:baidu	1.0M	$0.16/M	$0.63/M	$0.0031/M	1.2s	76 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:baidu	1.0M	$0.16/M	$0.63/M	$0.0031/M	1.2s	76 tps
GLM 5 FP8 z-ai/glm-5:baidu	203k	$0.73/M	$2.35/M	$0.15/M	1s	63 tps
GLM 5 (Thinking) FP8 z-ai/glm-5:thinking:baidu	203k	$0.73/M	$2.35/M	$0.15/M	1s	63 tps
GLM 5.1 FP8 z-ai/glm-5.1:baidu	203k	$1.01/M	$3.18/M	$0.19/M	1s	60 tps
GLM 5.1 (Thinking) FP8 z-ai/glm-5.1:thinking:baidu	203k	$1.01/M	$3.18/M	$0.19/M	1s	60 tps
GLM 5.2 FP8 z-ai/glm-5.2:baidu	1.0M	$0.65/M	$2.04/M	$0.12/M	0.8s	75 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:baidu	1.0M	$0.65/M	$2.04/M	$0.12/M	0.8s	75 tps
GLM 5.3 FP8 z-ai/glm-5.3:baidu	1.0M	$0.73/M	$2.31/M	$0.14/M	0.8s	92.5 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:baidu	1.0M	$0.73/M	$2.31/M	$0.14/M	0.8s	92.5 tps
Kimi K2.6 FP4 moonshotai/kimi-k2.6:baidu	262k	$0.45/M	$1.91/M	$0.08/M	1s	64 tps
Kimi K2.6 Thinking FP4 moonshotai/kimi-k2.6:thinking:baidu	262k	$0.45/M	$1.91/M	$0.08/M	1s	64 tps

DeepSeek V3.2

FP8

deepseek/deepseek-v3.2:baidu

Context

131k

Input /M

$0.29/M

Output /M

$0.44/M

Cache read /M

$0.03/M

TTFT

1.1s

Throughput

35 tps

DeepSeek V3.2 (Thinking)

FP8

deepseek/deepseek-v3.2:thinking:baidu

Context

131k

Input /M

$0.29/M

Output /M

$0.44/M

Cache read /M

$0.03/M

TTFT

1.1s

Throughput

35 tps

DeepSeek V4 Flash

FP8

deepseek/deepseek-v4-flash:baidu

Context

1.0M

Input /M

$0.04/M

Output /M

$0.08/M

Cache read /M

$0.0081/M

TTFT

0.8s

Throughput

75 tps

DeepSeek V4 Flash (Thinking)

FP8

deepseek/deepseek-v4-flash:thinking:baidu

Context

1.0M

Input /M

$0.04/M

Output /M

$0.08/M

Cache read /M

$0.0081/M

TTFT

0.8s

Throughput

75 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:baidu

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.01/M

TTFT

0.6s

Throughput

139 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.46/M

Output /M

$1.39/M

Cache read /M

$0.01/M

TTFT

0.6s

Throughput

139 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

$0.15/M

TTFT

0.8s

Throughput

59 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

$0.15/M

TTFT

0.8s

Throughput

59 tps

DeepSeek V4 Pro 0813

FP8

deepseek/deepseek-v4-pro-0813:baidu

Context

1.0M

Input /M

$0.15/M

Output /M

$0.46/M

Cache read /M

$0.0049/M

TTFT

1s

Throughput

42 tps

DeepSeek V4 Pro 0813 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.15/M

Output /M

$0.46/M

Cache read /M

$0.0049/M

TTFT

1s

Throughput

42 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:baidu

Context

1.0M

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.0031/M

TTFT

1.2s

Throughput

76 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.16/M

Output /M

$0.63/M

Cache read /M

$0.0031/M

TTFT

1.2s

Throughput

76 tps

GLM 5

FP8

z-ai/glm-5:baidu

Context

203k

Input /M

$0.73/M

Output /M

$2.35/M

Cache read /M

$0.15/M

TTFT

1s

Throughput

63 tps

GLM 5 (Thinking)

FP8

z-ai/glm-5:thinking:baidu

Context

203k

Input /M

$0.73/M

Output /M

$2.35/M

Cache read /M

$0.15/M

TTFT

1s

Throughput

63 tps

GLM 5.1

FP8

z-ai/glm-5.1:baidu

Context

203k

Input /M

$1.01/M

Output /M

$3.18/M

Cache read /M

$0.19/M

TTFT

1s

Throughput

60 tps

GLM 5.1 (Thinking)

FP8

z-ai/glm-5.1:thinking:baidu

Context

203k

Input /M

$1.01/M

Output /M

$3.18/M

Cache read /M

$0.19/M

TTFT

1s

Throughput

60 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

$0.12/M

TTFT

0.8s

Throughput

75 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

$0.12/M

TTFT

0.8s

Throughput

75 tps

GLM 5.3

FP8

z-ai/glm-5.3:baidu

Context

1.0M

Input /M

$0.73/M

Output /M

$2.31/M

Cache read /M

$0.14/M

TTFT

0.8s

Throughput

92.5 tps

GLM 5.3 (Thinking)

FP8

z-ai/glm-5.3:thinking:baidu

Context

1.0M

Input /M

$0.73/M

Output /M

$2.31/M

Cache read /M

$0.14/M

TTFT

0.8s

Throughput

92.5 tps

Kimi K2.6

FP4

moonshotai/kimi-k2.6:baidu

Context

262k

Input /M

$0.45/M

Output /M

$1.91/M

Cache read /M

$0.08/M

TTFT

1s

Throughput

64 tps

Kimi K2.6 Thinking

FP4

moonshotai/kimi-k2.6:thinking:baidu

Context

262k

Input /M

$0.45/M

Output /M

$1.91/M

Cache read /M

$0.08/M

TTFT

1s

Throughput

64 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.