BaseTen

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 BaseTen

Model name

13 models

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	TTFT	Throughput
DeepSeek V4 Flash 0731 FP8 deepseek/deepseek-v4-flash-0731:baseten	1.0M	$0.14/M	$0.27/M	$0.03/M	93.3%	0.5s	107.5 tps
DeepSeek V4 Flash 0731 (Thinking) FP8 deepseek/deepseek-v4-flash-0731:thinking:baseten	1.0M	$0.14/M	$0.27/M	$0.03/M	0%	0.5s	107.5 tps
DeepSeek V4.1 Flash FP8 deepseek/deepseek-v4.1-flash:baseten	1.0M	$0.31/M	$1.26/M	$0.0073/M	0%	0.3s	233.5 tps
DeepSeek V4.1 Flash (Thinking) FP8 deepseek/deepseek-v4.1-flash:thinking:baseten	1.0M	$0.31/M	$1.26/M	$0.0073/M	0%	0.3s	233.5 tps
GLM 5.2 FP8 z-ai/glm-5.2:baseten	1.0M	$1.47/M	$4.62/M	$0.15/M	N/A	0.7s	103 tps
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:baseten	1.0M	$1.47/M	$4.62/M	$0.15/M	N/A	0.7s	103 tps
GLM 5.3 FP4 z-ai/glm-5.3:baseten	1.0M	$1.47/M	$4.62/M	$0.15/M	N/A	1.3s	63 tps
GLM 5.3 (Thinking) FP4 z-ai/glm-5.3:thinking:baseten	1.0M	$1.47/M	$4.62/M	$0.15/M	83.7%	1.3s	63 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:baseten	1.0M	$0.16/M	$0.53/M	$0.03/M	27.3%	1.1s	56 tps
GPT OSS 120B FP4 openai/gpt-oss-120b:baseten	128k	$0.10/M	$0.53/M	$0.10/M	N/A	0.2s	176 tps
Inkling thinkingmachines/inkling:baseten	1.0M	$1.05/M	$4.25/M	$0.18/M	N/A	N/A	N/A
Inkling Thinking thinkingmachines/inkling:thinking:baseten	1.0M	$1.05/M	$4.25/M	$0.18/M	N/A	N/A	N/A
Kimi K3 FP8 moonshotai/kimi-k3:baseten	1.0M	$3.15/M	$15.75/M	$0.31/M	28.8%	4.2s	54 tps

DeepSeek V4 Flash 0731

FP8

deepseek/deepseek-v4-flash-0731:baseten

Context

1.0M

Input /M

$0.14/M

Output /M

$0.27/M

Cache read /M

$0.03/M

Cache hit

93.3%

TTFT

0.5s

Throughput

107.5 tps

DeepSeek V4 Flash 0731 (Thinking)

FP8

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

Context

1.0M

Input /M

$0.14/M

Output /M

$0.27/M

Cache read /M

$0.03/M

Cache hit

0%

TTFT

0.5s

Throughput

107.5 tps

DeepSeek V4.1 Flash

FP8

deepseek/deepseek-v4.1-flash:baseten

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0073/M

Cache hit

0%

TTFT

0.3s

Throughput

233.5 tps

DeepSeek V4.1 Flash (Thinking)

FP8

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

Context

1.0M

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.0073/M

Cache hit

0%

TTFT

0.3s

Throughput

233.5 tps

GLM 5.2

FP8

z-ai/glm-5.2:baseten

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

0.7s

Throughput

103 tps

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:baseten

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

0.7s

Throughput

103 tps

GLM 5.3

FP4

z-ai/glm-5.3:baseten

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.15/M

Cache hit

N/A

TTFT

1.3s

Throughput

63 tps

GLM 5.3 (Thinking)

FP4

z-ai/glm-5.3:thinking:baseten

Context

1.0M

Input /M

$1.47/M

Output /M

$4.62/M

Cache read /M

$0.15/M

Cache hit

83.7%

TTFT

1.3s

Throughput

63 tps

GLM 5.3 Flash

FP8

z-ai/glm-5.3-flash:baseten

Context

1.0M

Input /M

$0.16/M

Output /M

$0.53/M

Cache read /M

$0.03/M

Cache hit

27.3%

TTFT

1.1s

Throughput

56 tps

GPT OSS 120B

FP4

openai/gpt-oss-120b:baseten

Context

128k

Input /M

$0.10/M

Output /M

$0.53/M

Cache read /M

$0.10/M

Cache hit

N/A

TTFT

0.2s

Throughput

176 tps

Inkling

thinkingmachines/inkling:baseten

Context

1.0M

Input /M

$1.05/M

Output /M

$4.25/M

Cache read /M

$0.18/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Inkling Thinking

thinkingmachines/inkling:thinking:baseten

Context

1.0M

Input /M

$1.05/M

Output /M

$4.25/M

Cache read /M

$0.18/M

Cache hit

N/A

TTFT

N/A

Throughput

N/A

Kimi K3

FP8

moonshotai/kimi-k3:baseten

Context

1.0M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.31/M

Cache hit

28.8%

TTFT

4.2s

Throughput

54 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 BaseTen via the API

Call a model served by BaseTen 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-0731:baseten",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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