TensorX

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 TensorX

Model name

18 models

Model	Context	Input /M	Output /M	Cache read /M	TTFT	Throughput
DeepSeek V4 Flash 0731 FP4 deepseek/deepseek-v4-flash-0731:tensorix	1M	$0.16/M	$0.31/M	$0.04/M	N/A	N/A
DeepSeek V4 Flash 0731 (Thinking) FP4 deepseek/deepseek-v4-flash-0731:thinking:tensorix	1M	$0.16/M	$0.31/M	$0.04/M	N/A	N/A
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813:tensorix	1.0M	$2.10/M	$4.20/M	$0.53/M	N/A	N/A
DeepSeek V4 Pro 0813 (Thinking) deepseek/deepseek-v4-pro-0813:thinking:tensorix	1.0M	$2.10/M	$4.20/M	$0.53/M	N/A	N/A
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash:tensorix	1.0M	$0.53/M	$1.57/M	$0.13/M	N/A	N/A
DeepSeek V4.1 Flash (Thinking) deepseek/deepseek-v4.1-flash:thinking:tensorix	1.0M	$0.53/M	$1.57/M	$0.13/M	N/A	N/A
GLM 5.2 FP8 z-ai/glm-5.2:tensorix	1.0M	$1.16/M	$3.47/M	$0.29/M	N/A	N/A
GLM 5.2 (Thinking) FP8 z-ai/glm-5.2:thinking:tensorix	1.0M	$1.16/M	$3.47/M	$0.29/M	N/A	N/A
GLM 5.3 z-ai/glm-5.3:tensorix	1.0M	$1.84/M	$4.72/M	$0.46/M	N/A	N/A
GLM 5.3 (Thinking) z-ai/glm-5.3:thinking:tensorix	1.0M	$1.84/M	$4.72/M	$0.46/M	N/A	N/A
GLM 5.3 Flash z-ai/glm-5.3-flash:tensorix	1.0M	$0.21/M	$0.53/M	$0.05/M	N/A	N/A
Kimi K2.7 Code INT4 moonshotai/kimi-k2.7-code:tensorix	262k	$1.00/M	$4.20/M	$0.25/M	N/A	N/A
Kimi K3 moonshotai/kimi-k3:tensorix	1M	$3.15/M	$15.75/M	$0.79/M	N/A	N/A
MiniMax M3 FP8 minimax/minimax-m3:tensorix	512k	$0.31/M	$1.26/M	$0.08/M	N/A	N/A
MiniMax M3 Thinking FP8 minimax/minimax-m3:thinking:tensorix	512k	$0.31/M	$1.26/M	$0.08/M	N/A	N/A
Qwen3.8 Flash alibaba/qwen3.8-flash:tensorix	262k	$0.21/M	$0.53/M	$0.05/M	N/A	N/A
Qwen3.8 Max qwen3.8-max:tensorix	262k	$2.63/M	$6.30/M	$0.66/M	N/A	N/A
Qwen3.8 Max Thinking qwen3.8-max:thinking:tensorix	262k	$2.63/M	$6.30/M	$0.66/M	N/A	N/A

DeepSeek V4 Flash 0731

FP4

deepseek/deepseek-v4-flash-0731:tensorix

Context

1M

Input /M

$0.16/M

Output /M

$0.31/M

Cache read /M

$0.04/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Flash 0731 (Thinking)

FP4

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

Context

1M

Input /M

$0.16/M

Output /M

$0.31/M

Cache read /M

$0.04/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Pro 0813

deepseek/deepseek-v4-pro-0813:tensorix

Context

1.0M

Input /M

$2.10/M

Output /M

$4.20/M

Cache read /M

$0.53/M

TTFT

N/A

Throughput

N/A

DeepSeek V4 Pro 0813 (Thinking)

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

Context

1.0M

Input /M

$2.10/M

Output /M

$4.20/M

Cache read /M

$0.53/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash:tensorix

Context

1.0M

Input /M

$0.53/M

Output /M

$1.57/M

Cache read /M

$0.13/M

TTFT

N/A

Throughput

N/A

DeepSeek V4.1 Flash (Thinking)

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

Context

1.0M

Input /M

$0.53/M

Output /M

$1.57/M

Cache read /M

$0.13/M

TTFT

N/A

Throughput

N/A

GLM 5.2

FP8

z-ai/glm-5.2:tensorix

Context

1.0M

Input /M

$1.16/M

Output /M

$3.47/M

Cache read /M

$0.29/M

TTFT

N/A

Throughput

N/A

GLM 5.2 (Thinking)

FP8

z-ai/glm-5.2:thinking:tensorix

Context

1.0M

Input /M

$1.16/M

Output /M

$3.47/M

Cache read /M

$0.29/M

TTFT

N/A

Throughput

N/A

GLM 5.3

z-ai/glm-5.3:tensorix

Context

1.0M

Input /M

$1.84/M

Output /M

$4.72/M

Cache read /M

$0.46/M

TTFT

N/A

Throughput

N/A

GLM 5.3 (Thinking)

z-ai/glm-5.3:thinking:tensorix

Context

1.0M

Input /M

$1.84/M

Output /M

$4.72/M

Cache read /M

$0.46/M

TTFT

N/A

Throughput

N/A

GLM 5.3 Flash

z-ai/glm-5.3-flash:tensorix

Context

1.0M

Input /M

$0.21/M

Output /M

$0.53/M

Cache read /M

$0.05/M

TTFT

N/A

Throughput

N/A

Kimi K2.7 Code

INT4

moonshotai/kimi-k2.7-code:tensorix

Context

262k

Input /M

$1.00/M

Output /M

$4.20/M

Cache read /M

$0.25/M

TTFT

N/A

Throughput

N/A

Kimi K3

moonshotai/kimi-k3:tensorix

Context

1M

Input /M

$3.15/M

Output /M

$15.75/M

Cache read /M

$0.79/M

TTFT

N/A

Throughput

N/A

MiniMax M3

FP8

minimax/minimax-m3:tensorix

Context

512k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.08/M

TTFT

N/A

Throughput

N/A

MiniMax M3 Thinking

FP8

minimax/minimax-m3:thinking:tensorix

Context

512k

Input /M

$0.31/M

Output /M

$1.26/M

Cache read /M

$0.08/M

TTFT

N/A

Throughput

N/A

Qwen3.8 Flash

alibaba/qwen3.8-flash:tensorix

Context

262k

Input /M

$0.21/M

Output /M

$0.53/M

Cache read /M

$0.05/M

TTFT

N/A

Throughput

N/A

Qwen3.8 Max

qwen3.8-max:tensorix

Context

262k

Input /M

$2.63/M

Output /M

$6.30/M

Cache read /M

$0.66/M

TTFT

N/A

Throughput

N/A

Qwen3.8 Max Thinking

qwen3.8-max:thinking:tensorix

Context

262k

Input /M

$2.63/M

Output /M

$6.30/M

Cache read /M

$0.66/M

TTFT

N/A

Throughput

N/A

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 TensorX via the API

Call a model served by TensorX 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:tensorix",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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