TensorX

43 models available

Models served by TensorX

Model	Context	Input /M	Output /M	Cache read /M	Cache hit	Latency	Throughput
DeepSeek R1-0528 FP8	128k	$0.69/M	$2.73/M	$0.17/M	N/A	N/A	N/A
DeepSeek V3 0324 FP8	128k	$0.31/M	$1.05/M	$0.08/M	N/A	N/A	N/A
DeepSeek V3.1 FP8	128k	$0.21/M	$0.84/M	$0.05/M	N/A	N/A	N/A
DeepSeek V3.2 FP8	163k	$0.31/M	$0.53/M	$0.08/M	N/A	N/A	N/A
DeepSeek V3.2 (Thinking) FP8	163k	$0.31/M	$0.53/M	$0.08/M	N/A	N/A	N/A
DeepSeek V4 Flash 0731 FP4	1M	$0.16/M	$0.31/M	$0.04/M	N/A	N/A	N/A
DeepSeek V4 Flash 0731 (Thinking) FP4	1M	$0.16/M	$0.31/M	$0.04/M	N/A	N/A	N/A
DeepSeek V4 Pro FP8	1.0M	$1.84/M	$3.68/M	$0.46/M	N/A	N/A	N/A
DeepSeek V4 Pro (Thinking) FP8	1.0M	$1.84/M	$3.68/M	$0.46/M	N/A	N/A	N/A
GLM 4.6 FP8	200k	$0.42/M	$1.84/M	$0.11/M	N/A	N/A	N/A
GLM 4.6 (Thinking) FP8	200k	$0.42/M	$1.84/M	$0.11/M	N/A	N/A	N/A
GLM 4.7 FP8	200k	$0.63/M	$2.31/M	$0.16/M	N/A	N/A	N/A
GLM 4.7 (Thinking) FP8	200k	$0.63/M	$2.31/M	$0.16/M	N/A	N/A	N/A
GLM 5 FP8	200k	$1.05/M	$3.36/M	$0.26/M	N/A	N/A	N/A
GLM 5 (Thinking) FP8	200k	$1.05/M	$3.36/M	$0.26/M	N/A	N/A	N/A
GLM 5.1 FP8	200k	$1.47/M	$4.62/M	$0.37/M	N/A	N/A	N/A
GLM 5.1 (Thinking) FP8	200k	$1.47/M	$4.62/M	$0.37/M	N/A	N/A	N/A
GLM 5.2 FP8	1.0M	$1.16/M	$3.47/M	$0.29/M	15.5%	4.3s	214.3 tps
GLM 5.2 (Thinking) FP8	1.0M	$1.16/M	$3.47/M	$0.29/M	N/A	N/A	N/A
GLM 5.3	1.0M	$1.84/M	$4.72/M	$0.46/M	0%	2.2s	191 tps
GLM 5.3 (Thinking)	1.0M	$1.84/M	$4.72/M	$0.46/M	24.6%	2.7s	199.4 tps
GLM 5.3 Flash	1.0M	$0.21/M	$0.53/M	$0.05/M	21.2%	3.3s	111.9 tps
GPT OSS 120B FP8	128k	$0.04/M	$0.21/M	$0.01/M	N/A	N/A	N/A
GPT OSS 20B FP8	128k	$0.03/M	$0.15/M	$0.0079/M	N/A	N/A	N/A
Kimi K2.5 INT4	256k	$0.53/M	$2.94/M	$0.13/M	N/A	N/A	N/A
Kimi K2.5 Thinking INT4	256k	$0.53/M	$2.94/M	$0.13/M	N/A	N/A	N/A
Kimi K2.6 INT4	256k	$1.05/M	$4.20/M	$0.26/M	N/A	N/A	N/A
Kimi K2.6 Thinking INT4	256k	$1.05/M	$4.20/M	$0.26/M	N/A	N/A	N/A
Kimi K2.7 Code INT4	262k	$1.00/M	$4.20/M	$0.25/M	N/A	N/A	N/A
Kimi K3	1M	$3.15/M	$15.75/M	$0.79/M	N/A	N/A	N/A
Llama 3.3 70B Instruct FP8	131k	$0.11/M	$0.33/M	$0.03/M	N/A	N/A	N/A
Llama 4 Maverick FP8	1.0M	$0.14/M	$0.71/M	$0.04/M	N/A	N/A	N/A
MiniMax M2.1 FP8	200k	$0.31/M	$2.52/M	$0.08/M	N/A	N/A	N/A
MiniMax M2.5 FP8	205k	$0.31/M	$1.26/M	$0.08/M	N/A	N/A	N/A
MiniMax M2.7 FP8	205k	$0.31/M	$1.26/M	$0.08/M	N/A	N/A	N/A
MiniMax M3 FP8	512k	$0.31/M	$1.26/M	$0.08/M	N/A	N/A	N/A
MiniMax M3 Thinking FP8	512k	$0.31/M	$1.26/M	$0.08/M	N/A	N/A	N/A
Qwen 2.5 72B Instruct FP8	131k	$0.07/M	$0.27/M	$0.02/M	N/A	N/A	N/A
Qwen3.5 122B A10B FP8	131k	$0.53/M	$3.68/M	$0.13/M	N/A	N/A	N/A
Qwen3.5 122B A10B Thinking FP8	131k	$0.53/M	$3.68/M	$0.13/M	N/A	N/A	N/A
Qwen3.8 Flash	262k	$0.21/M	$0.53/M	$0.05/M	N/A	N/A	N/A
Qwen3.8 Max	262k	$2.63/M	$6.30/M	$0.66/M	N/A	N/A	N/A
Qwen3.8 Max Thinking	262k	$2.63/M	$6.30/M	$0.66/M	N/A	N/A	N/A

Prices are per million tokens and include the 5% provider-selection markup. Availability and pricing refresh continuously; each model page shows the live provider comparison.

Using TensorX via the API

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 5% markup over that provider's base price; the prices in the table above already include it.

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:tensorix",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

See the API documentation for provider preferences, price-aware routing, and error behavior.

TensorX terms of use TensorX privacy policy