io.net

Models served by io.net

Model	Context	Input /M	Output /M	Cache read /M	Latency	Throughput
GLM 5.3 FP8 z-ai/glm-5.3:ionet	262k	$1.31/M	$4.62/M	$0.27/M	1.5s	25 tps
GLM 5.3 (Thinking) FP8 z-ai/glm-5.3:thinking:ionet	262k	$1.31/M	$4.62/M	$0.27/M	1.5s	25 tps
GLM 5.3 Flash FP8 z-ai/glm-5.3-flash:ionet	262k	$0.16/M	$0.53/M	$0.03/M	2.7s	11 tps
Qwen 3.6 35B A3B FP8 Qwen/Qwen3.6-35B-A3B:ionet	262k	$0.20/M	$1.25/M	$0.09/M	2.5s	10 tps
Qwen 3.6 35B A3B Thinking FP8 Qwen/Qwen3.6-35B-A3B:thinking:ionet	262k	$0.20/M	$1.25/M	$0.09/M	2.5s	10 tps
Qwen3.8 27B FP8 qwen3.8-27b:ionet	262k	$0.45/M	$3.21/M	$0.24/M	0.7s	29 tps
Qwen3.8 27B Thinking FP8 qwen3.8-27b:thinking:ionet	262k	$0.45/M	$3.21/M	$0.24/M	0.7s	29 tps

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 io.net via the API

Append :ionet to the model ID, set "provider": "ionet" in the request body, or send an X-Provider: ionet 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": "z-ai/glm-5.3:ionet",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

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