Tryingopen API

GLM 5.3 Flash

by Z.ai · 320B parameters

z-ai/glm-5.3-flash

Reads text, pictures and video, and holds a million words at once. Only 18B of its 320B works on each word, so it is quick and cheap for its size. Through the API it takes text only.

Credits are charged at these prices whoever answers: the highest price any route lists for this model, including OpenRouter endpoints not shown below.

Providers

With no provider, requests go to Z.ai, which may keep what you send. Name one below to pin it; any provider preference goes through OpenRouter with zero retention.

Provider	Input / 1M	Output / 1M	Context	Zero retention	Slug to pin
Z.ai (default)	Not listed		1M	No	None: send no provider
CoreWeave	15	50	1M	Yes	coreweave
DeepInfra	7.5	25	1M	Yes	deepinfra
InferenceNet	9	28	1M	Yes	inference-net
Relace	9	30	1M	Yes	relace
Wafer	10	35	1M	Yes	wafer
Novita	13.2	44	1M	Yes	novita
Sail Research	14.25	47.5	1M	Yes	sail-research
Baseten	15	50	1M	Yes	baseten
Crusoe	15	50	1M	Yes	crusoe
DigitalOcean	15	50	1M	Yes	digitalocean
Io Net	15	50	262k	Yes	io-net
Near AI	15	50	1M	Yes	near-ai
Parasail	15	50	1M	Yes	parasail
Phala	15	50	1M	Yes	phala
Reka	15	50	262k	Yes	reka
SiliconFlow	15	50	1M	Yes	siliconflow
Together	15	50	1M	Yes	together
Venice	15	50	1M	Yes	venice
Z.AI	15	50	1M	Yes	z-ai
NextBit	18	60	1M	Yes	nextbit
Modal	45	150	1M	Yes	modal

Provider prices are their list prices, in credits, for comparison.

Code

curl https://www.tryingopen.com/v1/chat/completions \
  -H "Authorization: Bearer your-name" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-5.3-flash","max_tokens":1000,"messages":[{"role":"user","content":"Hello!"}]}'

Try it

The API isn't set up on this deployment yet.