GLM-5.3-Flash

Z.aiOpen weights1.05M context

GLM-5.3-Flash is an open-weights model from Z.ai with a 1.05M-token context window. 12 providers list it, all at $0.15 per million input tokens and $0.50 per million output tokens.

Maker
Z.ai
Licence
Open weights
Context window
1.05M
Providers listed
12
Lowest input, per 1M
$0.15
Lowest output, per 1M
$0.50
Effort settings
Max

Providers serving GLM-5.3-Flash

Cheapest first, by the blended rate of three input tokens to one output token. Prices in US dollars per million tokens, as of 26 Oct 2026.

ProviderInputOutputContextToolsJSON modeOpenAI-compatibleModel ID
Arcee AI
$0.15$0.501MYesYesYeszai-org/glm-5.3-flash
Baseten
$0.15$0.501.05MYesYesYeszai-org/GLM-5.3-Flash
Cloudflare
$0.15$0.501.05MYesYesYes@cf/zai-org/glm-5.3-flash
DeepInfra
$0.15$0.501.05MYesYesNozai-org/GLM-5.3-Flash
DigitalOcean
$0.15$0.501.05MYesYesYesglm-5.3-flash
Fireworks
$0.15$0.501.05MYesYesYesaccounts/fireworks/models/glm-5p3-flash
FriendliAI
$0.15$0.501.05MYesYesYeszai-org/GLM-5.3-Flash
Mistral
$0.15$0.501.05MYesYesNozai-glm-5-3-flash
Nebius
$0.15$0.501.02MYesYesYeszai-org/GLM-5.3-Flash
Novita
$0.15$0.501.05MYesYesYeszai-org/glm-5.3-flash
SiliconFlow
$0.15$0.501.05MYesYesYeszai-org/GLM-5.3-Flash
Together AI
$0.15$0.501.05MYesYesNozai-org/GLM-5.3-Flash

Benchmark scores

Published scores only, each linked to its source. Compare every model in Bench rankings

BenchmarkMax
GPQA Diamond
PhD-level scientific reasoning
90.2%
APEX-Agents
Agentic office work
52.8%

More from Z.ai