Updated GLM with reasoning capabilities.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Updated GLM with reasoning capabilities. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for GLM-4.6 on OffRail starts at $0.55 per million input tokens and $2.20 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
GLM-4.6 supports a context window of up to 204,800 tokens on its largest provider deployment.
GLM-4.6 is served by Z AI, NovitaAI through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
GLM-4.6 supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
GLM-4.6 was released on September 30, 2025.
GLM-5.2 Turbo
1,000,000 context$1.99 in / $6.16 out per 1M
GLM-5.3
1,000,000 context$1.40 in / $4.40 out per 1M
GLM-5.2
1,048,576 context$0.55 in / $1.78 out per 1M
GLM-5.1
204,800 context$0.93 in / $2.93 out per 1M
GLM-5
203,000 context$0.57 in / $2.30 out per 1M
GLM-4.7
204,800 context$0.38 in / $1.98 out per 1M