Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions providers/privatemode-ai/models/glm-5.3.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
# Sources (accessed 2026-09-01):
# Model overview (preview): https://docs.privatemode.ai/models/overview/#glm-53
# Pricing (EUR): https://docs.privatemode.ai/pricing/
# Added in v1.55.0 (upgraded from GLM-5.2): https://docs.privatemode.ai/release/#v1550
# Upstream: https://huggingface.co/zai-org/GLM-5.3
# Effort: reasoning_effort = low|high|max (default max; always on).
# Any other value including none is silently mapped to max; reasoning cannot be off.
# Cost: EUR list prices converted at 1 EUR = 1.1555 USD (Frankfurter 2026-08-10),
# matching other Privatemode catalog entries with the same EUR list prices.
# EUR/MTok: input 1.55 / output 7.74 / cached input 0.15
base_model = "zhipuai/glm-5.3"
status = "beta"
reasoning_options = [{ type = "effort", values = ["low", "high", "max"] }]

[cost]
input = 1.7910
output = 8.9436
cache_read = 0.1733

[limit]
context = 256_000
22 changes: 22 additions & 0 deletions providers/privatemode-ai/models/glm-latest.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
# Sources (accessed 2026-09-01):
# Alias routes to the latest available GLM model (currently GLM-5.3):
# https://docs.privatemode.ai/models/overview/#glm-53
# Pricing (EUR): https://docs.privatemode.ai/pricing/
# Release: https://docs.privatemode.ai/release/#v1550
# Effort: reasoning_effort = low|high|max (default max; always on).
# Any other value including none is silently mapped to max; reasoning cannot be off.
# Cost: EUR list prices converted at 1 EUR = 1.1555 USD (Frankfurter 2026-08-10),
# matching other Privatemode catalog entries with the same EUR list prices.
# EUR/MTok: input 1.55 / output 7.74 / cached input 0.15
base_model = "zhipuai/glm-5.3"
name = "GLM (latest)"
status = "beta"
reasoning_options = [{ type = "effort", values = ["low", "high", "max"] }]

[cost]
input = 1.7910
output = 8.9436
cache_read = 0.1733

[limit]
context = 256_000