Skip to content
Python

Price the Nemotron 3 Ultra, Nemotron 3.5 Lightning and GLM 5.3 OpenRouter rows (OPE-215)

Devika Vermae0543d656c86
diff --git a/coworker/headless/prices.yaml b/coworker/headless/prices.yaml
index 299c75a0..ff8d8208 100644
--- a/coworker/headless/prices.yaml
+++ b/coworker/headless/prices.yaml
@@ -92,3 +92,25 @@ models:
cache_read: 0.30
cache_write: 3.00
source: "https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints (read 2026-09-09), Together endpoint"
+ # NVIDIA Nemotron and GLM 5.3 via OpenRouter, each pinned to one host (`--provider-order`).
+ # OpenRouter serves these from several hosts at different rates; a row holds the pinned
+ # host's rate. None of the hosts quotes a separate cache-write price; cache_write is the
+ # plain input price, as for the Together rows above.
+ "openrouter:nvidia/nemotron-3-ultra-550b-a55b":
+ input: 0.60
+ output: 2.40
+ cache_read: 0.12
+ cache_write: 0.60
+ source: "https://openrouter.ai/api/v1/models/nvidia/nemotron-3-ultra-550b-a55b/endpoints (read 2026-10-01), BaseTen endpoint"
+ "openrouter:nvidia/nemotron-3.5-lightning":
+ input: 0.07
+ output: 0.20
+ cache_read: 0.04
+ cache_write: 0.07
+ source: "https://openrouter.ai/api/v1/models/nvidia/nemotron-3.5-lightning/endpoints (read 2026-10-01), CoreWeave endpoint"
+ "openrouter:z-ai/glm-5.3":
+ input: 1.40
+ output: 4.40
+ cache_read: 0.26
+ cache_write: 1.40
+ source: "https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints (read 2026-10-01), Z.AI endpoint"