fix(ollama-cloud): correct 3 context_lengths, add 3 served-but-missing tags

providers/ollama-cloud/models/deepseek-v4-flash:preview.toml

@@ -0,0 +1,18 @@
+# Preview tag of deepseek-v4-flash, served by Ollama Cloud and listed by GET /v1/models.
+# API-verified context: https://ollama.com/api/show (deepseek4.context_length = 1048576)
+name = "deepseek-v4-flash:preview"
+description = "Preview release of the fast DeepSeek model for efficient chat, coding help, and agent loops"
+family = "deepseek-flash"
+attachment = false
+reasoning = true
+reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["high", "max"] }]
+tool_call = true
+open_weights = true
+
+[limit]
+context = 1048576
+output = 1048576
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/ollama-cloud/models/deepseek-v4-pro:0813.toml

@@ -0,0 +1,18 @@
+# Dated tag of deepseek-v4-pro, served by Ollama Cloud and listed by GET /v1/models.
+# API-verified context: https://ollama.com/api/show (deepseek4.context_length = 1048576)
+name = "deepseek-v4-pro:0813"
+description = "Dated release of the flagship DeepSeek model for coding, reasoning, and agentic work"
+family = "deepseek-thinking"
+attachment = false
+reasoning = true
+reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["high", "max"] }]
+tool_call = true
+open_weights = true
+
+[limit]
+context = 1048576
+output = 1048576
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/ollama-cloud/models/deepseek-v4-pro:preview.toml

@@ -0,0 +1,19 @@
+# Preview tag of deepseek-v4-pro, served by Ollama Cloud and listed by GET /v1/models.
+# NOTE: this tag has HALF the context of the stable tag.
+# API-verified context: https://ollama.com/api/show (deepseek4.context_length = 524288)
+name = "deepseek-v4-pro:preview"
+description = "Preview release of the flagship DeepSeek model for coding, reasoning, and agentic work"
+family = "deepseek-thinking"
+attachment = false
+reasoning = true
+reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["high", "max"] }]
+tool_call = true
+open_weights = true
+
+[limit]
+context = 524288
+output = 524288
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/ollama-cloud/models/glm-5.2.toml

@@ -9,4 +9,4 @@ values = ["high", "max"]
 field = "reasoning_content"
 
 [limit]
-context = 976_000
+context = 1_000_000

providers/ollama-cloud/models/minimax-m3.toml

@@ -13,7 +13,7 @@ open_weights = true
 
 
 [limit]
-context = 512_000
+context = 524_288
 output = 131_072
 
 [modalities]

providers/ollama-cloud/models/nemotron-3-nano:30b.toml

@@ -10,7 +10,7 @@ last_updated = "2026-01-19"
 open_weights = true
 
 [limit]
-context = 1048576
+context = 262144
 output = 131072
 
 [modalities]