[venice] Add Claude Opus 4.7 and update Qwen models

- Add Claude Opus 4.7 with 1M context, 128K output, multimodal support
- Update Qwen 3.5 35B and 397B to open_weights=true and refresh last_updated
- Remove deprecated models: Grok Code Fast 1, Mercury Edit 2, MiniMax M2.1

Author: dpuyosa

providers/venice/models/claude-opus-4-7.toml

@@ -0,0 +1,24 @@
+name = "Claude Opus 4.7"
+family = "claude-opus"
+attachment = true
+reasoning = true
+tool_call = true
+structured_output = true
+temperature = true
+release_date = "2026-04-16"
+last_updated = "2026-04-16"
+open_weights = false
+
+[cost]
+input = 6
+output = 30
+cache_read = 0.6
+cache_write = 7.5
+
+[limit]
+context = 1_000_000
+output = 128_000
+
+[modalities]
+input = ["text", "image"]
+output = ["text"]

providers/venice/models/grok-code-fast-1.toml

@@ -6,8 +6,8 @@ tool_call = true
 structured_output = true
 temperature = true
 release_date = "2026-02-25"
-last_updated = "2026-04-12"
-open_weights = false
+last_updated = "2026-04-16"
+open_weights = true
 
 [cost]
 input = 0.3125

providers/venice/models/mercury-edit-2.toml

@@ -6,8 +6,8 @@ tool_call = true
 structured_output = true
 temperature = true
 release_date = "2026-02-16"
-last_updated = "2026-04-09"
-open_weights = false
+last_updated = "2026-04-16"
+open_weights = true
 
 [cost]
 input = 0.75