Merge branch 'anomalyco:dev' into dev

sylviezhang37 · web-flow · commit 53ac115e1afd · 2026-03-17T09:58:24.000-07:00
diff --git a/providers/chutes/models/MiniMaxAI/MiniMax-M2.5-TEE.toml b/providers/chutes/models/MiniMaxAI/MiniMax-M2.5-TEE.toml
@@ -10,8 +10,9 @@ structured_output = true
 open_weights = true
 
 [cost]
-input = 0.15
-output = 0.6
+input = 0.30
+output = 1.10
+cache_read = 0.15
 
 [limit]
 context = 196_608
diff --git a/providers/chutes/models/Qwen/Qwen3.5-397B-A17B-TEE.toml b/providers/chutes/models/Qwen/Qwen3.5-397B-A17B-TEE.toml
@@ -10,9 +10,9 @@ structured_output = true
 open_weights = true
 
 [cost]
-input = 0.30
-output = 1.20
-cache_read = 0.15
+input = 0.39
+output = 2.34
+cache_read = 0.195
 
 [limit]
 context = 262_144
diff --git a/providers/chutes/models/deepseek-ai/DeepSeek-V3.2-TEE.toml b/providers/chutes/models/deepseek-ai/DeepSeek-V3.2-TEE.toml
@@ -10,12 +10,12 @@ structured_output = true
 open_weights = true
 
 [cost]
-input = 0.25
-output = 0.38
-cache_read = 0.125
+input = 0.28
+output = 0.42
+cache_read = 0.14
 
 [limit]
-context = 163_840
+context = 131_072
 output = 65_536
 
 [modalities]
diff --git a/providers/chutes/models/zai-org/GLM-4.6-TEE.toml b/providers/chutes/models/zai-org/GLM-4.6-TEE.toml
@@ -10,8 +10,9 @@ structured_output = true
 open_weights = true
 
 [cost]
-input = 0.35
-output = 1.50
+input = 0.40
+output = 1.70
+cache_read = 0.20
 
 [limit]
 context = 202_752
diff --git a/providers/chutes/models/zai-org/GLM-4.6V.toml b/providers/chutes/models/zai-org/GLM-4.6V.toml
@@ -12,6 +12,7 @@ open_weights = true
 [cost]
 input = 0.30
 output = 0.90
+cache_read = 0.15
 
 [limit]
 context = 131_072
diff --git a/providers/chutes/models/zai-org/GLM-5-TEE.toml b/providers/chutes/models/zai-org/GLM-5-TEE.toml
@@ -10,8 +10,9 @@ structured_output = true
 open_weights = true
 
 [cost]
-input = 0.750
-output = 2.50
+input = 0.95
+output = 3.15
+cache_read = 0.475
 
 [limit]
 context = 202_752
diff --git a/providers/opencode/models/gemini-3-pro.toml b/providers/opencode/models/gemini-3-pro.toml
@@ -9,6 +9,7 @@ tool_call = true
 structured_output = true
 knowledge = "2025-01"
 open_weights = false
+status = "deprecated"
 
 [cost]
 input = 2.00
diff --git a/providers/opencode/models/glm-4.6.toml b/providers/opencode/models/glm-4.6.toml
@@ -8,6 +8,7 @@ temperature = true
 tool_call = true
 knowledge = "2025-04"
 open_weights = true
+status = "deprecated"
 
 [cost]
 input = 0.6
diff --git a/providers/opencode/models/glm-4.7.toml b/providers/opencode/models/glm-4.7.toml
@@ -8,6 +8,7 @@ temperature = true
 tool_call = true
 knowledge = "2025-04"
 open_weights = true
+status = "deprecated"
 
 [interleaved]
 field = "reasoning_content"
diff --git a/providers/opencode/models/minimax-m2.1.toml b/providers/opencode/models/minimax-m2.1.toml
@@ -8,6 +8,7 @@ temperature = true
 tool_call = true
 knowledge = "2025-01"
 open_weights = true
+status = "deprecated"
 
 [interleaved]
 field = "reasoning_content"
diff --git a/providers/vultr/models/DeepSeek-R1-Distill-Llama-70B.toml b/providers/vultr/models/DeepSeek-R1-Distill-Llama-70B.toml
@@ -10,8 +10,8 @@ release_date = "2025-01-20"
 last_updated = "2025-01-20"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 2.00
+output = 2.00
 
 [limit]
 context = 130_000
diff --git a/providers/vultr/models/DeepSeek-R1-Distill-Qwen-32B.toml b/providers/vultr/models/DeepSeek-R1-Distill-Qwen-32B.toml
@@ -10,8 +10,8 @@ release_date = "2025-01-20"
 last_updated = "2025-01-20"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 0.30
+output = 0.30
 
 [limit]
 context = 130_000
diff --git a/providers/vultr/models/DeepSeek-V3.2.toml b/providers/vultr/models/DeepSeek-V3.2.toml
@@ -11,7 +11,7 @@ last_updated = "2025-01-20"
 
 [cost]
 input = 0.55
-output = 2.75
+output = 1.65
 
 [limit]
 context = 163_000
diff --git a/providers/vultr/models/GLM-5-FP8.toml b/providers/vultr/models/GLM-5-FP8.toml
@@ -10,8 +10,8 @@ release_date = "2025-01-20"
 last_updated = "2025-01-20"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 0.85
+output = 3.10
 
 [limit]
 context = 202_000
diff --git a/providers/vultr/models/Llama-3_1-Nemotron-Ultra-253B-v1.toml b/providers/vultr/models/Llama-3_1-Nemotron-Ultra-253B-v1.toml
@@ -11,7 +11,7 @@ last_updated = "2025-01-20"
 
 [cost]
 input = 0.55
-output = 2.75
+output = 1.80
 
 [limit]
 context = 32_000
diff --git a/providers/vultr/models/MiniMax-M2.5.toml b/providers/vultr/models/MiniMax-M2.5.toml
@@ -10,8 +10,8 @@ release_date = "2025-01-20"
 last_updated = "2025-01-20"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 0.30
+output = 1.20
 
 [limit]
 context = 196_000
diff --git a/providers/vultr/models/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4.toml b/providers/vultr/models/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4.toml
@@ -10,8 +10,8 @@ release_date = "2025-01-20"
 last_updated = "2025-01-20"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 0.20
+output = 0.80
 
 [limit]
 context = 260_000
diff --git a/providers/vultr/models/Qwen2.5-Coder-32B-Instruct.toml b/providers/vultr/models/Qwen2.5-Coder-32B-Instruct.toml
@@ -10,8 +10,8 @@ release_date = "2024-11-06"
 last_updated = "2024-11-06"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 0.20
+output = 0.60
 
 [limit]
 context = 15_000
diff --git a/providers/vultr/models/gpt-oss-120b.toml b/providers/vultr/models/gpt-oss-120b.toml
@@ -10,8 +10,8 @@ release_date = "2025-06-23"
 last_updated = "2025-06-23"
 
 [cost]
-input = 0.55
-output = 2.75
+input = 0.15
+output = 0.60
 
 [limit]
 context = 130_000
