Merge pull request #687 from eliasto/ovhcloud/update-models

rekram1-node · web-flow · commit 23e99a093abf · 2026-01-21T16:19:52.000-08:00
Update OVHcloud AI Endpoints models
diff --git a/providers/ovhcloud/models/deepseek-r1-distill-llama-70b.toml b/providers/ovhcloud/models/deepseek-r1-distill-llama-70b.toml
@@ -1,5 +1,4 @@
 name = "DeepSeek-R1-Distill-Llama-70B"
-family = "deepseek-thinking"
 release_date = "2025-01-30"
 last_updated = "2025-01-30"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.74
 output = 0.74
 
 [limit]
-context = 131_000
-output = 131_000
+context = 131_072
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/gpt-oss-120b.toml b/providers/ovhcloud/models/gpt-oss-120b.toml
@@ -1,5 +1,4 @@
 name = "gpt-oss-120b"
-family = "gpt-oss"
 release_date = "2025-08-28"
 last_updated = "2025-08-28"
 attachment = false
@@ -13,8 +12,8 @@ input = 0.09
 output = 0.47
 
 [limit]
-context = 131_000
-output = 131_000
+context = 131_072
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/gpt-oss-20b.toml b/providers/ovhcloud/models/gpt-oss-20b.toml
@@ -1,5 +1,4 @@
 name = "gpt-oss-20b"
-family = "gpt-oss"
 release_date = "2025-08-28"
 last_updated = "2025-08-28"
 attachment = false
@@ -13,8 +12,8 @@ input = 0.05
 output = 0.18
 
 [limit]
-context = 131_000
-output = 131_000
+context = 131_072
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/llama-3.1-8b-instruct.toml b/providers/ovhcloud/models/llama-3.1-8b-instruct.toml
@@ -1,5 +1,4 @@
 name = "Llama-3.1-8B-Instruct"
-family = "llama"
 release_date = "2025-06-11"
 last_updated = "2025-06-11"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.11
 output = 0.11
 
 [limit]
-context = 131_000
-output = 131_000
+context = 131_072
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/llava-next-mistral-7b.toml b/providers/ovhcloud/models/llava-next-mistral-7b.toml
diff --git a/providers/ovhcloud/models/meta-llama-3_1-70b-instruct.toml b/providers/ovhcloud/models/meta-llama-3_1-70b-instruct.toml
diff --git a/providers/ovhcloud/models/meta-llama-3_3-70b-instruct.toml b/providers/ovhcloud/models/meta-llama-3_3-70b-instruct.toml
@@ -1,5 +1,4 @@
 name = "Meta-Llama-3_3-70B-Instruct"
-family = "llama"
 release_date = "2025-04-01"
 last_updated = "2025-04-01"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.74
 output = 0.74
 
 [limit]
-context = 131_000
-output = 131_000
+context = 131_072
+output = 131_072
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/mistral-7b-instruct-v0.3.toml b/providers/ovhcloud/models/mistral-7b-instruct-v0.3.toml
@@ -1,5 +1,4 @@
 name = "Mistral-7B-Instruct-v0.3"
-family = "mistral"
 release_date = "2025-04-01"
 last_updated = "2025-04-01"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.11
 output = 0.11
 
 [limit]
-context = 127_000
-output = 127_000
+context = 65_536
+output = 65_536
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/mistral-nemo-instruct-2407.toml b/providers/ovhcloud/models/mistral-nemo-instruct-2407.toml
@@ -1,5 +1,4 @@
 name = "Mistral-Nemo-Instruct-2407"
-family = "mistral-nemo"
 release_date = "2024-11-20"
 last_updated = "2024-11-20"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.14
 output = 0.14
 
 [limit]
-context = 118_000
-output = 118_000
+context = 65_536
+output = 65_536
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/mistral-small-3.2-24b-instruct-2506.toml b/providers/ovhcloud/models/mistral-small-3.2-24b-instruct-2506.toml
@@ -1,5 +1,4 @@
 name = "Mistral-Small-3.2-24B-Instruct-2506"
-family = "mistral-small"
 release_date = "2025-07-16"
 last_updated = "2025-07-16"
 attachment = true
@@ -14,8 +13,8 @@ input = 0.10
 output = 0.31
 
 [limit]
-context = 128_000
-output = 128_000
+context = 131_072
+output = 131_072
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/ovhcloud/models/mixtral-8x7b-instruct-v0.1.toml b/providers/ovhcloud/models/mixtral-8x7b-instruct-v0.1.toml
@@ -1,5 +1,4 @@
 name = "Mixtral-8x7B-Instruct-v0.1"
-family = "mixtral"
 release_date = "2025-04-01"
 last_updated = "2025-04-01"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.70
 output = 0.70
 
 [limit]
-context = 32_000
-output = 32_000
+context = 32_768
+output = 32_768
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/qwen2.5-coder-32b-instruct.toml b/providers/ovhcloud/models/qwen2.5-coder-32b-instruct.toml
@@ -1,5 +1,4 @@
 name = "Qwen2.5-Coder-32B-Instruct"
-family = "qwen"
 release_date = "2025-03-24"
 last_updated = "2025-03-24"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.96
 output = 0.96
 
 [limit]
-context = 32_000
-output = 32_000
+context = 32_768
+output = 32_768
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/qwen2.5-vl-72b-instruct.toml b/providers/ovhcloud/models/qwen2.5-vl-72b-instruct.toml
@@ -1,5 +1,4 @@
 name = "Qwen2.5-VL-72B-Instruct"
-family = "qwen"
 release_date = "2025-03-31"
 last_updated = "2025-03-31"
 attachment = true
@@ -14,8 +13,8 @@ input = 1.01
 output = 1.01
 
 [limit]
-context = 32_000
-output = 32_000
+context = 32_768
+output = 32_768
 
 [modalities]
 input = ["text", "image"]
diff --git a/providers/ovhcloud/models/qwen3-32b.toml b/providers/ovhcloud/models/qwen3-32b.toml
@@ -1,5 +1,4 @@
 name = "Qwen3-32B"
-family = "qwen"
 release_date = "2025-07-16"
 last_updated = "2025-07-16"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.09
 output = 0.25
 
 [limit]
-context = 32_000
-output = 32_000
+context = 32_768
+output = 32_768
 
 [modalities]
 input = ["text"]
diff --git a/providers/ovhcloud/models/qwen3-coder-30b-a3b-instruct.toml b/providers/ovhcloud/models/qwen3-coder-30b-a3b-instruct.toml
@@ -1,5 +1,4 @@
 name = "Qwen3-Coder-30B-A3B-Instruct"
-family = "qwen"
 release_date = "2025-10-28"
 last_updated = "2025-10-28"
 attachment = false
@@ -14,8 +13,8 @@ input = 0.07
 output = 0.26
 
 [limit]
-context = 256_000
-output = 256_000
+context = 262_144
+output = 262_144
 
 [modalities]
 input = ["text"]
