Add Tempr's Mistral models

models/mistral/mistral-embed.toml

@@ -0,0 +1,18 @@
+name = "Mistral Embed"
+description = "Embedding model for semantic search, retrieval, clustering, and ranking pipelines"
+family = "mistral-embed"
+release_date = "2023-12-11"
+last_updated = "2023-12-11"
+attachment = false
+reasoning = false
+temperature = false
+tool_call = false
+open_weights = false
+
+[limit]
+context = 8_000
+output = 3_072
+
+[modalities]
+input = ["text"]
+output = ["text"]

providers/tempr/models/mistral/mistral-embed.toml

@@ -0,0 +1,5 @@
+base_model = "mistral/mistral-embed"
+
+[cost]
+input = 0.1
+output = 0

providers/tempr/models/mistral/mistral-large-2512.toml

@@ -0,0 +1,5 @@
+base_model = "mistral/mistral-large-2512"
+
+[cost]
+input = 0.5
+output = 1.5

providers/tempr/models/mistral/mistral-large-latest.toml

@@ -0,0 +1,5 @@
+base_model = "mistral/mistral-large-latest"
+
+[cost]
+input = 0.5
+output = 1.5

providers/tempr/models/mistral/mistral-medium-2604.toml

@@ -0,0 +1,14 @@
+# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
+# Off: reasoning.effort = "none" (or reasoning.enabled = false)
+# Effort: reasoning.effort = none|high (alias: top-level reasoning_effort)
+# /v1/messages: thinking.type = enabled|disabled; output_config.effort = high
+# /v1/responses: reasoning.effort = none|high
+base_model = "mistral/mistral-medium-2604"
+
+reasoning_options = [
+  { type = "effort", values = ["none", "high"] },
+]
+
+[cost]
+input = 1.5
+output = 7.5

providers/tempr/models/mistral/mistral-medium-latest.toml

@@ -0,0 +1,14 @@
+# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
+# Off: reasoning.effort = "none" (or reasoning.enabled = false)
+# Effort: reasoning.effort = none|high (alias: top-level reasoning_effort)
+# /v1/messages: thinking.type = enabled|disabled; output_config.effort = high
+# /v1/responses: reasoning.effort = none|high
+base_model = "mistral/mistral-medium-latest"
+
+reasoning_options = [
+  { type = "effort", values = ["none", "high"] },
+]
+
+[cost]
+input = 1.5
+output = 7.5

providers/tempr/models/mistral/mistral-small-2603.toml

@@ -0,0 +1,14 @@
+# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
+# Off: reasoning.effort = "none" (or reasoning.enabled = false)
+# Effort: reasoning.effort = none|high (alias: top-level reasoning_effort)
+# /v1/messages: thinking.type = enabled|disabled; output_config.effort = high
+# /v1/responses: reasoning.effort = none|high
+base_model = "mistral/mistral-small-2603"
+
+reasoning_options = [
+  { type = "effort", values = ["none", "high"] },
+]
+
+[cost]
+input = 0.15
+output = 0.6

providers/tempr/models/mistral/mistral-small-latest.toml

@@ -0,0 +1,14 @@
+# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
+# Off: reasoning.effort = "none" (or reasoning.enabled = false)
+# Effort: reasoning.effort = none|high (alias: top-level reasoning_effort)
+# /v1/messages: thinking.type = enabled|disabled; output_config.effort = high
+# /v1/responses: reasoning.effort = none|high
+base_model = "mistral/mistral-small-latest"
+
+reasoning_options = [
+  { type = "effort", values = ["none", "high"] },
+]
+
+[cost]
+input = 0.15
+output = 0.6

providers/tempr/models/mistral/voxtral-small-latest.toml

@@ -0,0 +1,5 @@
+base_model = "mistral/voxtral-small-latest"
+
+[cost]
+input = 0.1
+output = 0.3

providers/tempr/models/mistral/zai-glm-5-2.toml

@@ -0,0 +1,16 @@
+# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
+# Off: reasoning.effort = "none" (or reasoning.enabled = false)
+# Effort: reasoning.effort = none|high|max (alias: top-level reasoning_effort)
+# /v1/messages: thinking.type = enabled|disabled; output_config.effort = high|max
+# /v1/responses: reasoning.effort = none|high|max
+base_model = "zhipuai/glm-5.2"
+status = "beta"
+
+reasoning_options = [
+  { type = "effort", values = ["none", "high", "max"] },
+]
+
+[cost]
+input = 1.4
+output = 4.4
+cache_read = 0.14

providers/tempr/models/mistral/zai-glm-5-3.toml

@@ -0,0 +1,14 @@
+# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
+# Effort: reasoning.effort = low|high|max (alias: top-level reasoning_effort)
+# /v1/messages: output_config.effort = low|high|max
+# /v1/responses: reasoning.effort = low|high|max
+base_model = "zhipuai/glm-5.3"
+
+reasoning_options = [
+  { type = "effort", values = ["low", "high", "max"] },
+]
+
+[cost]
+input = 1.4
+output = 4.4
+cache_read = 0.14