Skip to content

Add Tempr's AWS Bedrock models #7586

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
chrissalomon wants to merge 1 commit into from
Closed

Add Tempr's AWS Bedrock models #7586

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions providers/tempr/logo.svg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
20 changes: 20 additions & 0 deletions providers/tempr/models/aws-bedrock/amazon.nova-2-lite-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high (alias: top-level reasoning_effort)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high
# /v1/responses: reasoning.effort = none|low|medium|high
base_model = "amazon/nova-2-lite"

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high"] },
]

[cost]
input = 0.33
output = 2.75
cache_read = 0.0825
cache_write = 0.33

[limit]
output = 65_535
7 changes: 7 additions & 0 deletions providers/tempr/models/aws-bedrock/amazon.nova-lite-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
base_model = "amazon/nova-lite"

[cost]
input = 0.06
output = 0.24
cache_read = 0.015
cache_write = 0.06
7 changes: 7 additions & 0 deletions providers/tempr/models/aws-bedrock/amazon.nova-micro-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
base_model = "amazon/nova-micro"

[cost]
input = 0.035
output = 0.14
cache_read = 0.00875
cache_write = 0.035
7 changes: 7 additions & 0 deletions providers/tempr/models/aws-bedrock/amazon.nova-pro-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
base_model = "amazon/nova-pro"

[cost]
input = 0.80
output = 3.20
cache_read = 0.20
cache_write = 0.80
15 changes: 15 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-fable-5-1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Effort: reasoning.effort = low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = low|medium|high|xhigh|max
base_model = "anthropic/claude-fable-5-1"

reasoning_options = [
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 10
output = 50
cache_read = 0.25
cache_write = 12.5
15 changes: 15 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-fable-5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Effort: reasoning.effort = low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = low|medium|high|xhigh|max
base_model = "anthropic/claude-fable-5"

reasoning_options = [
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 10
output = 50
cache_read = 1
cache_write = 12.5
18 changes: 18 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high (sized to a thinking budget)
base_model = "anthropic/claude-haiku-4-5-20251001"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 1.00
output = 5.00
cache_read = 0.10
cache_write = 1.25
18 changes: 18 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-opus-4-1-20250805-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high (sized to a thinking budget)
base_model = "anthropic/claude-opus-4-1-20250805"
status = "deprecated"

reasoning_options = [
{ type = "toggle" },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 15
output = 75
cache_read = 1.5
cache_write = 18.75
20 changes: 20 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-opus-4-5-20251101-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high (alias: top-level reasoning_effort)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high
base_model = "anthropic/claude-opus-4-5-20251101"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high"] },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 5.00
output = 25.00
cache_read = 0.50
cache_write = 6.25
20 changes: 20 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-opus-4-6-v1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|max (alias: top-level reasoning_effort)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|max; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high|max
base_model = "anthropic/claude-opus-4-6"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "max"] },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 5.50
output = 27.50
cache_read = 0.55
cache_write = 6.875
17 changes: 17 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-opus-4-7.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = none|low|medium|high|xhigh|max
base_model = "anthropic/claude-opus-4-7"

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 5.00
output = 25.00
cache_read = 0.50
cache_write = 6.25
17 changes: 17 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-opus-4-8.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = none|low|medium|high|xhigh|max
base_model = "anthropic/claude-opus-4-8"

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 5
output = 25
cache_read = 0.5
cache_write = 6.25
15 changes: 15 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-opus-5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Effort: reasoning.effort = low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = low|medium|high|xhigh|max
base_model = "anthropic/claude-opus-5"

reasoning_options = [
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 5
output = 25
cache_read = 0.5
cache_write = 6.25
18 changes: 18 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high (sized to a thinking budget)
base_model = "anthropic/claude-sonnet-4-5-20250929"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 3.00
output = 15.00
cache_read = 0.30
cache_write = 3.75
23 changes: 23 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-sonnet-4-6.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|max (alias: top-level reasoning_effort)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|max; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high|max
base_model = "anthropic/claude-sonnet-4-6"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "max"] },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 3.30
output = 16.50
cache_read = 0.33
cache_write = 4.125

[limit]
output = 128_000
18 changes: 18 additions & 0 deletions providers/tempr/models/aws-bedrock/anthropic.claude-sonnet-5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = none|low|medium|high|xhigh|max
base_model = "anthropic/claude-sonnet-5"
structured_output = false

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 2
output = 10
cache_read = 0.2
cache_write = 2.5
8 changes: 8 additions & 0 deletions providers/tempr/models/aws-bedrock/apac.amazon.nova-lite-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
base_model = "amazon/nova-lite"
name = "Nova Lite (APAC)"

[cost]
input = 0.063
output = 0.252
cache_read = 0.01575
cache_write = 0.063
8 changes: 8 additions & 0 deletions providers/tempr/models/aws-bedrock/apac.amazon.nova-micro-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
base_model = "amazon/nova-micro"
name = "Nova Micro (APAC)"

[cost]
input = 0.037
output = 0.148
cache_read = 0.00925
cache_write = 0.037
8 changes: 8 additions & 0 deletions providers/tempr/models/aws-bedrock/apac.amazon.nova-pro-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,8 @@
base_model = "amazon/nova-pro"
name = "Nova Pro (APAC)"

[cost]
input = 0.840
output = 3.360
cache_read = 0.210
cache_write = 0.840
19 changes: 19 additions & 0 deletions providers/tempr/models/aws-bedrock/apac.anthropic.claude-sonnet-4-20250514-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high (sized to a thinking budget)
base_model = "anthropic/claude-sonnet-4-20250514"
name = "Claude Sonnet 4 (APAC)"
status = "deprecated"

reasoning_options = [
{ type = "toggle" },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 3
output = 15
cache_read = 0.3
cache_write = 3.75
19 changes: 19 additions & 0 deletions providers/tempr/models/aws-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high (sized to a thinking budget)
base_model = "anthropic/claude-haiku-4-5-20251001"
name = "Claude Haiku 4.5 (AU)"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 1.10
output = 5.50
cache_read = 0.11
cache_write = 1.375
21 changes: 21 additions & 0 deletions providers/tempr/models/aws-bedrock/au.anthropic.claude-opus-4-6-v1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|max (alias: top-level reasoning_effort)
# Budget: reasoning.max_tokens (integer reasoning tokens)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|max; thinking.budget_tokens
# /v1/responses: reasoning.effort = none|low|medium|high|max
base_model = "anthropic/claude-opus-4-6"
name = "AU Anthropic Claude Opus 4.6"
structured_output = true

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "max"] },
{ type = "budget_tokens", min = 1024 },
]

[cost]
input = 5.50
output = 27.50
cache_read = 0.55
cache_write = 6.875
18 changes: 18 additions & 0 deletions providers/tempr/models/aws-bedrock/au.anthropic.claude-opus-4-7.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,18 @@
# Tempr Gateway: https://temprhq.io/docs/gateway-chat-completions#reasoning
# Toggle: reasoning.enabled = true|false (reasoning.effort = "none" also turns it off)
# Effort: reasoning.effort = none|low|medium|high|xhigh|max (alias: top-level reasoning_effort)
# /v1/messages: thinking.type = enabled|disabled; output_config.effort = low|medium|high|xhigh|max
# /v1/responses: reasoning.effort = none|low|medium|high|xhigh|max
base_model = "anthropic/claude-opus-4-7"
name = "Claude Opus 4.7 (AU)"

reasoning_options = [
{ type = "toggle" },
{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] },
]

[cost]
input = 5.50
output = 27.50
cache_read = 0.55
cache_write = 6.875
Loading
Loading