chore: update model catalog from bot issues #1000
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -740,6 +740,7 @@ | |
| "output_cost_per_mil_tokens": 0.4, | ||
| "input_cache_read_cost_per_mil_tokens": 0.025, | ||
| "displayName": "GPT-4.1 nano", | ||
| "deprecation_date": "2026-10-23", | ||
| "max_input_tokens": 1047576, | ||
| "max_output_tokens": 32768, | ||
| "available_providers": [ | ||
|
|
@@ -815,6 +816,7 @@ | |
| "input_cost_per_mil_tokens": 10, | ||
| "output_cost_per_mil_tokens": 30, | ||
| "displayName": "GPT-4 Turbo", | ||
| "deprecation_date": "2026-10-23", | ||
| "max_input_tokens": 128000, | ||
| "max_output_tokens": 4096, | ||
| "available_providers": [ | ||
|
|
@@ -830,6 +832,7 @@ | |
| "output_cost_per_mil_tokens": 10, | ||
| "input_cache_read_cost_per_mil_tokens": 1.25, | ||
| "displayName": "GPT-4o", | ||
| "deprecation_date": "2026-10-23", | ||
| "max_input_tokens": 128000, | ||
| "max_output_tokens": 16384, | ||
| "available_providers": [ | ||
|
|
@@ -1346,6 +1349,7 @@ | |
| "input_cache_read_cost_per_mil_tokens": 0.275, | ||
| "displayName": "o4-mini", | ||
| "reasoning": true, | ||
| "deprecation_date": "2026-10-23", | ||
| "max_input_tokens": 200000, | ||
| "max_output_tokens": 100000, | ||
| "available_providers": [ | ||
|
|
@@ -1443,6 +1447,7 @@ | |
| "input_cache_read_cost_per_mil_tokens": 0.55, | ||
| "displayName": "o3 mini", | ||
| "reasoning": true, | ||
| "deprecation_date": "2026-10-23", | ||
| "max_input_tokens": 200000, | ||
| "max_output_tokens": 100000, | ||
| "available_providers": [ | ||
|
|
@@ -1542,6 +1547,7 @@ | |
| "input_cache_read_cost_per_mil_tokens": 7.5, | ||
| "displayName": "o1", | ||
| "reasoning": true, | ||
| "deprecation_date": "2026-10-23", | ||
| "max_input_tokens": 200000, | ||
| "max_output_tokens": 100000, | ||
| "available_providers": [ | ||
|
|
@@ -5888,6 +5894,34 @@ | |
| "cerebras" | ||
| ] | ||
| }, | ||
| "gpt-realtime-2.1": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 4, | ||
| "output_cost_per_mil_tokens": 24, | ||
| "input_cache_read_cost_per_mil_tokens": 0.4, | ||
| "displayName": "GPT Realtime 2.1", | ||
| "max_input_tokens": 128000, | ||
| "max_output_tokens": 32000, | ||
| "available_providers": [ | ||
| "openai", | ||
| "azure" | ||
| ] | ||
| }, | ||
| "gpt-realtime-2.1-mini": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 0.6, | ||
| "output_cost_per_mil_tokens": 2.4, | ||
| "input_cache_read_cost_per_mil_tokens": 0.06, | ||
| "displayName": "GPT Realtime 2.1 mini", | ||
| "max_input_tokens": 128000, | ||
| "max_output_tokens": 32000, | ||
| "available_providers": [ | ||
| "openai", | ||
| "azure" | ||
| ] | ||
| }, | ||
| "zai-glm-4.7": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
|
|
@@ -7439,6 +7473,116 @@ | |
| "max_input_tokens": 262144, | ||
| "max_output_tokens": 16384 | ||
| }, | ||
| "publishers/mistralai/models/mistral-medium-3": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 0.4, | ||
| "output_cost_per_mil_tokens": 2, | ||
| "displayName": "Mistral Medium 3 (Vertex)", | ||
| "locations": [ | ||
| "europe-west4", | ||
| "us-central1" | ||
| ], | ||
| "max_input_tokens": 131072, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "publishers/mistralai/models/mistral-small-2503": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 0.1, | ||
| "output_cost_per_mil_tokens": 0.3, | ||
| "displayName": "Mistral Small 3.1 (Vertex)", | ||
| "locations": [ | ||
| "europe-west4", | ||
| "us-central1" | ||
| ], | ||
| "max_input_tokens": 131072, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "publishers/mistralai/models/codestral-2": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 0.3, | ||
| "output_cost_per_mil_tokens": 0.9, | ||
| "displayName": "Codestral 2 (Vertex)", | ||
| "locations": [ | ||
| "europe-west4", | ||
| "us-central1" | ||
| ], | ||
| "max_input_tokens": 262144, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "publishers/openai/models/gpt-oss-120b-maas": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 0.15, | ||
| "output_cost_per_mil_tokens": 0.6, | ||
| "displayName": "GPT-OSS 120B (Vertex)", | ||
| "reasoning": true, | ||
| "locations": [ | ||
| "us-central1" | ||
| ], | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 32768, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "publishers/openai/models/gpt-oss-20b-maas": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "input_cost_per_mil_tokens": 0.075, | ||
| "output_cost_per_mil_tokens": 0.3, | ||
| "displayName": "GPT-OSS 20B (Vertex)", | ||
| "reasoning": true, | ||
| "locations": [ | ||
| "us-central1" | ||
| ], | ||
| "max_input_tokens": 131072, | ||
| "max_output_tokens": 32768, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "publishers/xai/models/grok-4.3": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "multimodal": true, | ||
| "input_cost_per_mil_tokens": 1.25, | ||
| "output_cost_per_mil_tokens": 2.5, | ||
| "input_cache_read_cost_per_mil_tokens": 0.2, | ||
| "displayName": "Grok 4.3 (Vertex)", | ||
| "reasoning": true, | ||
| "locations": [ | ||
| "global" | ||
| ], | ||
| "max_input_tokens": 1000000, | ||
| "max_output_tokens": 1000000, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "publishers/xai/models/grok-4.20-non-reasoning": { | ||
| "format": "openai", | ||
| "flavor": "chat", | ||
| "multimodal": true, | ||
| "input_cost_per_mil_tokens": 1.25, | ||
| "output_cost_per_mil_tokens": 2.5, | ||
| "displayName": "Grok 4.20 Non-Reasoning (Vertex)", | ||
| "locations": [ | ||
| "global" | ||
| ], | ||
| "max_input_tokens": 1000000, | ||
| "available_providers": [ | ||
| "vertex" | ||
| ] | ||
| }, | ||
| "text-davinci-003": { | ||
| "format": "openai", | ||
| "flavor": "completion", | ||
|
|
@@ -11619,7 +11763,7 @@ | |
| "multimodal": true, | ||
| "input_cost_per_mil_tokens": 2, | ||
| "output_cost_per_mil_tokens": 6, | ||
| "input_cache_read_cost_per_mil_tokens": 0.3, | ||
| "displayName": "Grok 4.5", | ||
| "reasoning": true, | ||
| "max_input_tokens": 500000, | ||
|
|
@@ -11634,7 +11778,7 @@ | |
| "multimodal": true, | ||
| "input_cost_per_mil_tokens": 2, | ||
| "output_cost_per_mil_tokens": 6, | ||
| "input_cache_read_cost_per_mil_tokens": 0.3, | ||
| "displayName": "Grok 4.5 (Latest)", | ||
| "reasoning": true, | ||
| "parent": "grok-4.5", | ||
|
|
@@ -12395,7 +12539,8 @@ | |
| "reasoning": true, | ||
| "max_input_tokens": 1048576, | ||
| "available_providers": [ | ||
| "baseten", | ||
| "together" | ||
|
There was a problem hiding this comment.
For Together requests the proxy forwards Useful? React with 👍 / 👎. |
||
| ] | ||
| } | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
When these new OpenAI/xAI Vertex models are selected,
packages/proxy/src/proxy.ts:2202-2225only sendspublishers/metaandpublishers/qwenthrough the OpenAI-compatible/endpoints/openapi/chat/completionspath; these entries therefore fall into the rawPredict branch. Google/xAI docs for Grok use the OpenAI-compatible endpoint andxai/...model IDs, and Google's gpt-oss MaaS examples likewise use the OpenAI-compatible API withopenai/...IDs, so these newly advertised Vertex options will return not-found/unsupported until the routing and model-id rewrite are extended. Sources: https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/grok/capabilities/function-calling, https://discuss.google.dev/t/now-ga-openais-gpt-oss-qwen3-models-on-vertex-ai-as-open-model-apis/253945Useful? React with 👍 / 👎.