Skip to content

chore: update model catalog from bot issues #989

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

Open
github-actions wants to merge 1 commit into
base: main
Choose a base branch
from
Open

chore: update model catalog from bot issues #989

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
9 changes: 9 additions & 0 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1075,6 +1075,15 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"google.gemma-4-26b-a4b": ["bedrock"],
"google.gemma-4-e2b": ["bedrock"],
"accounts/fireworks/models/nemotron-3-ultra-nvfp4": ["fireworks"],
"databricks-gpt-5-5-pro": ["databricks"],
"databricks-gpt-5-4-mini": ["databricks"],
"databricks-gemini-3-5-flash": ["databricks"],
"claude-mythos-5": ["anthropic"],
"claude-mythos-preview": ["anthropic"],
"databricks-gpt-5-3-codex": ["databricks"],
"databricks-gemma-3-12b": ["databricks"],
"publishers/meta/models/llama-4-maverick-17b-128e-instruct-maas": ["vertex"],
"publishers/meta/models/llama-4-scout-17b-16e-instruct-maas": ["vertex"],
};

const modelEndpointAvailableModels = getAvailableModels();
Expand Down
126 changes: 123 additions & 3 deletions packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5918,9 +5918,9 @@
"openai/gpt-oss-120b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.1,
"output_cost_per_mil_tokens": 0.5,
"input_cache_read_cost_per_mil_tokens": 0.1,
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.6,
"input_cache_read_cost_per_mil_tokens": 0.075,
"displayName": "OpenAI GPT-OSS (120B)",
"reasoning": true,
"max_input_tokens": 131072,
Expand Down Expand Up @@ -7439,6 +7439,36 @@
"max_input_tokens": 262144,
"max_output_tokens": 16384
},
"publishers/meta/models/llama-4-maverick-17b-128e-instruct-maas": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.5,
"output_cost_per_mil_tokens": 1.5,
Comment on lines +7446 to +7447

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 18, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Use the current Vertex Llama pricing

These Vertex MaaS prices don't match Google's pricing for the same models: the official Agent Platform pricing page lists Llama 4 Maverick at $0.35 input / $1.15 output per MTok and Llama 4 Scout at $0.25 / $0.70, while this catalog sets Maverick to $0.50 / $1.50 and the Scout entry below to $0.20 / $0.60 (https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing). Since these new catalog entries are provider-specific to Vertex, requests to either model will be mispriced.

Useful? React with 👍 / 👎.

"displayName": "Llama 4 Maverick (17Bx128E) Instruct",
"locations": [
"us-east5"
],
"max_input_tokens": 1048576,

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 18, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Cap the Vertex Llama quota values

Google's current MaaS specs list llama-4-maverick-17b-128e-instruct-maas with max output 8,192 and context length 524,288, and Scout below with max output 8,192 and context length 1,310,720 (https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/llama/llama4-maverick and https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/llama/llama4-scout). Advertising 1,048,576 here and 10,485,760 for Scout, while omitting max_output_tokens, lets clients/UI that rely on this catalog accept prompts or output settings that Vertex will reject.

Useful? React with 👍 / 👎.

"available_providers": [
"vertex"
]
},
"publishers/meta/models/llama-4-scout-17b-16e-instruct-maas": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 0.2,
"output_cost_per_mil_tokens": 0.6,
"displayName": "Llama 4 Scout (17Bx16E) Instruct",
"locations": [
"us-east5"
],
"max_input_tokens": 10485760,
"available_providers": [
"vertex"
]
},
"text-davinci-003": {
"format": "openai",
"flavor": "completion",
Expand Down Expand Up @@ -8261,6 +8291,35 @@
"anthropic"
]
},
"claude-mythos-5": {
"format": "anthropic",
"flavor": "chat",
"multimodal": true,
"input_cost_per_mil_tokens": 10,
"output_cost_per_mil_tokens": 50,
"input_cache_read_cost_per_mil_tokens": 1,

@chatgpt-codex-connector chatgpt-codex-connector Bot Jul 18, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Add cache-write pricing for Mythos 5

When a claude-mythos-5 request creates prompt-cache entries, the proxy emits cache_write_input_tokens, but this new catalog entry only supplies cache-hit/read pricing. Anthropic's pricing table lists Mythos 5 5-minute cache writes at $12.50/MTok and 1-hour writes at $20/MTok, matching Fable 5 (https://platform.claude.com/docs/en/about-claude/pricing), so cache-creation usage for this newly routed model will be unc costed or undercharged unless the input_cache_write_* fields are added.

Useful? React with 👍 / 👎.

"displayName": "Claude Mythos 5",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"available_providers": [
"anthropic"
]
},
"claude-mythos-preview": {
"format": "anthropic",
"flavor": "chat",
"multimodal": true,
"displayName": "Claude Mythos Preview",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"available_providers": [
"anthropic"
]
},
"anthropic.claude-fable-5": {
"format": "anthropic",
"flavor": "chat",
Expand Down Expand Up @@ -10716,6 +10775,8 @@
"input_cost_per_mil_tokens": 0.15,
"output_cost_per_mil_tokens": 0.6,
"displayName": "Mistral Small (2603)",
"reasoning": true,
"reasoning_budget": true,
"parent": "mistral-small-latest",
"max_input_tokens": 262144,
"available_providers": [
Expand Down Expand Up @@ -11546,6 +11607,7 @@
"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 4.20 (Non-Reasoning)",
"max_input_tokens": 1000000,
"available_providers": [
Expand Down Expand Up @@ -12384,6 +12446,64 @@
"databricks"
]
},
"databricks-gpt-5-5-pro": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-5.5 Pro",
"reasoning": true,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"databricks-gpt-5-4-mini": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-5.4 mini",
"reasoning": true,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"databricks-gemini-3-5-flash": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "Gemini 3.5 Flash",
"reasoning": true,
"reasoning_budget": true,
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"available_providers": [
"databricks"
]
},
"databricks-gpt-5-3-codex": {
"format": "openai",
"flavor": "chat",
"multimodal": true,
"displayName": "GPT-5.3 Codex",
"reasoning": true,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"available_providers": [
"databricks"
]
},
"databricks-gemma-3-12b": {
"format": "openai",
"flavor": "chat",
"displayName": "Gemma 3 12B",
"max_input_tokens": 131072,
"available_providers": [
"databricks"
]
},
"thinkingmachines/inkling": {
"format": "openai",
"flavor": "chat",
Expand Down