Skip to content

fix: refresh Cerebras models #322

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
Joyce Er (joyceerhl) wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: refresh Cerebras models #322

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
da594fc
fix: refresh Cerebras models
joyceerhl Oct 13, 2025
78b9d3d
Fix JSON indentation
joyceerhl Oct 20, 2025
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
7 changes: 5 additions & 2 deletions packages/proxy/schema/index.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -304,7 +304,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"mistral-saba-24b": ["groq"],
"mixtral-8x7b-32768": ["groq"],
"gemma-7b-it": ["groq"],
"deepseek-r1-distill-llama-70b": ["groq", "cerebras"],
"deepseek-r1-distill-llama-70b": ["groq"],
"gemma2-9b-it": ["groq"],
"llama-3.3-70b-specdec": ["groq"],
"llama-3.2-90b-vision-preview": ["groq"],
Expand All @@ -330,9 +330,12 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = {
"wizardlm-2-8x22b": ["lepton"],
"nous-hermes-llama2-13b": ["lepton"],
"dolphin-mixtral-8x7b": ["lepton"],
"llama-4-scout-17b-16e-instruct": ["cerebras"],
"llama3.1-8b": ["cerebras"],
"llama3.3-70b": ["cerebras"],
"qwen-3-32b": ["cerebras"],
"qwen-3-235b-a22b-instruct-2507": ["cerebras"],
"qwen-3-235b-a22b-thinking-2507": ["cerebras"],
"qwen-3-coder-480b": ["cerebras"],
"accounts/fireworks/models/llama4-maverick-instruct-basic": ["fireworks"],
"accounts/fireworks/models/llama4-scout-instruct-basic": ["fireworks"],
"accounts/fireworks/models/llama-v3p3-70b-instruct": ["fireworks"],
Expand Down
36 changes: 35 additions & 1 deletion packages/proxy/schema/model_list.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1072,6 +1072,40 @@
"output_cost_per_mil_tokens": 0.69,
"displayName": "OpenAI GPT-OSS (120B)"
},
"qwen-3-32b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.4,
"output_cost_per_mil_tokens": 0.8,
"displayName": "Qwen 3 32B"
},
"qwen-3-235b-a22b-instruct-2507": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 1.2,
"displayName": "Qwen 3 235B Instruct",
"experimental": true,
"max_input_tokens": 131000,
"max_output_tokens": 8192
},
"qwen-3-235b-a22b-thinking-2507": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.6,
"output_cost_per_mil_tokens": 2.9,
"displayName": "Qwen 3 235B Thinking",
"experimental": true,
"reasoning": true
},
"qwen-3-coder-480b": {
"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 2,
"output_cost_per_mil_tokens": 2,
"displayName": "Qwen 3 Coder 480B",
"experimental": true
},
"meta/llama-2-70b-chat": {
"format": "openai",
"flavor": "chat",
Expand Down Expand Up @@ -2212,7 +2246,7 @@
"output_cost_per_mil_tokens": 0.1,
"displayName": "Llama 3.3 70B"
},
"llama3.1-8b": {
"llama3.1-8b": {
Copy link
Copy Markdown
Contributor

@graphite-app graphite-app bot Oct 13, 2025

Choose a reason for hiding this comment

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

There's an indentation issue in the JSON structure at line 2249. The "llama3.1-8b": { entry has an extra leading space that would cause a JSON parsing error. The line should be formatted without the leading space:

  "llama3.1-8b": {

This ensures proper JSON syntax and prevents runtime errors when parsing the model list.

Spotted by Graphite Agent

Fix in Graphite

Is this helpful? React 👍 or 👎 to let us know.

"format": "openai",
"flavor": "chat",
"input_cost_per_mil_tokens": 0.1,
Expand Down