Skip to content

Update model sizes for github-copilot #810

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
nulladdict wants to merge 1 commit into from
Closed

Update model sizes for github-copilot #810

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
5 changes: 3 additions & 2 deletions providers/github-copilot/models/claude-haiku-4.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,9 @@ input = 0
output = 0

[limit]
context = 128_000
output = 16_000
context = 200_000
Copy link
Copy Markdown
Collaborator

@rekram1-node rekram1-node Feb 10, 2026

Choose a reason for hiding this comment

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

where is this 200k coming from?

In their models api I see:

          "max_context_window_tokens": 144000,
          "max_non_streaming_output_tokens": 16000,
          "max_output_tokens": 32000,
          "max_prompt_tokens": 128000,

So I would expect:

context: 144k
input: 128k
output: 32k

Copy link
Copy Markdown
Collaborator

@rekram1-node rekram1-node Feb 10, 2026

Choose a reason for hiding this comment

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

Same goes for a lot of the other values in here, I can update them all myself but im wondering the logic here maybe im missing soemthing

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026

Choose a reason for hiding this comment

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

I trusted the json in the comment above. If you have a more trustworthy source or a way to update these values programmatically I think it’s better to use it instead

It would also help with opus 4.6 fast and gpt 5.3 codex (even though the rollout is paused)

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026

Choose a reason for hiding this comment

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

Nevermind the gpt 5.3 part, it’s now generally available:
https://github.blog/changelog/2026-02-09-gpt-5-3-codex-is-now-generally-available-for-github-copilot/

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026 •
edited
Loading

Choose a reason for hiding this comment

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

I took a peak inside the vscode extension and it doesn't seem to have context size only "maxInputTokens" and "maxOutputTokens" fields. I can post the json of models available to my account if needed but if you have a more reliable way you should use it instead

Copy link
Copy Markdown
Collaborator

@rekram1-node rekram1-node Feb 10, 2026

Choose a reason for hiding this comment

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

Ex:

 {
      "capabilities": {
        "family": "claude-haiku-4.5",
        "limits": {
          "max_context_window_tokens": 144000,
          "max_non_streaming_output_tokens": 16000,
          "max_output_tokens": 32000,
          "max_prompt_tokens": 128000,
          "vision": {
            "max_prompt_image_size": 3145728,
            "max_prompt_images": 5,
            "supported_media_types": [
              "image/jpeg",
              "image/png",
              "image/webp"
            ]
          }
        },
        "object": "model_capabilities",
        "supports": {
          "max_thinking_budget": 32000,
          "min_thinking_budget": 1024,
          "parallel_tool_calls": true,
          "streaming": true,
          "tool_calls": true,
          "vision": true
        },
        "tokenizer": "o200k_base",
        "type": "chat"
      },
      "id": "claude-haiku-4.5",
      "model_picker_category": "versatile",
      "model_picker_enabled": true,
      "name": "Claude Haiku 4.5",
      "object": "model",
      "policy": {
        "state": "enabled",
        "terms": "Enable access to the latest Claude Haiku 4.5 model from Anthropic. [Learn more about how GitHub Copilot serves Claude Haiku 4.5](https://gh.io/copilot-anthropic)."
      },
      "preview": false,
      "supported_endpoints": [
        "/chat/completions"
      ],
      "vendor": "Anthropic",
      "version": "claude-haiku-4.5"
    },

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026

Choose a reason for hiding this comment

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

Here's what i have for haiku 4.5 inside vscode:

{
        "metadata": {
            "extension": {
                "value": "GitHub.copilot-chat",
                "_lower": "github.copilot-chat"
            },
            "id": "claude-haiku-4.5",
            "vendor": "copilot",
            "name": "Claude Haiku 4.5",
            "family": "claude-haiku-4.5",
            "tooltip": "Fastest and most compact Claude model. Ideal for quick responses and simple tasks. Rate is counted at 0.33x.",
            "version": "claude-haiku-4.5",
            "multiplier": "0.33x",
            "maxInputTokens": 127805,
            "maxOutputTokens": 32000,
            "auth": {
                "providerLabel": "GitHub Copilot Chat",
                "accountLabel": "nulladdict"
            },
            "isDefaultForLocation": {
                "panel": false,
                "terminal": false,
                "notebook": false,
                "editor": false
            },
            "isUserSelectable": true,
            "modelPickerCategory": {
                "label": "Premium Models",
                "order": 1
            },
            "capabilities": {
                "vision": true,
                "toolCalling": true,
                "agentMode": true
            }
        },
        "identifier": "copilot/claude-haiku-4.5"
    }

Input tokens seems kinda weird to me (it matches the ui, but still)
Screenshot 2026-02-10 at 21 58 30

It seems close enough so I think you should just use whatever the api gives you

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026

Choose a reason for hiding this comment

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

Meanwhile copilot-cli shows something different

Screenshot 2026-02-10 at 22 04 39 Screenshot 2026-02-10 at 22 04 54

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026

Choose a reason for hiding this comment

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

I also took a look inside copilot cli and scraped models from there. Here's the haiku definition:

    {
      "billing": { "is_premium": true, "multiplier": 0.33 },
      "capabilities": {
        "family": "claude-haiku-4.5",
        "limits": {
          "max_context_window_tokens": 144000,
          "max_non_streaming_output_tokens": 16000,
          "max_output_tokens": 32000,
          "max_prompt_tokens": 128000,
          "vision": {
            "max_prompt_image_size": 3145728,
            "max_prompt_images": 5,
            "supported_media_types": ["image/jpeg", "image/png", "image/webp"]
          }
        },
        "object": "model_capabilities",
        "supports": {
          "max_thinking_budget": 32000,
          "min_thinking_budget": 1024,
          "parallel_tool_calls": true,
          "streaming": true,
          "tool_calls": true,
          "vision": true
        },
        "tokenizer": "o200k_base",
        "type": "chat"
      },
      "id": "claude-haiku-4.5",
      "is_chat_default": false,
      "is_chat_fallback": false,
      "model_picker_category": "versatile",
      "model_picker_enabled": true,
      "name": "Claude Haiku 4.5",
      "object": "model",
      "policy": {
        "state": "enabled",
        "terms": "Enable access to the latest Claude Haiku 4.5 model from Anthropic. [Learn more about how GitHub Copilot serves Claude Haiku 4.5](https://gh.io/copilot-anthropic)."
      },
      "preview": false,
      "supported_endpoints": ["/chat/completions"],
      "vendor": "Anthropic",
      "version": "claude-haiku-4.5"
    },

So I think the api can be trusted over whatever vscode is doing

Copy link
Copy Markdown
Author

@nulladdict nulladdict Feb 10, 2026

Choose a reason for hiding this comment

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

Here are so more interesting findings:

{
        "family": "claude-opus-4.6-fast",
        "limits": {
          "max_context_window_tokens": 200000,
          "max_non_streaming_output_tokens": 16000,
          "max_output_tokens": 64000,
          "max_prompt_tokens": 128000,
          "vision": {
            "max_prompt_image_size": 3145728,
            "max_prompt_images": 1,
            "supported_media_types": ["image/jpeg", "image/png", "image/webp"]
          }
        },
}
{
        "family": "claude-opus-4.6",
        "limits": {
          "max_context_window_tokens": 144000,
          "max_non_streaming_output_tokens": 16000,
          "max_output_tokens": 64000,
          "max_prompt_tokens": 128000,
          "vision": {
            "max_prompt_image_size": 3145728,
            "max_prompt_images": 1,
            "supported_media_types": ["image/jpeg", "image/png", "image/webp"]
          }
        },
}

So regular opus 4.6 has 144k context window and fast has the full 200k

input = 128_000
output = 32_000

[modalities]
input = ["text", "image"]
Expand Down
5 changes: 3 additions & 2 deletions providers/github-copilot/models/claude-opus-4.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,9 @@ input = 0
output = 0

[limit]
context = 128_000
output = 16_000
context = 200_000
input = 128_000
output = 32_000

[modalities]
input = ["text", "image"]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/claude-opus-4.6.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ input = 0
output = 0

[limit]
context = 128_000
context = 200_000
input = 128_000
output = 64_000

[modalities]
Expand Down
1 change: 1 addition & 0 deletions providers/github-copilot/models/claude-opus-41.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ output = 0

[limit]
context = 80_000
input = 80_000
output = 16_000

[modalities]
Expand Down
5 changes: 3 additions & 2 deletions providers/github-copilot/models/claude-sonnet-4.5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,9 @@ input = 0
output = 0

[limit]
context = 128_000
output = 16_000
context = 200_000
input = 128_000
output = 32_000

[modalities]
input = ["text", "image"]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/claude-sonnet-4.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ input = 0
output = 0

[limit]
context = 128_000
context = 216_000
input = 128_000
output = 16_000

[modalities]
Expand Down
1 change: 1 addition & 0 deletions providers/github-copilot/models/gemini-2.5-pro.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ output = 0

[limit]
context = 128_000
input = 109_000
output = 64_000

[modalities]
Expand Down
1 change: 1 addition & 0 deletions providers/github-copilot/models/gemini-3-flash-preview.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ output = 0

[limit]
context = 128_000
input = 109_000
output = 64_000

[modalities]
Expand Down
1 change: 1 addition & 0 deletions providers/github-copilot/models/gemini-3-pro-preview.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ output = 0

[limit]
context = 128_000
input = 109_000
output = 64_000

[modalities]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/gpt-4.1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,8 @@ output = 0

[limit]
context = 128_000
output = 16_384
input = 111_000
output = 16_000

[modalities]
input = ["text", "image"]
Expand Down
5 changes: 3 additions & 2 deletions providers/github-copilot/models/gpt-4o.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,9 @@ input = 0
output = 0

[limit]
context = 64_000
output = 16_384
context = 128_000
input = 64_000
output = 4_000

[modalities]
input = ["text", "image"]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/gpt-5-mini.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ input = 0
output = 0

[limit]
context = 128_000
context = 264_000
input = 128_000
output = 64_000

[modalities]
Expand Down
7 changes: 4 additions & 3 deletions providers/github-copilot/models/gpt-5.1-codex-max.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,10 @@ open_weights = false
input = 0
output = 0

[limit]
context = 128_000
output = 128_000
[limit]
context = 400_000
input = 128_000
output = 128_000

[modalities]
input = ["text", "image"]
Expand Down
7 changes: 4 additions & 3 deletions providers/github-copilot/models/gpt-5.1-codex-mini.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,10 @@ open_weights = false
input = 0
output = 0

[limit]
context = 128_000
output = 100_000
[limit]
context = 400_000
input = 128_000
output = 128_000

[modalities]
input = ["text", "image"]
Expand Down
7 changes: 4 additions & 3 deletions providers/github-copilot/models/gpt-5.1-codex.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,10 @@ open_weights = false
input = 0
output = 0

[limit]
context = 128_000
output = 128_000
[limit]
context = 400_000
input = 128_000
output = 128_000

[modalities]
input = ["text", "image"]
Expand Down
7 changes: 4 additions & 3 deletions providers/github-copilot/models/gpt-5.1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,10 @@ open_weights = false
input = 0
output = 0

[limit]
context = 128_000
output = 128_000
[limit]
context = 264_000
input = 128_000
output = 64_000

[modalities]
input = ["text", "image"]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/gpt-5.2-codex.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ input = 0
output = 0

[limit]
context = 272_000
context = 400_000
input = 272_000
output = 128_000

[modalities]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/gpt-5.2.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ input = 0
output = 0

[limit]
context = 128_000
context = 264_000
input = 128_000
output = 64_000

[modalities]
Expand Down
3 changes: 2 additions & 1 deletion providers/github-copilot/models/gpt-5.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,8 @@ input = 0
output = 0

[limit]
context = 128_000
context = 400_000
input = 128_000
output = 128_000

[modalities]
Expand Down
1 change: 1 addition & 0 deletions providers/github-copilot/models/grok-code-fast-1.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ output = 0

[limit]
context = 128_000
input = 109_000
output = 64_000

[modalities]
Expand Down