Detailed changes
@@ -187,8 +187,8 @@ jobs:
- Fix
- Validation
- Potentially Related Issues (High/Medium/Low from LINKED_ISSUES.md)
- - Release Notes
- Reviewer Checklist
+ - Release Notes (final section; format as Release Notes:, then a blank line, then one bullet like - N/A)
Constraints:
- Do not merge or auto-approve.
@@ -251,9 +251,34 @@ jobs:
printf "Automated draft crash-fix pipeline output for %s.\n\nNo PR_BODY.md was generated by the agent; please review commit and linked artifacts manually.\n" "$CRASH_ID" > "$BODY_FILE"
fi
- if ! python3 -c 'import re, sys; body = open(sys.argv[1], encoding="utf-8").read(); raise SystemExit(0 if re.search(r"Release Notes:\r?\n\s+-", body) else 1)' "$BODY_FILE"; then
- printf '\nRelease Notes:\n\n- N/A\n' >> "$BODY_FILE"
- fi
+ python3 -c '
+ import re
+ import sys
+
+ path = sys.argv[1]
+ body = open(path, encoding="utf-8").read()
+ pattern = re.compile(r"(^|\n)Release Notes:\r?\n(?:\r?\n)*(?P<bullets>(?:\s*-\s+.*(?:\r?\n|$))+)", re.MULTILINE)
+ match = pattern.search(body)
+
+ if match:
+ bullets = [
+ re.sub(r"^\s*", "", bullet)
+ for bullet in re.findall(r"^\s*-\s+.*$", match.group("bullets"), re.MULTILINE)
+ ]
+ if not bullets:
+ bullets = ["- N/A"]
+ section = "Release Notes:\n\n" + "\n".join(bullets)
+ body_without_release_notes = (body[: match.start()] + body[match.end() :]).rstrip()
+ if body_without_release_notes:
+ normalized_body = f"{body_without_release_notes}\n\n{section}\n"
+ else:
+ normalized_body = f"{section}\n"
+ else:
+ normalized_body = body.rstrip() + "\n\nRelease Notes:\n\n- N/A\n"
+
+ with open(path, "w", encoding="utf-8") as file:
+ file.write(normalized_body)
+ ' "$BODY_FILE"
EXISTING_PR="$(gh pr list --head "$BRANCH" --json number --jq '.[0].number')"
if [ -n "$EXISTING_PR" ]; then
@@ -145,9 +145,17 @@ When an agent opens or updates a pull request, it must:
- Avoid conventional commit prefixes in PR titles (`fix:`, `feat:`, `docs:`, etc.).
- Avoid trailing punctuation in PR titles.
- Optionally prefix the title with a crate name when one crate is the clear scope (for example, `git_ui: Add history view`).
-- Include a `Release Notes:` section in the PR body with one bullet:
+- Include a `Release Notes:` section as the final section in the PR body.
+- Use one bullet under `Release Notes:`:
- `- Added ...`, `- Fixed ...`, or `- Improved ...` for user-facing changes, or
- - `- N/A` for non-user-facing changes.
+ - `- N/A` for docs-only and other non-user-facing changes.
+- Format release notes exactly with a blank line after the heading, for example:
+
+```
+Release Notes:
+
+- N/A
+```
# Crash Investigation
@@ -156,3 +156,14 @@ Zed doesn't index your project like IntelliJ does. You open a folder and start w
```
While some users might miss indexing, Zed's approach is actually better because it's faster.
```
+
+## Pull request hygiene
+
+- Include a `Release Notes:` section as the final section in the PR body.
+- For docs-only PRs, use exactly:
+
+```
+Release Notes:
+
+- N/A
+```
@@ -134,7 +134,7 @@ You can also do this at any time with an ongoing thread via the "Agent Options"
After you've configured your LLM providers—either via [a custom API key](./llm-providers.md) or through [Zed's hosted models](./models.md)—you can switch between their models by clicking on the model selector on the message editor or by using the {#kb agent::ToggleModelSelector} keybinding.
-> The same model can be offered via multiple providers - for example, Claude Sonnet 4 is available via Zed Pro, OpenRouter, Anthropic directly, and more.
+> The same model can be offered via multiple providers - for example, Claude Sonnet 4.5 is available via Zed Pro, OpenRouter, Anthropic directly, and more.
> Make sure you've selected the correct model **_provider_** for the model you'd like to use, delineated by the logo to the left of the model in the model selector.
### Favoriting Models
@@ -11,7 +11,7 @@ Settings for Zed's Agent Panel, including model selection, UI preferences, and t
### Default Model {#default-model}
-If you're using [Zed's hosted LLM service](./subscription.md), it sets `claude-sonnet-4` as the default model for agentic work (agent panel, inline assistant) and `gpt-5-nano` as the default "fast" model (thread summarization, git commit messages). If you're not subscribed or want to change these defaults, you can manually edit the `default_model` object in your settings:
+If you're using [Zed's hosted LLM service](./subscription.md), it sets `claude-sonnet-4-5` as the default model for agentic work (agent panel, inline assistant) and `gpt-5-nano` as the default "fast" model (thread summarization, git commit messages). If you're not subscribed or want to change these defaults, you can manually edit the `default_model` object in your settings:
```json [settings]
{
@@ -37,7 +37,7 @@ You can assign distinct and specific models for the following AI-powered feature
"agent": {
"default_model": {
"provider": "zed.dev",
- "model": "claude-sonnet-4"
+ "model": "claude-sonnet-4-5"
},
"inline_assistant_model": {
"provider": "anthropic",
@@ -68,7 +68,7 @@ Here's how you can customize your settings file ([how to edit](../configuring-ze
"agent": {
"default_model": {
"provider": "zed.dev",
- "model": "claude-sonnet-4"
+ "model": "claude-sonnet-4-5"
},
"inline_alternatives": [
{
@@ -85,14 +85,14 @@ When multiple models are configured, you'll see in the Inline Assistant UI butto
The models you specify here are always used in _addition_ to your [default model](#default-model).
For example, the following configuration will generate three outputs for every assist.
-One with Claude Sonnet 4 (the default model), another with GPT-5-mini, and another one with Gemini 2.5 Flash.
+One with Claude Sonnet 4.5 (the default model), another with GPT-5-mini, and another one with Gemini 3 Flash.
```json [settings]
{
"agent": {
"default_model": {
"provider": "zed.dev",
- "model": "claude-sonnet-4"
+ "model": "claude-sonnet-4-5"
},
"inline_alternatives": [
{
@@ -101,7 +101,7 @@ One with Claude Sonnet 4 (the default model), another with GPT-5-mini, and anoth
},
{
"provider": "zed.dev",
- "model": "gemini-2.5-flash"
+ "model": "gemini-3-flash"
}
]
}
@@ -128,7 +128,7 @@ Specify a custom temperature for a provider and/or model:
// To set parameters for a specific provider and model:
{
"provider": "zed.dev",
- "model": "claude-sonnet-4",
+ "model": "claude-sonnet-4-5",
"temperature": 1.0
}
]
@@ -54,7 +54,7 @@ Here's how you can customize your settings file ([how to edit](../configuring-ze
"agent": {
"default_model": {
"provider": "zed.dev",
- "model": "claude-sonnet-4"
+ "model": "claude-sonnet-4-5"
},
"inline_alternatives": [
{
@@ -71,14 +71,14 @@ When multiple models are configured, you'll see in the Inline Assistant UI butto
The models you specify here are always used in _addition_ to your [default model](#default-model).
For example, the following configuration will generate three outputs for every assist.
-One with Claude Sonnet 4 (the default model), another with GPT-5-mini, and another one with Gemini 2.5 Flash.
+One with Claude Sonnet 4.5 (the default model), another with GPT-5-mini, and another one with Gemini 3 Flash.
```json [settings]
{
"agent": {
"default_model": {
"provider": "zed.dev",
- "model": "claude-sonnet-4"
+ "model": "claude-sonnet-4-5"
},
"inline_alternatives": [
{
@@ -87,7 +87,7 @@ One with Claude Sonnet 4 (the default model), another with GPT-5-mini, and anoth
},
{
"provider": "zed.dev",
- "model": "gemini-2.5-flash"
+ "model": "gemini-3-flash"
}
]
}
@@ -304,8 +304,8 @@ Here is an example of a custom Google AI model you could add to your Zed setting
"google": {
"available_models": [
{
- "name": "gemini-2.5-flash-preview-05-20",
- "display_name": "Gemini 2.5 Flash (Thinking)",
+ "name": "gemini-3-flash-preview",
+ "display_name": "Gemini 3 Flash (Thinking)",
"max_tokens": 1000000,
"mode": {
"type": "thinking",
@@ -508,7 +508,7 @@ Zed will also use the `OPENAI_API_KEY` environment variable if it's defined.
#### Custom Models {#openai-custom-models}
-The Zed agent comes pre-configured to use the latest version for common models (GPT-5, GPT-5 mini, o4-mini, GPT-4.1, and others).
+The Zed agent comes pre-configured to use the latest version for common OpenAI models (GPT-5.2, GPT-5 mini, GPT-5.2 Codex, and others).
To use alternate models, perhaps a preview release, or if you wish to control the request parameters, you can do so by adding the following to your Zed settings file ([how to edit](../configuring-zed.md#settings-files)):
```json [settings]
@@ -517,20 +517,20 @@ To use alternate models, perhaps a preview release, or if you wish to control th
"openai": {
"available_models": [
{
- "name": "gpt-5",
- "display_name": "gpt-5 high",
+ "name": "gpt-5.2",
+ "display_name": "gpt-5.2 high",
"reasoning_effort": "high",
"max_tokens": 272000,
"max_completion_tokens": 20000
},
{
- "name": "gpt-4o-2024-08-06",
- "display_name": "GPT 4o Summer 2024",
- "max_tokens": 128000
+ "name": "gpt-5-nano",
+ "display_name": "GPT-5 Nano",
+ "max_tokens": 400000
},
{
- "name": "gpt-5-codex",
- "display_name": "GPT-5 Codex",
+ "name": "gpt-5.2-codex",
+ "display_name": "GPT-5.2 Codex",
"max_tokens": 128000,
"capabilities": {
"chat_completions": false
@@ -544,9 +544,9 @@ To use alternate models, perhaps a preview release, or if you wish to control th
You must provide the model's context window in the `max_tokens` parameter; this can be found in the [OpenAI model documentation](https://platform.openai.com/docs/models).
-OpenAI `o1` and `o`-class models should set `max_completion_tokens` as well to avoid incurring high reasoning token costs.
+For reasoning-focused models, set `max_completion_tokens` as well to avoid incurring high reasoning token costs.
-If a model does not support the `/chat/completions` endpoint (for example `gpt-5-codex`), disable it by setting `capabilities.chat_completions` to `false`. Zed will use the Responses endpoint instead.
+If a model does not support the `/chat/completions` endpoint (for example `gpt-5.2-codex`), disable it by setting `capabilities.chat_completions` to `false`. Zed will use the Responses endpoint instead.
Custom models will be listed in the model dropdown in the Agent Panel.
@@ -1,6 +1,6 @@
---
title: AI Models and Pricing - Zed
-description: AI models available via Zed Pro including Claude, GPT-5, Gemini, and Grok. Pricing, context windows, and tool call support.
+description: AI models available via Zed Pro including Claude, GPT-5.2, Gemini, and Grok. Pricing, context windows, and tool call support.
---
# Models
@@ -13,19 +13,15 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir
| | Anthropic | Output | $25.00 | $27.50 |
| | Anthropic | Input - Cache Write | $6.25 | $6.875 |
| | Anthropic | Input - Cache Read | $0.50 | $0.55 |
-| Claude Opus 4.1 | Anthropic | Input | $15.00 | $16.50 |
-| | Anthropic | Output | $75.00 | $82.50 |
-| | Anthropic | Input - Cache Write | $18.75 | $20.625 |
-| | Anthropic | Input - Cache Read | $1.50 | $1.65 |
+| Claude Opus 4.6 | Anthropic | Input | $5.00 | $5.50 |
+| | Anthropic | Output | $25.00 | $27.50 |
+| | Anthropic | Input - Cache Write | $6.25 | $6.875 |
+| | Anthropic | Input - Cache Read | $0.50 | $0.55 |
| Claude Sonnet 4.5 | Anthropic | Input | $3.00 | $3.30 |
| | Anthropic | Output | $15.00 | $16.50 |
| | Anthropic | Input - Cache Write | $3.75 | $4.125 |
| | Anthropic | Input - Cache Read | $0.30 | $0.33 |
-| Claude Sonnet 4 | Anthropic | Input | $3.00 | $3.30 |
-| | Anthropic | Output | $15.00 | $16.50 |
-| | Anthropic | Input - Cache Write | $3.75 | $4.125 |
-| | Anthropic | Input - Cache Read | $0.30 | $0.33 |
-| Claude Sonnet 3.7 | Anthropic | Input | $3.00 | $3.30 |
+| Claude Sonnet 4.6 | Anthropic | Input | $3.00 | $3.30 |
| | Anthropic | Output | $15.00 | $16.50 |
| | Anthropic | Input - Cache Write | $3.75 | $4.125 |
| | Anthropic | Input - Cache Read | $0.30 | $0.33 |
@@ -33,7 +29,10 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir
| | Anthropic | Output | $5.00 | $5.50 |
| | Anthropic | Input - Cache Write | $1.25 | $1.375 |
| | Anthropic | Input - Cache Read | $0.10 | $0.11 |
-| GPT-5 | OpenAI | Input | $1.25 | $1.375 |
+| GPT-5.2 | OpenAI | Input | $1.25 | $1.375 |
+| | OpenAI | Output | $10.00 | $11.00 |
+| | OpenAI | Cached Input | $0.125 | $0.1375 |
+| GPT-5.2 Codex | OpenAI | Input | $1.25 | $1.375 |
| | OpenAI | Output | $10.00 | $11.00 |
| | OpenAI | Cached Input | $0.125 | $0.1375 |
| GPT-5 mini | OpenAI | Input | $0.25 | $0.275 |
@@ -42,11 +41,9 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir
| GPT-5 nano | OpenAI | Input | $0.05 | $0.055 |
| | OpenAI | Output | $0.40 | $0.44 |
| | OpenAI | Cached Input | $0.005 | $0.0055 |
-| Gemini 3.0 Pro | Google | Input | $2.00 | $2.20 |
+| Gemini 3 Pro | Google | Input | $2.00 | $2.20 |
| | Google | Output | $12.00 | $13.20 |
-| Gemini 2.5 Pro | Google | Input | $1.25 | $1.375 |
-| | Google | Output | $10.00 | $11.00 |
-| Gemini 2.5 Flash | Google | Input | $0.30 | $0.33 |
+| Gemini 3 Flash | Google | Input | $0.30 | $0.33 |
| | Google | Output | $2.50 | $2.75 |
| Grok 4 | X.ai | Input | $3.00 | $3.30 |
| | X.ai | Output | $15.00 | $16.5 |
@@ -61,6 +58,17 @@ Zed's plans offer hosted versions of major LLMs with higher rate limits than dir
| | X.ai | Output | $1.50 | $1.65 |
| | X.ai | Cached Input | $0.02 | $0.022 |
+## Recent Model Retirements
+
+As of February 19, 2026, Zed Pro serves newer model versions in place of the retired models below:
+
+- Claude Opus 4.1 → Claude Opus 4.5 or Claude Opus 4.6
+- Claude Sonnet 4 → Claude Sonnet 4.5 or Claude Sonnet 4.6
+- Claude Sonnet 3.7 (retired Feb 19) → Claude Sonnet 4.5 or Claude Sonnet 4.6
+- GPT-5.1 and GPT-5 → GPT-5.2 or GPT-5.2 Codex
+- Gemini 2.5 Pro → Gemini 3 Pro
+- Gemini 2.5 Flash → Gemini 3 Flash
+
## Usage {#usage}
Any usage of a Zed-hosted model will be billed at the Zed Price (rightmost column above). See [Plans and Usage](./plans-and-usage.md) for details on Zed's plans and limits for use of hosted models.
@@ -74,18 +82,18 @@ A context window is the maximum span of text and code an LLM can consider at onc
| Model | Provider | Zed-Hosted Context Window |
| ----------------- | --------- | ------------------------- |
| Claude Opus 4.5 | Anthropic | 200k |
-| Claude Opus 4.1 | Anthropic | 200k |
-| Claude Sonnet 4 | Anthropic | 200k |
-| Claude Sonnet 3.7 | Anthropic | 200k |
+| Claude Opus 4.6 | Anthropic | 200k |
+| Claude Sonnet 4.5 | Anthropic | 200k |
+| Claude Sonnet 4.6 | Anthropic | 200k |
| Claude Haiku 4.5 | Anthropic | 200k |
-| GPT-5 | OpenAI | 400k |
+| GPT-5.2 | OpenAI | 400k |
+| GPT-5.2 Codex | OpenAI | 400k |
| GPT-5 mini | OpenAI | 400k |
| GPT-5 nano | OpenAI | 400k |
-| Gemini 2.5 Pro | Google | 200k |
-| Gemini 2.5 Flash | Google | 200k |
-| Gemini 3.0 Pro | Google | 200k |
+| Gemini 3 Pro | Google | 200k |
+| Gemini 3 Flash | Google | 200k |
-> Context window limits for hosted Sonnet 4 and Gemini 2.5 Pro/Flash may increase in future releases.
+> Context window limits for hosted Sonnet 4.5/4.6 and Gemini 3 Pro/Flash may increase in future releases.
Each Agent thread and text thread in Zed maintains its own context window.
The more prompts, attached files, and responses included in a session, the larger the context window grows.
@@ -301,6 +301,13 @@ EOF
echo "$MANIFEST" | jq -r '.suggestions[] | "- [PR #\(.pr)](\(.file)): \(.title)"' >> "$PR_BODY_FILE"
+cat >> "$PR_BODY_FILE" << 'EOF'
+
+Release Notes:
+
+- N/A
+EOF
+
git add docs/
git commit -m "docs: auto-apply preview release suggestions
@@ -156,6 +156,7 @@ Required workflow:
- Validation
- Potentially Related Issues (High/Medium/Low from LINKED_ISSUES.md)
- Reviewer Checklist
+ - Release Notes (final section, formatted as "Release Notes:", blank line, then one bullet like "- N/A" when not user-facing)
Constraints:
- Keep changes narrowly scoped to this crash.