Skip to content

feat: add Gemini 3.7 Flash - #4632

Merged
rekram1-node merged 2 commits into
devfrom
add/gemini-3-7-flash-aiden
Aug 13, 2026
Merged

feat: add Gemini 3.7 Flash#4632
rekram1-node merged 2 commits into
devfrom
add/gemini-3-7-flash-aiden

Conversation

@opencode-agent

@opencode-agent opencode-agent Bot commented Aug 13, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Summary

  • add complete provider-agnostic metadata for Gemini 3.7 Flash, including multimodal limits, March 2026 knowledge cutoff, and selected first-party benchmarks
  • add gemini-3.7-flash to the Google Gemini API and Vertex AI providers
  • record the model's narrower thinking controls: low, medium, and high; unlike Gemini 3.6 Flash, Gemini 3.7 Flash rejects minimal
  • use the currently charged introductory pricing through December 31, 2026

Validation

  • bun validate

Evidence

Requested by: @rekram1-node (Aiden Cline via Slack)

@github-actions

github-actions Bot commented Aug 13, 2026

Copy link
Copy Markdown
Contributor

Action items

  • [high] [possible mistake] providers/google/models/gemini-3.7-flash.toml:12 - Check: Provider cost must reflect currently charged USD/MTok rates. Why: The PR body says these figures are standard pricing effective 2027-01-01, while introductory pricing runs through 2026-12-31; with today at 2026-08-13, publishing only the future band makes the catalog report wrong prices for both Google and Vertex until 2027. Action: Set cost on providers/google/models/gemini-3.7-flash.toml and providers/google-vertex/models/gemini-3.7-flash.toml to the current introductory rates (cite the pricing page for those numbers); switch to standard rates when they actually apply.

@github-actions

github-actions Bot commented Aug 13, 2026

Copy link
Copy Markdown
Contributor

No actionable findings.

@github-actions github-actions Bot added the reviewer: ready Automated review found no actionable items label Aug 13, 2026
@rekram1-node
rekram1-node merged commit 0012011 into dev Aug 13, 2026
2 checks passed
@rekram1-node
rekram1-node deleted the add/gemini-3-7-flash-aiden branch August 13, 2026 17:26
Vlaaaaaaad added a commit to Vlaaaaaaad/zed that referenced this pull request Aug 14, 2026
@Vlaaaaaaad
OpenCode Zen: add Gemini 3.7 Flash
3aac97f 
As per anomalyco/models.dev#4632 and anomalyco/models.dev@b1810e3 and anomalyco/opencode#42390 and anomalyco/opencode#42393
@Vlaaaaaaad Vlaaaaaaad mentioned this pull request Aug 14, 2026
Merged
5 tasks
@mtgto mtgto mentioned this pull request Aug 18, 2026
Open
@zed-zippy zed-zippy Bot mentioned this pull request Aug 19, 2026
Merged
5 tasks
pixel365 pushed a commit to pixel365/zed that referenced this pull request Aug 19, 2026
@Vlaaaaaaad @dinocosta
agent: OpenCode model updates (+6 Go, +7/-1 Zen, removed Free) (zed-i…
99f4c21 
…ndustries#61199)

Closes zed-industries#62559
Related discussion:
zed-industries#61160

# Objective

Adding newly-released OpenCode models. Removing OpenCode Free models
completely.

## Solution

> [!TIP]
> This pull request is **best reviewed commit-by-commit**!

**OpenCode Go**:
- added **Kimi K3** as per
[[1]](https://github.com/anomalyco/models.dev/blob/89183a9646cf2fa30300f7203a5b4f2ca69d1374/providers/opencode-go/models/kimi-k3.toml)
and
[[2]](https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k3.toml).
Currently, the only supported reasoning level available is `Max` which
was validated both with Models.dev data and OpenCode CLI.
- added **Grok 4.5** as per
[[1]](https://github.com/anomalyco/models.dev/blob/89183a9646cf2fa30300f7203a5b4f2ca69d1374/providers/opencode-go/models/grok-4.5.toml)
and
[[2]](https://github.com/anomalyco/models.dev/blob/89183a9646cf2fa30300f7203a5b4f2ca69d1374/models/xai/grok-4.5.toml)
- added **Tencent Hy3** as per
[[1]](anomalyco/models.dev@b013d94)
and
[[2]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/models/tencent/hy3.toml)
- added **GPT 5.6 Luna** as per
[[1]](anomalyco/opencode#39812) and
[[2]](https://github.com/anomalyco/models.dev/blob/dev/providers/opencode-go/models/gpt-5.6-luna.toml)
- added **Qwen 3.8 Max** as per
[[1]](anomalyco/models.dev@403a7bd)
and
[[2]](anomalyco/opencode@e9e7472)
- added **GLM 5.3** as per
[[1]](https://github.com/anomalyco/models.dev/blob/3876740bf4f0290e014bc85340e1dba34f0e99a7/models/zhipuai/glm-5.3.toml)
and
[[2]](anomalyco/models.dev@94a1629)
and [[3]](anomalyco/opencode#42518)

**OpenCode Zen**:
- added **Gemini 3.5 Flash Lite** as per
[[1]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/providers/opencode/models/gemini-3.5-flash-lite.toml)
and
[[2]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/models/google/gemini-3.5-flash-lite.toml)
- added **Gemini 3.6 Flash** as per
[[1]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/providers/opencode/models/gemini-3.6-flash.toml)
and
[[2]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/models/google/gemini-3.6-flash.toml)
- added **Gemini 3.7 Flash** as per
[[1]](anomalyco/models.dev#4632) and
[[2]](anomalyco/models.dev@b1810e3)
and [[3]](anomalyco/opencode#42390) and
[[4]](anomalyco/opencode#42393)
- added **Claude Opus 5** as per
[[1]](anomalyco/models.dev@e3ae24c)
and
[[2]](anomalyco/models.dev@342b557)
- added **Kimi K3** as per
[[1]](anomalyco/opencode@a9bebd3)
and
[[2]](anomalyco/models.dev@38ccccc)
- added **Grok 4.6** as per
[[1]](anomalyco/models.dev@74789f5)
and
[[2]](anomalyco/opencode@d92d1e6)
and [[3]](anomalyco/models.dev#4575)
- added **Muse Spark 1.2** as per
[[1]](anomalyco/models.dev@fa03dca)
and
[[2]](https://github.com/anomalyco/models.dev/blob/3876740bf4f0290e014bc85340e1dba34f0e99a7/models/meta/muse-spark-1.2.toml)
and [[3]](anomalyco/opencode#42508)
- removed **Claude Opus 4.1** as per
[[1]](anomalyco/models.dev@6951484)

**OpenCode Free**: removed all the models and the whole concept of
"OpenCode Free" from Zed. As confirmed [by an Anomaly employee on the
OpenCode
Discord](https://discord.com/channels/1391832426048651334/1394667004979445931/1537530485356363899),
free models are now OpenCode-only since they got abused waaaaay too much
by people. Testing shows that even with an active OpenCode Go
subscription configured, I can't use Free models in Zed — both Big
Pickle and DeepSeek V4 Flash Free failed to reply to a _"hello"_ message
and instead returned a rate-limit error.
A full removal of OpenCode Free from Zed was implemented in
zed-industries@49acbf7
as there was no point in keeping a _"Show free models"_ toggle that
would confuse users.
Users that had `show_free_models` configures in Zed settings will get an
`Property show_free_models is not allowed.` notice. Users that had any
Custom OpenCode models with `"subscription": "free"` configured will get
an `Value is not accepted. Valid values: "zen", "go".` notice. Neither
are blocking errors.

## Testing

✅ Kimi K3 on OpenCode Go - happily confirmed Kimi K3 works by running a
simple "_rename this variable for me. add a function. delete the
function_" test.

✅ Grok 4.5 on OpenCode Go - bravely resisted the continuous and
relentless waves of disgust and confirmed Grok 4.5 works by running a
simple "_rename this variable for me. add a function. delete the
function_" test. I was a bit surprised this worked as I was located in
an EU country while testing this.

✅ Hy3 on OpenCode Go - happily confirmed Hy3 works by running a simple
"_rename this variable for me. add a function. delete the function_"
test.

✅ GPT 5.6 Luna on OpeCode Go - confirmed GPT 5.6 Luna works on OpenCode
Go by running a simple "_rename this variable for me. add a function.
delete the function_" test.

✅ Qwen 3.8 Max on OpeCode Go - confirmed Qwen 3.8 Max works on OpenCode
Go by running a simple "_rename this variable for me. add a function.
delete the function_" test.

✅ GLM 5.3 on OpeCode Go - confirmed GLM 5.3 works on OpenCode Go by
running a simple "_rename this variable for me. add a function. delete
the function_" test.


🤷 I did not test the new OpenCode Zen models (Claude Opus 5, Gemini 3.5
Flash Lite, Gemini 3.6 Flash, Kimi K3, Grok 4.6, Gemini 3.7 Flash, and
Muse Spark 1.2) as I don't have a Zen subscription and I am stubbornly
refusing to get one.

✅ Confirmed removal of OpenCode Free does not impact the rest of the
OpenCode. Confirmed that any Free-related settings generate notices and
not errors. Confirmed the OpenCode tab in Setting looks good.

## Self-Review Checklist:

- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards
([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and
[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable

## Showcase

<details>
<summary>Screenshots of the OpenCode Free deprecation warnings</summary>

**Notice shown in the corner of Zed**:
<img width="345" height="90" alt="Notice banner shown in Zed"
src="https://github.com/user-attachments/assets/3e65ba96-582c-424e-9335-1b43d6c632a8"
/>

**Notice shown in Settings -> LLM Providers -> OpenCode**:
<img width="421" height="323" alt="Settings screen showing unexpected
values"
src="https://github.com/user-attachments/assets/a5eb6005-8576-4311-8b23-9c5baf314d8d"
/>

**Notice shown in `settings.json`**:
<img width="569" height="231" alt="Notices shown in settings.json"
src="https://github.com/user-attachments/assets/475375a1-268c-4420-8ef7-a896548e4498"
/>

</details>

---

Release Notes:

- Removed OpenCode Free models from Zed's built-in OpenCode provider
because they are only available through OpenCode surfaces, such as its
external agent through ACP.
- Added Kimi K3, Grok 4.5, Hy3, GPT 5.6 Luna, Qwen 3.8 Max, and GLM 5.3
to OpenCode Go.
- Added Claude Opus 5, Gemini 3.5 Flash Lite, Gemini 3.6 Flash, Gemini
3.7 Flash, Kimi K3, Grok 4.6, and Muse Spark 1.2 to OpenCode Zen.
- Removed the deprecated Claude Opus 4.1 model from OpenCode Zen.

----

> [!TIP]
> This pull request is **best reviewed commit-by-commit**!

---------

Co-authored-by: dino <dinojoaocosta@gmail.com>
zed-zippy Bot added a commit to zed-industries/zed that referenced this pull request Aug 19, 2026
@zed-zippy @Vlaaaaaaad @dinocosta
agent: OpenCode model updates (+6 Go, +7/-1 Zen, removed Free) (#61199)…
d5953f9 
… (cherry-pick to preview) (#62869)

Cherry-pick of #61199 to preview

----
Closes #62559
Related discussion:
https://github.com/zed-industries/zed/discussions/61160

# Objective

Adding newly-released OpenCode models. Removing OpenCode Free models
completely.

## Solution

> [!TIP]
> This pull request is **best reviewed commit-by-commit**!

**OpenCode Go**:
- added **Kimi K3** as per

[[1]](https://github.com/anomalyco/models.dev/blob/89183a9646cf2fa30300f7203a5b4f2ca69d1374/providers/opencode-go/models/kimi-k3.toml)
and

[[2]](https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k3.toml).
Currently, the only supported reasoning level available is `Max` which
was validated both with Models.dev data and OpenCode CLI.
- added **Grok 4.5** as per

[[1]](https://github.com/anomalyco/models.dev/blob/89183a9646cf2fa30300f7203a5b4f2ca69d1374/providers/opencode-go/models/grok-4.5.toml)
and

[[2]](https://github.com/anomalyco/models.dev/blob/89183a9646cf2fa30300f7203a5b4f2ca69d1374/models/xai/grok-4.5.toml)
- added **Tencent Hy3** as per

[[1]](anomalyco/models.dev@b013d94)
and

[[2]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/models/tencent/hy3.toml)
- added **GPT 5.6 Luna** as per
[[1]](anomalyco/opencode#39812) and

[[2]](https://github.com/anomalyco/models.dev/blob/dev/providers/opencode-go/models/gpt-5.6-luna.toml)
- added **Qwen 3.8 Max** as per

[[1]](anomalyco/models.dev@403a7bd)
and

[[2]](anomalyco/opencode@e9e7472)
- added **GLM 5.3** as per

[[1]](https://github.com/anomalyco/models.dev/blob/3876740bf4f0290e014bc85340e1dba34f0e99a7/models/zhipuai/glm-5.3.toml)
and

[[2]](anomalyco/models.dev@94a1629)
and [[3]](anomalyco/opencode#42518)

**OpenCode Zen**:
- added **Gemini 3.5 Flash Lite** as per

[[1]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/providers/opencode/models/gemini-3.5-flash-lite.toml)
and

[[2]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/models/google/gemini-3.5-flash-lite.toml)
- added **Gemini 3.6 Flash** as per

[[1]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/providers/opencode/models/gemini-3.6-flash.toml)
and

[[2]](https://github.com/anomalyco/models.dev/blob/f63b5ce78dd78869faa0612353b1055f6608dc97/models/google/gemini-3.6-flash.toml)
- added **Gemini 3.7 Flash** as per
[[1]](anomalyco/models.dev#4632) and

[[2]](anomalyco/models.dev@b1810e3)
and [[3]](anomalyco/opencode#42390) and
[[4]](anomalyco/opencode#42393)
- added **Claude Opus 5** as per

[[1]](anomalyco/models.dev@e3ae24c)
and

[[2]](anomalyco/models.dev@342b557)
- added **Kimi K3** as per

[[1]](anomalyco/opencode@a9bebd3)
and

[[2]](anomalyco/models.dev@38ccccc)
- added **Grok 4.6** as per

[[1]](anomalyco/models.dev@74789f5)
and

[[2]](anomalyco/opencode@d92d1e6)
and [[3]](anomalyco/models.dev#4575)
- added **Muse Spark 1.2** as per

[[1]](anomalyco/models.dev@fa03dca)
and

[[2]](https://github.com/anomalyco/models.dev/blob/3876740bf4f0290e014bc85340e1dba34f0e99a7/models/meta/muse-spark-1.2.toml)
and [[3]](anomalyco/opencode#42508)
- removed **Claude Opus 4.1** as per

[[1]](anomalyco/models.dev@6951484)

**OpenCode Free**: removed all the models and the whole concept of
"OpenCode Free" from Zed. As confirmed [by an Anomaly employee on the
OpenCode

Discord](https://discord.com/channels/1391832426048651334/1394667004979445931/1537530485356363899),
free models are now OpenCode-only since they got abused waaaaay too much
by people. Testing shows that even with an active OpenCode Go
subscription configured, I can't use Free models in Zed — both Big
Pickle and DeepSeek V4 Flash Free failed to reply to a _"hello"_ message
and instead returned a rate-limit error.
A full removal of OpenCode Free from Zed was implemented in

49acbf7
as there was no point in keeping a _"Show free models"_ toggle that
would confuse users.
Users that had `show_free_models` configures in Zed settings will get an
`Property show_free_models is not allowed.` notice. Users that had any
Custom OpenCode models with `"subscription": "free"` configured will get
an `Value is not accepted. Valid values: "zen", "go".` notice. Neither
are blocking errors.

## Testing

✅ Kimi K3 on OpenCode Go - happily confirmed Kimi K3 works by running a
simple "_rename this variable for me. add a function. delete the
function_" test.

✅ Grok 4.5 on OpenCode Go - bravely resisted the continuous and
relentless waves of disgust and confirmed Grok 4.5 works by running a
simple "_rename this variable for me. add a function. delete the
function_" test. I was a bit surprised this worked as I was located in
an EU country while testing this.

✅ Hy3 on OpenCode Go - happily confirmed Hy3 works by running a simple
"_rename this variable for me. add a function. delete the function_"
test.

✅ GPT 5.6 Luna on OpeCode Go - confirmed GPT 5.6 Luna works on OpenCode
Go by running a simple "_rename this variable for me. add a function.
delete the function_" test.

✅ Qwen 3.8 Max on OpeCode Go - confirmed Qwen 3.8 Max works on OpenCode
Go by running a simple "_rename this variable for me. add a function.
delete the function_" test.

✅ GLM 5.3 on OpeCode Go - confirmed GLM 5.3 works on OpenCode Go by
running a simple "_rename this variable for me. add a function. delete
the function_" test.


🤷 I did not test the new OpenCode Zen models (Claude Opus 5, Gemini 3.5
Flash Lite, Gemini 3.6 Flash, Kimi K3, Grok 4.6, Gemini 3.7 Flash, and
Muse Spark 1.2) as I don't have a Zen subscription and I am stubbornly
refusing to get one.

✅ Confirmed removal of OpenCode Free does not impact the rest of the
OpenCode. Confirmed that any Free-related settings generate notices and
not errors. Confirmed the OpenCode tab in Setting looks good.

## Self-Review Checklist:

- [x] I've reviewed my own diff for quality, security, and reliability
- [x] Unsafe blocks (if any) have justifying comments
- [x] The content adheres to Zed's UI standards

([UX/UI](https://github.com/zed-industries/zed/blob/main/CONTRIBUTING.md#uiux-checklist)
and

[icon](https://github.com/zed-industries/zed/blob/main/crates/icons/README.md)
guidelines)
- [ ] Tests cover the new/changed behavior
- [x] Performance impact has been considered and is acceptable

## Showcase

<details>
<summary>Screenshots of the OpenCode Free deprecation warnings</summary>

**Notice shown in the corner of Zed**:
<img width="345" height="90" alt="Notice banner shown in Zed"

src="https://github.com/user-attachments/assets/3e65ba96-582c-424e-9335-1b43d6c632a8"
/>

**Notice shown in Settings -> LLM Providers -> OpenCode**:
<img width="421" height="323" alt="Settings screen showing unexpected
values"

src="https://github.com/user-attachments/assets/a5eb6005-8576-4311-8b23-9c5baf314d8d"
/>

**Notice shown in `settings.json`**:
<img width="569" height="231" alt="Notices shown in settings.json"

src="https://github.com/user-attachments/assets/475375a1-268c-4420-8ef7-a896548e4498"
/>

</details>

---

Release Notes:

- Removed OpenCode Free models from Zed's built-in OpenCode provider
because they are only available through OpenCode surfaces, such as its
external agent through ACP.
- Added Kimi K3, Grok 4.5, Hy3, GPT 5.6 Luna, Qwen 3.8 Max, and GLM 5.3
to OpenCode Go.
- Added Claude Opus 5, Gemini 3.5 Flash Lite, Gemini 3.6 Flash, Gemini
3.7 Flash, Kimi K3, Grok 4.6, and Muse Spark 1.2 to OpenCode Zen.
- Removed the deprecated Claude Opus 4.1 model from OpenCode Zen.

----

> [!TIP]
> This pull request is **best reviewed commit-by-commit**!

---------

Co-authored-by: dino <dinojoaocosta@gmail.com>

Co-authored-by: Vlad Ionescu <Vlaaaaaaad@users.noreply.github.com>
Co-authored-by: dino <dinojoaocosta@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

@rekram1-node rekram1-node

Labels

reviewer: ready Automated review found no actionable items

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@rekram1-node