mirror of
https://github.com/anomalyco/opencode.git
synced 2026-11-17 05:26:47 +03:00
docs(console): sync with current Console (#58279)
This commit is contained in:
@@ -5,6 +5,9 @@ description: "Read effective monthly budgets for every workspace member and mana
|
||||
|
||||
Read effective monthly budgets for every workspace member and manage each member's custom budget from an integration.
|
||||
|
||||
These `/api/v1/budgets` endpoints manage each member's monthly budget and keep working after migration to budget
|
||||
policies. Use **Controls** to manage shared, tag-based, or model-specific policies.
|
||||
|
||||
## Quick start
|
||||
|
||||
Create a [service account](/console/api#service-accounts) API key in the [Console](https://opencode.ai/console) with
|
||||
@@ -31,8 +34,12 @@ curl --fail-with-body \
|
||||
GET /api/v1/budgets/members
|
||||
```
|
||||
|
||||
The response includes every current member, ordered by email. A limit with source `custom` is a member override;
|
||||
source `default` is inherited from the workspace default. A null limit and source mean the member is unlimited.
|
||||
The response includes every current member, ordered by email. In policy-based workspaces, it reports each member's lowest
|
||||
monthly limit, including tag-based limits. Shared and model-specific budgets are not included.
|
||||
|
||||
Source `custom` means a single-member limit; `default` means a limit from a broader audience. A null limit and source
|
||||
mean the member has no individual limit; other policies can still cap spend. Before migration, `custom`
|
||||
means a member override and `default` means the workspace default.
|
||||
|
||||
```json
|
||||
[
|
||||
@@ -50,7 +57,8 @@ source `default` is inherited from the workspace default. A null limit and sourc
|
||||
```
|
||||
|
||||
Monetary response fields are decimal strings in microcents so integrations do not lose precision. There are
|
||||
100,000,000 microcents per US dollar. Spend and reset timestamps cover the current UTC calendar month. `updated_at` is
|
||||
100,000,000 microcents per US dollar. Spend and reset timestamps cover the current UTC calendar month. In policy-based
|
||||
workspaces, `updated_at` is the reported rule's update time, or null when no rule applies. Before migration, it is
|
||||
null when there is no custom member override.
|
||||
|
||||
## Set a custom budget
|
||||
@@ -72,7 +80,10 @@ curl --fail-with-body --request PUT \
|
||||
`budget_dollars` accepts a non-negative US-dollar amount with at most two decimal places. The PUT is idempotent and
|
||||
returns HTTP 204. Use the member ID returned by the list operation.
|
||||
|
||||
## Return to the workspace default
|
||||
A migrated member budget changed to a shared, tag-based, or model-specific rule in **Controls** cannot be overwritten
|
||||
through this API. Conflicting rules, such as multiple single-member limits, also return HTTP `409`.
|
||||
|
||||
## Remove a custom budget
|
||||
|
||||
```text
|
||||
DELETE /api/v1/budgets/members/:user_id
|
||||
@@ -86,14 +97,16 @@ curl --fail-with-body --request DELETE \
|
||||
--header "Authorization: Bearer ${SERVICE_API_KEY}"
|
||||
```
|
||||
|
||||
Deleting an override does not delete the member. The member inherits the workspace default budget afterward, or
|
||||
becomes unlimited when the workspace has no default. Repeating the request is safe and returns HTTP 204.
|
||||
Deleting a single-member limit does not delete the member. Other applicable policies still cap spend. For legacy or
|
||||
migrated defaults, deleting the override restores the workspace default, if one exists. Repeating a successful
|
||||
request is safe and returns HTTP 204.
|
||||
|
||||
## Errors
|
||||
|
||||
| Status | Meaning |
|
||||
| ------ | -------------------------------------------------------- |
|
||||
| `400` | Invalid member ID or budget amount. |
|
||||
| `401` | Missing, invalid, expired, or revoked service API key. |
|
||||
| `403` | The API key does not have permission to manage budgets. |
|
||||
| `404` | The member is not in the workspace bound to the API key. |
|
||||
| Status | Meaning |
|
||||
| ------ | --------------------------------------------------------------------------------- |
|
||||
| `400` | Invalid member ID or budget amount. |
|
||||
| `401` | Missing, invalid, expired, or revoked service API key. |
|
||||
| `403` | The API key does not have permission to manage budgets. |
|
||||
| `404` | The member is not in the workspace bound to the API key. |
|
||||
| `409` | The budget cannot be changed through this API. Manage it in **Controls** instead. |
|
||||
|
||||
@@ -19,7 +19,8 @@ curl -X POST "https://opencode.ai/inference/openai/v1/chat/completions" \
|
||||
## Authentication
|
||||
|
||||
Replace `<token>` with a [personal API key](/console/api#personal-api-keys) or a [service account key](/console/api#service-accounts) created in the [Console](https://opencode.ai/console). Paid models
|
||||
require the header; free chat models can be called without it.
|
||||
require the header. Free-tier chat models are only available from within OpenCode; other clients receive HTTP `403`,
|
||||
even with an API key. Use paid models or a [Go](/console/go) subscription from other clients.
|
||||
|
||||
```text
|
||||
Authorization: Bearer <token>
|
||||
|
||||
@@ -47,7 +47,7 @@ turns off until you set it up again.
|
||||
|
||||
## Check your balance
|
||||
|
||||
The **Credits** card on **Overview** shows the balance for owners and admins.
|
||||
The **Billing** card on **Activity** shows the balance for owners and admins and opens **Settings › Billing**.
|
||||
|
||||
## When credits run out
|
||||
|
||||
@@ -81,4 +81,4 @@ Workspaces with a credit agreement can be invoiced monthly instead of buying cre
|
||||
## Go
|
||||
|
||||
[OpenCode Go](/console/go) subscriptions use the same payment methods and appear in the same invoice list. Turn on
|
||||
**Extra usage** on the **Overview** credits card to pay from credits once a Go limit is reached.
|
||||
**Extra Usage** on the **Go** page to pay from credits once a Go limit is reached.
|
||||
|
||||
@@ -3,71 +3,77 @@ title: "Budgets"
|
||||
description: "Cap monthly spend for a workspace, its members, and its service accounts."
|
||||
---
|
||||
|
||||
Budgets cap how much a workspace spends each month. Owners and admins set them from the **Budget limits** panel on
|
||||
the **Members** and **Keys** pages.
|
||||
Budgets cap monthly spend through policies. Owners and admins manage them in **Controls**.
|
||||
|
||||
## Budget levels
|
||||
|
||||
| Budget | Applies to | Where to set it |
|
||||
| ----------------------- | ------------------------------------------- | -------------------------------------------------- |
|
||||
| Workspace | Combined spend of everyone in the workspace | **Members** or **Keys › Monthly workspace budget** |
|
||||
| Default user | Each member without a custom limit | **Members › Monthly default user budget** |
|
||||
| Custom user | One member | **Members** table or member page |
|
||||
| Default service account | Each service account without a custom limit | **Keys › Monthly default service account budget** |
|
||||
| Custom service account | One service account | Service account page |
|
||||
| Policy audience | Applies to |
|
||||
| ---------------------- | ---------------------------------------------------- |
|
||||
| Entire workspace | Combined spend of all members and service accounts |
|
||||
| All members | Each member, or one shared allowance for all members |
|
||||
| Members tagged with | Members with the chosen tags |
|
||||
| These members | Specific members |
|
||||
| All service accounts | Each service account, or one shared allowance |
|
||||
| These service accounts | Specific service accounts |
|
||||
|
||||
A request must fit under both the workspace budget and the person's own budget. Without any budget, spend is
|
||||
unlimited.
|
||||
A request must fit under every applicable budget. A larger allowance never overrides a smaller one. Without any
|
||||
budget, spend is unlimited.
|
||||
|
||||
## Workspace budget
|
||||
|
||||
The workspace budget blocks requests for everyone once the workspace reaches it.
|
||||
|
||||
1. Open **Members** or **Keys**.
|
||||
2. In **Budget limits**, click **Monthly workspace budget**.
|
||||
3. Enter a **Workspace limit** in USD and click **Save**.
|
||||
1. Open **Controls** and click **Add policy**.
|
||||
2. Choose **Entire workspace** and add a **Budget** rule.
|
||||
3. Enter the monthly limit in USD and click **Save**.
|
||||
|
||||
## Member budgets
|
||||
|
||||
The default user budget applies to every member who has no custom limit. Set it under **Monthly default user budget**.
|
||||
Choose **All members** in a policy to give each member a monthly allowance, or share one amount across the group.
|
||||
Choose specific members or tags to cover a smaller group.
|
||||
|
||||
Give one member a custom limit from either place:
|
||||
To budget for one person:
|
||||
|
||||
- Click the **Limit** cell in their **Members** row and enter an amount.
|
||||
- Open the member and click **Set User Budget** under **Monthly Budget**.
|
||||
1. Open the member in **Settings › Members**.
|
||||
2. Click **Create budget policy** to open the builder with that person selected.
|
||||
3. Enter the amount and click **Save**.
|
||||
|
||||
Custom limits are highlighted in the Members table. Clear a custom limit to return the member to the default; the
|
||||
member page then shows **Using Default**.
|
||||
Their member page lists the policies that apply. If an all-member budget also covers them, both limits apply.
|
||||
|
||||
## Service account budgets
|
||||
|
||||
Service accounts work the same way. Set **Monthly default service account budget** on the **Keys** page, or open a
|
||||
service account and click **Set Service Account Budget**.
|
||||
In **Controls**, choose **All service accounts** or **These service accounts**, add a **Budget** rule, and set an
|
||||
individual or shared monthly allowance. The policy covers every key belonging to those accounts.
|
||||
|
||||
## Amounts and resets
|
||||
|
||||
- Amounts are in US dollars with up to two decimal places.
|
||||
- Budgets reset on the 1st of each month at 00:00 UTC.
|
||||
- A `$0` budget blocks all spend that counts toward budgets.
|
||||
- Adding or changing a budget includes spend already recorded that month; it does not reset the allowance.
|
||||
|
||||
## What counts
|
||||
|
||||
By default, a budget covers **All spend**. You can narrow it to selected models; then only those models count,
|
||||
with either one allowance for the set or a separate allowance for each model.
|
||||
|
||||
| Spend | Counts toward budgets |
|
||||
| ------------------------------------------------------------------- | ---------------------------- |
|
||||
| Paid Console models | Yes |
|
||||
| Models on [your own providers](/console/providers) with a price set | Yes, at the configured price |
|
||||
| [Web search](/console/websearch) | Yes |
|
||||
| [Web search](/console/websearch) | Yes, for all-spend budgets |
|
||||
| Free models | No |
|
||||
| [Go](/console/go) usage within the plan | No |
|
||||
| Go extra usage paid from credits | Yes |
|
||||
|
||||
## When a budget is reached
|
||||
|
||||
New requests fail with HTTP `429` until the budget resets or an admin raises it. The response does not say which
|
||||
budget was reached.
|
||||
New requests fail with HTTP `429` until the budget resets or an owner or admin raises it. The response identifies
|
||||
a policy budget failure but does not name the budget. Open the request in **Activity › Logs** to see the policy
|
||||
that blocked it.
|
||||
|
||||
```text
|
||||
Upstream request failed: Account budget exceeded
|
||||
Upstream request failed: Policy budget exceeded
|
||||
```
|
||||
|
||||
Budgets are checked when a request starts. Requests already in progress finish, so spend can end slightly above the
|
||||
@@ -75,12 +81,14 @@ limit.
|
||||
|
||||
## Track spend
|
||||
|
||||
Each member sees their own budget on **Overview**: the amount left, the amount spent, and the reset date.
|
||||
Each member sees their own spending and limit on **Activity**. Open **My usage** for **Activity › Overview**,
|
||||
including budget details and reset dates.
|
||||
|
||||
Owners and admins of workspaces with more than one member also see **Usage**. It breaks down cost by day, model, and
|
||||
Owners and admins can open **Activity › Usage** from the spending chart. It breaks down cost by day, model, and
|
||||
person, and the **Export usage** button downloads daily totals for the last 7, 30, or 90 days as CSV.
|
||||
|
||||
## Automate budgets
|
||||
|
||||
Use the [Budgets API](/console/api/budgets) to read every member's budget and set custom limits from your own
|
||||
tools.
|
||||
Use the [Budgets API](/console/api/budgets) to read individual monthly all-spend limits and manage single-member
|
||||
limits, including after migration to budget policies. Manage shared, tag-based, and model-specific policies in
|
||||
**Controls**.
|
||||
|
||||
@@ -68,6 +68,19 @@ The current list of models includes:
|
||||
|
||||
The list of models may change as we test and add new ones.
|
||||
|
||||
### Enable restricted models
|
||||
|
||||
Workspace privacy settings apply to Go. By default, paid endpoints that train on request data are blocked, and
|
||||
allowed regions are **Europe & United States**. Workspaces without saved privacy settings also allow **Global**
|
||||
for requests from China.
|
||||
|
||||
In **Settings › Privacy**, an owner or admin can enable:
|
||||
|
||||
- **DeepSeek V4.1 Flash and V4 Pro:** select **Global** under **Regions**.
|
||||
- **Gemini 4 Argon Contributor, Muse Spark 1.3 Contributor, and Muse Spark 1.2 Contributor:** turn on **Allow paid endpoints that train on request data**.
|
||||
|
||||
See [Privacy](#privacy) for each model's training and retention terms.
|
||||
|
||||
## Where can I use it?
|
||||
|
||||
OpenCode Go is designed for [OpenCode](https://opencode.ai) and other coding agents
|
||||
@@ -108,8 +121,8 @@ investigated. The linked reports track fixes and workarounds.
|
||||
| ----------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| **DeepSeek Harness** | Session information arrives on some model paths, but is missing on others. We recognize its native header; the remaining work is to send it across all adapters. [Discussion #5495](https://github.com/deepseek-ai/deepseek-harness/discussions/5495). |
|
||||
| **GitHub Copilot Chat** | Automatic session-header support is requested in [VS Code issue #334186](https://github.com/microsoft/vscode/issues/334186). |
|
||||
| **Kimi Code** | Automatic session-header support is requested in [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506). |
|
||||
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) has a proposed fix in [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327), which has not yet merged. |
|
||||
| **Kimi Code** | The session-header request in [issue #3506](https://github.com/MoonshotAI/kimi-code/issues/3506) was closed as not planned. |
|
||||
| **MiMo Code** | [Issue #2317](https://github.com/XiaomiMiMo/MiMo-Code/issues/2317) is closed, and [PR #2327](https://github.com/XiaomiMiMo/MiMo-Code/pull/2327) was closed without merging. |
|
||||
|
||||
## Usage limits
|
||||
|
||||
@@ -333,8 +346,8 @@ Usage limits may change as we learn from early usage and feedback.
|
||||
|
||||
### Usage beyond limits
|
||||
|
||||
If you also have credits in your Console balance, you can turn on **Extra usage** on the
|
||||
**Overview** credits card. When enabled, Go will fall back to your [pay-as-you-go balance](/console/models#pricing)
|
||||
If you also have credits in your Console balance, you can turn on **Extra Usage** on the
|
||||
**Go** page. When enabled, Go will fall back to your [pay-as-you-go balance](/console/models#pricing)
|
||||
after you've reached your usage limits instead of blocking requests.
|
||||
|
||||
### Why some models have lower usage
|
||||
|
||||
@@ -4,7 +4,7 @@ description: "Use Console and Go models from Hermes Agent."
|
||||
---
|
||||
|
||||
[Hermes Agent](https://hermes-agent.nousresearch.com) includes OpenCode providers for pay-as-you-go and Go. It picks the
|
||||
right API for each model, so every Console model works.
|
||||
right API for each paid or Go model. Free-tier chat models require OpenCode and return HTTP `403` from Hermes.
|
||||
|
||||
| Provider | Plan | Key variable |
|
||||
| -------------- | ------------- | ---------------------- |
|
||||
|
||||
@@ -10,9 +10,12 @@ is billed to your workspace like any other request.
|
||||
| --------------------------------------------- | ------------- | --------- | ------------------------- | --- |
|
||||
| [Claude Code](/console/harnesses/claude-code) | Yes | Yes | Anthropic Messages models | Yes |
|
||||
| [Codex](/console/harnesses/codex) | Yes | Yes | OpenAI Responses models | Yes |
|
||||
| [Hermes](/console/harnesses/hermes) | Built in | Built in | All models | Yes |
|
||||
| [Pi](/console/harnesses/pi) | Built in | Built in | All models | Yes |
|
||||
| [Raycast](/console/harnesses/raycast) | Extension | Extension | All models | Yes |
|
||||
| [Hermes](/console/harnesses/hermes) | Built in | Built in | Paid and Go models | Yes |
|
||||
| [Pi](/console/harnesses/pi) | Built in | Built in | Paid and Go models | Yes |
|
||||
| [Raycast](/console/harnesses/raycast) | Extension | Extension | Paid and Go models | Yes |
|
||||
|
||||
Free-tier chat models are only available from within OpenCode. Other harnesses receive HTTP `403` for those models,
|
||||
even with a Console API key. Use paid models or a Go subscription.
|
||||
|
||||
## Get an API key
|
||||
|
||||
@@ -62,7 +65,7 @@ A harness can only use the models that accept the API it speaks. Most models acc
|
||||
The endpoint column in the [Console](/console/models#endpoints) and [Go](/console/go#endpoints) tables lists one API per
|
||||
model, so check the harness page for the full list.
|
||||
|
||||
Hermes, Pi, and the Raycast extension pick the right API for each model, so they can use every model. Claude Code and
|
||||
Hermes, Pi, and the Raycast extension pick the right API for each paid or Go model. Claude Code and
|
||||
Codex speak a single API and only reach part of the catalog.
|
||||
|
||||
| Harness | API | Models |
|
||||
|
||||
@@ -3,8 +3,8 @@ title: "Pi"
|
||||
description: "Use Console and Go models from the Pi coding agent."
|
||||
---
|
||||
|
||||
[Pi](https://pi.dev) includes OpenCode providers for pay-as-you-go and Go. It picks the right API for each model, so
|
||||
every Console model works.
|
||||
[Pi](https://pi.dev) includes OpenCode providers for pay-as-you-go and Go. It picks the right API for each paid or Go
|
||||
model. Free-tier chat models require OpenCode and return HTTP `403` from Pi.
|
||||
|
||||
| Provider | Plan |
|
||||
| ------------- | ------------- |
|
||||
|
||||
@@ -9,7 +9,8 @@ Use Console and Go models in Raycast AI Chat, Quick AI, and AI Commands through
|
||||
|
||||
## Configure
|
||||
|
||||
The extension loads the models enabled in your workspace and bills them to it.
|
||||
The extension loads the models enabled in your workspace and bills them to it. Choose paid or Go models;
|
||||
free-tier chat models require OpenCode and return HTTP `403` from Raycast.
|
||||
|
||||
1. Install the extension from the Raycast Store.
|
||||
2. Create a [personal API key](/console/harnesses#get-an-api-key) and paste it into the extension's **API Key** preference.
|
||||
|
||||
@@ -3,12 +3,11 @@ title: "Members"
|
||||
description: "Invite people to an OpenCode Console workspace, manage their roles, and remove them."
|
||||
---
|
||||
|
||||
Owners and admins manage people from the **Members** page. Each row shows the member's role, join date, monthly
|
||||
usage, and budget limit.
|
||||
Owners and admins manage people from **Settings › Members**. Open a member to see their usage and budget policies.
|
||||
|
||||
## Invite members
|
||||
|
||||
1. Open **Members** and click **Invite Members**.
|
||||
1. Open **Settings › Members** and click **Invite Members**.
|
||||
2. Add one or more email addresses. Separate them with spaces, commas, or semicolons, or paste a list.
|
||||
3. Click **Send invitations**.
|
||||
|
||||
|
||||
@@ -28,7 +28,8 @@ You are charged per request and can add credits to your account.
|
||||
|
||||
## Endpoints
|
||||
|
||||
You can also access the models directly through the following API endpoints.
|
||||
You can also access the models directly through the following API endpoints. Free-tier chat models require OpenCode;
|
||||
use paid models or [Go](/console/go) from other clients.
|
||||
|
||||
<div class="docs-table-scroll" role="region" aria-label="Console model endpoints" tabIndex={0}>
|
||||
|
||||
@@ -89,8 +90,6 @@ You can also access the models directly through the following API endpoints.
|
||||
| Muse Spark 1.2 | muse-spark-1.2 | `https://opencode.ai/inference/openai/v1/responses` | `@ai-sdk/openai` |
|
||||
| Qwen3.8 Max | qwen3.8-max | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| Qwen3.8 Flash | qwen3.8-flash | `https://opencode.ai/inference/anthropic/v1/messages` | `@ai-sdk/anthropic` |
|
||||
| Qwen3.7 Max | qwen3.7-max | `https://opencode.ai/inference/anthropic/v1/messages` | `@ai-sdk/anthropic` |
|
||||
| Qwen3.7 Plus | qwen3.7-plus | `https://opencode.ai/inference/anthropic/v1/messages` | `@ai-sdk/anthropic` |
|
||||
| Qwen3.6 Plus | qwen3.6-plus | `https://opencode.ai/inference/anthropic/v1/messages` | `@ai-sdk/anthropic` |
|
||||
| Qwen3.5 Plus | qwen3.5-plus | `https://opencode.ai/inference/anthropic/v1/messages` | `@ai-sdk/anthropic` |
|
||||
| DeepSeek V4.1 Flash | deepseek-v4.1-flash | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
@@ -116,9 +115,7 @@ You can also access the models directly through the following API endpoints.
|
||||
| Beam Free | beam-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| Flint 40B Free | flint-40b-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| LongCat 2.5 Preview Free | longcat-2.5-preview-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| Exo Free | exo-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| MiMo-V2.6-Flash Free | mimo-v2.6-flash-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| MiMo-V2.5 Free | mimo-v2.5-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| Nemotron 3 Ultra Free | nemotron-3-ultra-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| Nemotron 3.5 Lightning Free | nemotron-3.5-lightning-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
| Nemotron 3.5 Super VL Free | nemotron-3.5-super-vl-free | `https://opencode.ai/inference/openai/v1/chat/completions` | `@ai-sdk/openai-compatible` |
|
||||
@@ -209,9 +206,7 @@ Console uses pay-as-you-go pricing. Below are the prices **per 1M tokens**.
|
||||
| Beam Free | Free | Free | Free | - |
|
||||
| Flint 40B Free | Free | Free | Free | - |
|
||||
| LongCat 2.5 Preview Free | Free | Free | Free | - |
|
||||
| Exo Free | Free | Free | Free | - |
|
||||
| MiMo-V2.6-Flash Free | Free | Free | Free | - |
|
||||
| MiMo-V2.5 Free | Free | Free | Free | - |
|
||||
| Nemotron 3 Ultra Free | Free | Free | Free | - |
|
||||
| Nemotron 3.5 Lightning Free | Free | Free | Free | - |
|
||||
| Nemotron 3.5 Super VL Free | Free | Free | Free | - |
|
||||
@@ -232,8 +227,6 @@ Console uses pay-as-you-go pricing. Below are the prices **per 1M tokens**.
|
||||
| Mistral Large 4 (50% off) | ~~$1.36~~ $0.68 | ~~$4.18~~ $2.09 | ~~$0.14~~ $0.07 | - |
|
||||
| Qwen3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 |
|
||||
| Qwen3.8 Flash | $0.15 | $0.47 | $0.016 | $0.20 |
|
||||
| Qwen3.7 Max | $2.50 | $7.50 | $0.50 | $3.125 |
|
||||
| Qwen3.7 Plus | $0.40 | $1.60 | $0.04 | $0.50 |
|
||||
| Qwen3.6 Plus | $0.50 | $3.00 | $0.05 | $0.625 |
|
||||
| Qwen3.5 Plus | $0.20 | $1.20 | $0.02 | $0.25 |
|
||||
| DeepSeek V4.1 Flash | $0.30 | $1.20 | $0.006 | - |
|
||||
@@ -322,9 +315,7 @@ models to generate session titles.
|
||||
|
||||
- GLM-5.3-Flash Free is free on OpenCode for a limited time. Its provider follows a zero-retention policy and does not use your data for model training.
|
||||
- DeepSeek V4.1 Flash Free is free on OpenCode for a limited time. Its provider follows a zero-retention policy and does not use your data for model training.
|
||||
- Exo Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
|
||||
- MiMo-V2.6-Flash Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
|
||||
- MiMo-V2.5 Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
|
||||
- Nemotron 3 Ultra Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
|
||||
- Nemotron 3.5 Lightning Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
|
||||
- Nemotron 3.5 Super VL Free is available on OpenCode for a limited time. The team is using this time to collect feedback and improve the model.
|
||||
@@ -372,9 +363,7 @@ All our models are hosted in the US and EU. Our providers follow a zero-retentio
|
||||
|
||||
- Big Pickle: During its free period, collected data may be used to improve the model.
|
||||
- Flint 40B Free: During its free period, collected data may be used to improve the model. Data is retained for 30 days.
|
||||
- Exo Free: During its free period, collected data may be used to improve the model.
|
||||
- MiMo-V2.6-Flash Free: During its free period, collected data may be used to improve the model.
|
||||
- MiMo-V2.5 Free: During its free period, collected data may be used to improve the model.
|
||||
- Nemotron 3 Ultra Free (NVIDIA free endpoints): Trial use only — do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
|
||||
- Nemotron 3.5 Lightning Free (NVIDIA free endpoints): Trial use only — do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
|
||||
- Nemotron 3.5 Super VL Free (NVIDIA free endpoints): Trial use only — do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).
|
||||
|
||||
@@ -18,6 +18,8 @@ https://opencode.ai/console/scim/v2
|
||||
|
||||
## Create a token
|
||||
|
||||
Only workspace owners can set up directory sync or create and revoke its tokens.
|
||||
|
||||
1. Open **Settings › Security** and click **Set up** under **Directory sync**.
|
||||
2. Copy the **SCIM base URL** and the token. The token is shown only once, so store it in a secrets manager.
|
||||
|
||||
|
||||
@@ -3,8 +3,8 @@ title: "SSO"
|
||||
description: "Sign in to an OpenCode Console workspace through your identity provider with OIDC or SAML."
|
||||
---
|
||||
|
||||
Single sign-on (SSO) sends workspace members through your company's identity provider when they sign in. Owners and
|
||||
admins set it up in **Settings › Security**, and it's included with every workspace.
|
||||
Single sign-on (SSO) sends workspace members through your company's identity provider when they sign in. Owners
|
||||
set it up in **Settings › Security**, and it's included with every workspace.
|
||||
|
||||
| Protocol | Providers |
|
||||
| -------------- | -------------------------------------------------------------------------------------- |
|
||||
@@ -79,8 +79,9 @@ Invitations to an SSO workspace send the invitee to your identity provider when
|
||||
|
||||
## Existing accounts
|
||||
|
||||
If someone already has a Console account with the same email, Console asks them to sign in to it once to link SSO.
|
||||
Invited people and people added by directory sync are linked automatically.
|
||||
If someone already has a Console account with the same email, they sign in again during the SSO flow and confirm
|
||||
with **Link account**. An invitation does not skip this confirmation. SCIM-provisioned accounts on a verified
|
||||
workspace domain can still link automatically.
|
||||
|
||||
## Edit or delete
|
||||
|
||||
|
||||
@@ -10,8 +10,8 @@ Each successful search costs **$0.01** and counts toward the workspace balance a
|
||||
## Enable
|
||||
|
||||
1. Sign in to the [Console](https://opencode.ai/console) as a workspace owner or admin.
|
||||
2. Open **Settings** > **General**.
|
||||
3. Turn on **Hosted web search**.
|
||||
2. Open **Integrations** and click **Set up** on **Hosted Web Search**.
|
||||
3. Click **Enable**.
|
||||
|
||||
Each member then connects OpenCode to the workspace with `/connect`.
|
||||
|
||||
@@ -37,7 +37,7 @@ See the [Websearch guide](/websearch) to configure permissions or disable the to
|
||||
|
||||
Console charges **$0.01** after a search returns a valid result set. Failed and rate-limited searches are not charged.
|
||||
|
||||
Web search appears separately from model usage in **Usage**, **My Activity**, member activity, invoices, and CSV exports. Workspace and member monthly spending limits include web search charges.
|
||||
Web search appears separately from model usage in **Activity › Usage**, **Activity › Overview**, member activity, invoices, and CSV exports. Applicable all-spend budget policies include web search charges.
|
||||
|
||||
## Privacy
|
||||
|
||||
|
||||
@@ -25,7 +25,7 @@ You become the owner of the new workspace.
|
||||
## Switch workspaces
|
||||
|
||||
Pick another workspace from the workspace menu. Console keeps you on the same page, so switching from
|
||||
`/acme/members` opens the other workspace's Members page.
|
||||
`/acme/settings/members` opens the other workspace's Members page.
|
||||
|
||||
Pending invitations appear at the top of the same menu. See [Members](/console/members#accept-an-invitation).
|
||||
|
||||
@@ -49,9 +49,10 @@ Every member has one role. New members always join as **Member**.
|
||||
| ------ | -------------------------------------------------------------------------------------------------------------------- |
|
||||
| Member | Use OpenCode, see their own usage, logs, and budget. |
|
||||
| Admin | Everything a member can, plus manage members, billing, budgets, providers, policies, service accounts, and settings. |
|
||||
| Owner | Everything an admin can, plus grant the Owner role and delete the workspace. |
|
||||
| Owner | Everything an admin can, plus manage SSO and directory sync, grant the Owner role, and delete the workspace. |
|
||||
|
||||
Members only see **Overview**, **Logs**, **Leaderboard** when it is visible to members, and **Settings › Account**.
|
||||
Members see their own usage and logs on **Activity**, plus the leaderboard when it is visible to members.
|
||||
They open **Account** from the account menu.
|
||||
|
||||
### Role rules
|
||||
|
||||
@@ -61,7 +62,7 @@ Members only see **Overview**, **Logs**, **Leaderboard** when it is visible to m
|
||||
|
||||
### Transfer ownership
|
||||
|
||||
1. As an owner, open **Members** and set the new owner's role to **Owner**.
|
||||
1. As an owner, open **Settings › Members** and set the new owner's role to **Owner**.
|
||||
2. Ask the new owner to change your role to **Admin** or **Member**.
|
||||
|
||||
## Delete a workspace
|
||||
@@ -84,4 +85,10 @@ Deletion is immediate and cannot be undone:
|
||||
|
||||
## Leave a workspace
|
||||
|
||||
Members cannot remove themselves. Ask an owner or admin to [remove you](/console/members#remove-a-member).
|
||||
1. Open **Account** from the account menu.
|
||||
2. Under **Connected workspaces**, click **Leave** beside the workspace.
|
||||
3. Confirm with **Leave workspace**.
|
||||
|
||||
The last owner can't leave; make another member an owner first. In workspaces with SSO or directory sync, your
|
||||
identity provider manages membership, so you can't leave from Console. To rejoin after leaving, ask for a new
|
||||
invitation.
|
||||
|
||||
Reference in New Issue
Block a user