Add dashboard screenshots to the Kimi integration page

Connect Provider modal with the Kimi catalog entry, the catalog models
with pricing, and the three Configure Your Agent variants (Claude Code,
Codex, Kimi CLI). Captured from a live dashboard + management build at
2x, cropped to the modal like the sibling pages' screenshots.
This commit is contained in:
mlsmaycon
2026-07-21 08:47:08 +00:00
parent ca3abcaf0d
commit 9917d471d7
6 changed files with 20 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 133 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 149 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 141 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 162 KiB

Binary file not shown.

After

Width:  |  Height:  |  Size: 5.1 KiB

View File

@@ -34,6 +34,10 @@ through the endpoint, so pick it based on the tools you plan to connect (see bel
encrypted server-side and never sent to callers.
5. Save the provider.
<p>
<img src="/docs-static/img/agent-network/integrations/agent-network-connect-kimi.png" alt="connect Kimi (Moonshot AI) provider in NetBird Agent Network" className="imagewrapper" />
</p>
<Note>
A provider forwards to a single upstream URL. If your team runs both OpenAI-shaped and
Anthropic-shaped agents, connect two Kimi providers — one per upstream URL — and give
@@ -52,6 +56,10 @@ their default per-token prices, which drive the cost figures in
[Usage & Logs](/agent-network/usage-and-logs) — adjust them if your rates differ. See
[Providers](/agent-network/providers) for details.
<p>
<img src="/docs-static/img/agent-network/integrations/agent-network-kimi-models.png" alt="Kimi catalog models kimi-k3 and kimi-k2-thinking with per-token prices" className="imagewrapper" />
</p>
## Create a Policy
By default nothing is allowed — a policy must connect a source group to the Kimi provider
@@ -94,6 +102,10 @@ Claude Code doesn't prompt for a key — NetBird supplies the real one.
`ANTHROPIC_MODEL` and `ANTHROPIC_SMALL_FAST_MODEL` point both of Claude Code's model slots
at Kimi K3, so no Anthropic model names leak into requests.
<p>
<img src="/docs-static/img/agent-network/integrations/agent-network-configure-agent-kimi-claude-code.png" alt="NetBird Configure Your Agent modal showing the Claude Code settings.json configuration for Kimi" className="imagewrapper" />
</p>
## Use with Codex
Codex speaks the OpenAI shape, so it needs the Kimi provider whose upstream URL is
@@ -114,6 +126,10 @@ wire_api = "chat"
than the OpenAI Responses API. The `/v1` suffix is the OpenAI-compatible base path on your
endpoint.
<p>
<img src="/docs-static/img/agent-network/integrations/agent-network-configure-agent-kimi-codex.png" alt="NetBird Configure Your Agent modal showing the Codex config.toml configuration for Kimi with wire_api chat" className="imagewrapper" />
</p>
## Use with Kimi CLI
[Kimi CLI](https://github.com/MoonshotAI/kimi-cli) is Moonshot's own coding agent. Configure
@@ -137,6 +153,10 @@ model = "kimi-k3"
max_context_size = 1000000
```
<p>
<img src="/docs-static/img/agent-network/integrations/agent-network-configure-agent-kimi-cli.png" alt="NetBird Configure Your Agent modal showing the Kimi CLI config.toml configuration" className="imagewrapper" />
</p>
## Result
Agents point at the NetBird endpoint with no key and call `kimi-k3` (or `kimi-k2-thinking`)