Skip to content

[AI Gateway] Update Auto Router models and add Guardrails S14 category #34743

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

Open
ethulia wants to merge 1 commit into
base: production
Choose a base branch
from
Open

[AI Gateway] Update Auto Router models and add Guardrails S14 category #34743

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
82 changes: 44 additions & 38 deletions src/content/docs/ai-gateway/features/auto-router.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ curl -i -X POST "https://gateway.ai.cloudflare.com/v1/$CLOUDFLARE_ACCOUNT_ID/$CL
The response headers show which model Auto Router selected:

```txt output
cf-aig-routed-model: openai/gpt-5.6-luna
cf-aig-routed-model: openai/gpt-6-luna
cf-aig-routing-reason: cost_optimal_within_pool
cf-aig-routing-decision-id: 91e0b970-33f0-4921-b8dc-127412e7b103
```
Expand Down Expand Up @@ -108,12 +108,12 @@ By default, Auto Router selects from a set of [default models](#default-models).

The response includes headers that describe the routing decision. These headers can help you identify the selected model, understand why it was selected, and correlate the request with AI Gateway logs for support and diagnostics:

| Header | Description |
| ---------------------------- | --------------------------------------------------------------------------- |
| `cf-aig-routed-model` | The model that served the request, for example `anthropic/claude-sonnet-5`. |
| `cf-aig-routing-reason` | Why that model was selected. Refer to [Routing reasons](#routing-reasons). |
| `cf-aig-routing-decision-id` | The routing decision identifier. |
| `cf-aig-request-id` | The request identifier. |
| Header | Description |
| ---------------------------- | ----------------------------------------------------------------------------- |
| `cf-aig-routed-model` | The model that served the request, for example `anthropic/claude-sonnet-5.5`. |
| `cf-aig-routing-reason` | Why that model was selected. Refer to [Routing reasons](#routing-reasons). |
| `cf-aig-routing-decision-id` | The routing decision identifier. |
| `cf-aig-request-id` | The request identifier. |

### Routing reasons

Expand All @@ -138,44 +138,50 @@ Auto Router selects from a pool of models managed by Cloudflare. The pool may ch

By default, Auto Router selects from the following models. To provide your own set of models, use the [`cf-aig-allowed-models` or `cf-aig-allowed-providers` header](#headers).

| Model | Provider |
| --------------------------- | ----------- |
| `anthropic/claude-fable-5` | `anthropic` |
| `anthropic/claude-opus-5` | `anthropic` |
| `anthropic/claude-sonnet-5` | `anthropic` |
| `openai/gpt-5.6-luna` | `openai` |
| `openai/gpt-5.6-sol` | `openai` |
| `openai/gpt-5.6-terra` | `openai` |
| `xai/grok-4.5` | `xai` |
| Model | Provider |
| ---------------------------------------- | ------------ |
| `@cf/deepseek-ai/deepseek-v4-flash-0731` | `workers-ai` |
| `anthropic/claude-haiku-5.5` | `anthropic` |
| `anthropic/claude-opus-5.5` | `anthropic` |
| `anthropic/claude-sonnet-5.5` | `anthropic` |
| `moonshotai/kimi-k3` | `workers-ai` |
| `openai/gpt-6-luna` | `openai` |
| `openai/gpt-6.1-sol` | `openai` |
| `xai/grok-4.7` | `xai` |

### Additional models

Auto Router only selects these models when they match `cf-aig-allowed-models` or `cf-aig-allowed-providers`.

<Details header="Additional models">

| Model | Provider |
| ---------------------------------------- | ------------ |
| `@cf/deepseek-ai/deepseek-v4-flash-0731` | `workers-ai` |
| `@cf/deepseek-ai/deepseek-v4-pro-0813` | `workers-ai` |
| `@cf/google/gemma-4-26b-a4b-it` | `workers-ai` |
| `@cf/moonshotai/kimi-k2.7-code` | `workers-ai` |
| `@cf/openai/gpt-oss-20b` | `workers-ai` |
| `@cf/qwen/qwen3.8-27b` | `workers-ai` |
| `@cf/zai-org/glm-5.2` | `workers-ai` |
| `alibaba/qwen3.8-max` | `alibaba` |
| `anthropic/claude-fable-5.1` | `anthropic` |
| `anthropic/claude-opus-4.8` | `anthropic` |
| `anthropic/claude-opus-5.5` | `anthropic` |
| `anthropic/claude-sonnet-4.6` | `anthropic` |
| `fireworks/glm-5.3` | `fireworks` |
| `fireworks/glm-5.3-flash` | `fireworks` |
| `minimax/m3` | `minimax` |
| `openai/gpt-5.5` | `openai` |
| `openai/gpt-6-astra` | `openai` |
| `openai/gpt-6-luna` | `openai` |
| `openai/gpt-6-sol` | `openai` |
| `xai/grok-4.6` | `xai` |
| Model | Provider |
| -------------------------------------- | ------------------ |
| `@cf/deepseek-ai/deepseek-v4-pro-0813` | `workers-ai` |
| `@cf/google/gemma-4-26b-a4b-it` | `workers-ai` |
| `@cf/moonshotai/kimi-k2.7-code` | `workers-ai` |
| `@cf/openai/gpt-oss-20b` | `workers-ai` |
| `@cf/qwen/qwen3.8-27b` | `workers-ai` |
| `@cf/zai-org/glm-5.2` | `workers-ai` |
| `alibaba/qwen3.8-max` | `alibaba` |
| `anthropic/claude-fable-5` | `anthropic` |
| `anthropic/claude-fable-5.1` | `anthropic` |
| `anthropic/claude-opus-4.8` | `anthropic` |
| `anthropic/claude-opus-5` | `anthropic` |
| `anthropic/claude-sonnet-4.6` | `anthropic` |
| `anthropic/claude-sonnet-5` | `anthropic` |
| `fireworks/glm-5.3` | `fireworks` |
| `fireworks/glm-5.3-flash` | `fireworks` |
| `google/gemini-3.8-flash` | `google-vertex-ai` |
| `minimax/m3` | `minimax` |
| `openai/gpt-5.5` | `openai` |
| `openai/gpt-5.6-luna` | `openai` |
| `openai/gpt-5.6-sol` | `openai` |
| `openai/gpt-5.6-terra` | `openai` |
| `openai/gpt-6-astra` | `openai` |
| `openai/gpt-6-sol` | `openai` |
| `xai/grok-4.5` | `xai` |
| `xai/grok-4.6` | `xai` |

</Details>

Expand Down
3 changes: 2 additions & 1 deletion src/content/docs/ai-gateway/features/guardrails/usage-considerations.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ Since Guardrails runs on Workers AI, enabling it incurs usage on Workers AI. You

Guardrails evaluate content against the following hazard categories. Each category is identified by a code that appears in your Guardrail configuration and in AI Gateway Logs. You can independently set each category to **Flag**, **Ignore**, or **Block** for prompts and responses.

Guardrails evaluate categories `S1` through `S13`, a subset of the [Llama Guard 3 ↗](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) hazard categories, using the [`@cf/meta/llama-guard-3-8b`](/workers-ai/models/llama-guard-3-8b/) model on Workers AI. The Llama Guard 3 category `S14` (Code interpreter abuse) is not evaluated by Guardrails. Category `P1` is prompt injection, evaluated separately by the `@cf/meta/prompt-guard-2-86m` model.
Guardrails evaluate categories `S1` through `S14`, the [Llama Guard 3 ↗](https://ai.meta.com/research/publications/llama-guard-llm-based-input-output-safeguard-for-human-ai-conversations/) hazard categories, using the [`@cf/meta/llama-guard-3-8b`](/workers-ai/models/llama-guard-3-8b/) model on Workers AI. Category `P1` is prompt injection, evaluated separately by the `@cf/meta/prompt-guard-2-86m` model.

These codes also appear in the `guardrails` property of the AI Gateway REST API, where you configure each category's action programmatically. See the [`create`](/api/resources/ai_gateway/methods/create/) and [`update`](/api/resources/ai_gateway/methods/update/) methods.

Expand All @@ -35,6 +35,7 @@ These codes also appear in the `guardrails` property of the AI Gateway REST API,
| `S11` | Suicide & Self-Harm |
| `S12` | Sexual Content |
| `S13` | Elections |
| `S14` | Code Interpreter Abuse |
| `P1` | Prompt Injection |

## Additional considerations
Expand Down
Loading