Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
2 changes: 1 addition & 1 deletion skills/openrouter-analytics-schema/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -127,7 +127,7 @@ All other dimensions (e.g., `model`, `provider`, `country`) are returned as-is w
### Dimension Categories

**Available with all time ranges:**
- `model` — the OpenRouter model ID (permaslug)
- `model` — the resolved model that actually served the generation (permaslug, e.g., `openai/gpt-4o`). For routed requests, this is the downstream model the router chose — not the router itself. To identify router traffic, drill down to individual generations via `generation_id` and check the `router` field using the `openrouter-generations` skill, or query `router_permaslug` in ClickHouse directly.
- `variant` — model variant (e.g., standard, extended)
- `api_key_id` — which API key made the request
- `user` — the creator user ID (for org-level queries)
Expand Down
6 changes: 3 additions & 3 deletions skills/openrouter-generations/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ npx tsx get-generation.ts --id gen-1234567890 --json

**What you get back:**

- **Model & routing**: `model`, `provider_name`, `router`, `service_tier`
- **Model & routing**: `model` (resolved model that served the request), `provider_name`, `router` (the router that chose the model, if any), `service_tier`
- **Tokens**: `tokens_prompt`, `tokens_completion`, `native_tokens_reasoning`, `native_tokens_cached`
- **Cost**: `total_cost`, `usage`, `upstream_inference_cost`, `cache_discount`
- **Performance**: `latency`, `generation_time`, `moderation_latency`
Expand Down Expand Up @@ -201,7 +201,7 @@ If you have a `request_id` or `session_id` from one generation, you can find rel
| Field | Type | Description |
|-------|------|-------------|
| `id` | string | Generation ID (`gen-...`) |
| `model` | string | Model permaslug (e.g., `openai/gpt-4o`) |
| `model` | string | Resolved model permaslug (e.g., `openai/gpt-4o`). For routed requests, this is the downstream model the router chose — not the router slug. |
| `provider_name` | string\|null | Provider that served the request |
| `api_type` | string | One of: `completions`, `embeddings`, `rerank`, `tts`, `stt`, `video` |
| `tokens_prompt` | int\|null | Prompt token count |
Expand All @@ -224,7 +224,7 @@ If you have a `request_id` or `session_id` from one generation, you can find rel
| `external_user` | string\|null | External user identifier (X-External-User header) |
| `session_id` | string\|null | Session grouping ID |
| `request_id` | string\|null | Request grouping ID (all gens from one API call) |
| `router` | string\|null | Router used (e.g., `openrouter/auto`) |
| `router` | string\|null | Router that selected the model (e.g., `openrouter/auto`, `openrouter/fusion`). Null when the user explicitly chose a model. Use this — not `model` — to identify router traffic. |
| `service_tier` | string\|null | Provider service tier |
| `web_search_engine` | string\|null | Search engine used (e.g., `exa`, `firecrawl`) |
| `num_search_results` | int\|null | Number of search results included |
Expand Down