Eleven IDs. One base URL.
The list below is the live /v1/models response. If a model is not on this page, the gateway does not route to it. If a model on this page is missing from the live endpoint, the live endpoint is the source of truth — this page is reconciled to it on every doc-deploy.
GET https://api.slashed.pro/v1/models. No auth required. Returns OpenAI-spec list with id, object, created, owned_by. The data on this page mirrors that response as of last deploy.
01The current catalogue
Eleven models. Three providers. All addressable by their exact id in the model field of /v1/chat/completions.
gpt-5.5
gpt-5.4
gpt-5.4-mini
gpt-5.3-codex
gpt-5.2
claude-opus-4-7
claude-sonnet-4-6
gemini-3.1-pro-preview
gemini-3.5-flash
gemini-3-flash-preview
gemini-2.5-pro
02The /v1/models response shape
Documented as OpenAI-list-spec compatible. Every entry has the same four keys; created is set to 0 for all entries today — SLASHED does not preserve the upstream model's release timestamp.
03Capability matrix (documented)
The columns below reflect what the gateway documents as supported per upstream model. Documented, not contractually guaranteed — if the upstream provider deprecates a field, the gateway forwards the deprecation. Always test the specific feature you depend on.
| Model ID | Chat | Tools | Vision | Streaming | Reasoning |
|---|---|---|---|---|---|
gpt-5.5openai | ✓ | ✓ | ✓ | ✓ | ✓ |
gpt-5.4openai | ✓ | ✓ | ✓ | ✓ | — |
gpt-5.4-miniopenai | ✓ | ✓ | ✓ | ✓ | — |
gpt-5.3-codexopenai | ✓ | ✓ | — | ✓ | — |
gpt-5.2openai | ✓ | ✓ | ✓ | ✓ | — |
claude-opus-4-7anthropic | ✓ | ✓ | ✓ | ✓ | ✓ |
claude-sonnet-4-6anthropic | ✓ | ✓ | ✓ | ✓ | — |
gemini-3.1-pro-previewgoogle | ✓ | ✓ | ✓ | ✓ | — |
gemini-3.5-flashgoogle | ✓ | ✓ | ✓ | ✓ | — |
gemini-3-flash-previewgoogle | ✓ | ✓ | ✓ | ✓ | — |
gemini-2.5-progoogle | ✓ | ✓ | ✓ | ✓ | — |
04Choosing a model
- Quick + cheap:
gpt-5.4-mini,gemini-3.5-flash,gemini-3-flash-preview. - Heavy reasoning, long form:
claude-opus-4-7,gpt-5.5. - Code-heavy:
gpt-5.3-codex,claude-sonnet-4-6. - Vision-heavy: any
gpt-5.4/5.4-mini/claude-*/gemini-*.gpt-5.3-codexis text-only. - Preview-quality acceptable:
gemini-3.1-pro-preview,gemini-3-flash-preview. Marked preview by upstream — semantics may change.
/v1/models, the live endpoint wins. File the drift via security contact and we'll re-sync the page.