Models
Use this page when you need to verify model ids, understand endpoint support, and choose the right OpenAI-compatible model before configuring a client. For a product-style visual catalog, start with the Quotaflow Model Library.
What /models means
GET /models is scoped to the authenticated key and base URL you call. Quotaflow lists only public model ids enabled for that key. A default customer key can include multiple model families; a product-scoped key may list only GPT, embeddings, images, video, or another enabled subset.
Unsupported model ids fail fast instead of being silently changed to another public model id.
Endpoint
GET https://api.quotaflow.ai/openai/v1/modelsCurl
curl https://api.quotaflow.ai/openai/v1/models \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY"Curated model families
| Model family | Model ids | Endpoints | Common cases | Reference |
|---|---|---|---|---|
| GPT and Codex | gpt-5.5, gpt-5.5-pro, gpt-5-codex, gpt-5.4, gpt-5.4-pro, gpt-5.4-mini, gpt-5.4-nano, gpt-5.3-codex, gpt-5.3-codex-spark, gpt-5.2, gpt-5.2-codex, gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini, gpt-5.1-codex-max, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-4, gpt-4-1106-preview, chat-gpt, o1, o3, o3-mini, o4-mini | /responses, /chat/completions | Agents, chat, extraction, coding, classification | Responses API |
| Claude-compatible | claude-sonnet-5, claude-fable-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6, claude-sonnet-4-5, claude-opus-4-5-20251101, claude-haiku-4-5 | /v1/messages, /responses, /chat/completions | Claude-style coding, reasoning, Messages API clients, and OpenAI-compatible clients enabled for Claude models | Messages |
| Embeddings | text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002, openai/text-embedding-3-small, openai/text-embedding-3-large, openai/text-embedding-ada-002 | /embeddings | Search, RAG, clustering, semantic matching | Embeddings |
| GPT image | gpt-image-2 | /images/generations, /images/edits, /responses image tool | Product images, ecommerce edits, masked edits, marketing creative | GPT Image 2 |
| Gemini text and reasoning | gemini-3.5-flash, gemini-3.1-pro, gemini-3.1-flash-lite, gemini-3.0-flash, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite | /chat/completions, Gemini :generateContent | Gemini text, multimodal, and reasoning-capable apps. Use Gemini-compatible endpoints for countTokens and cached-content workflows. | generateContent |
| GLM text | glm-5.2 | /chat/completions | OpenAI-compatible chat clients that need GLM text output. GLM chat supports non-streaming chat, streaming, and tool calls. Strict JSON mode is not part of the GLM public contract; strict JSON requests return 400 invalid_request_error instead of falling back. | Chat Completions |
| Kimi code chat | kimi-k2.7-code | /chat/completions | OpenAI-compatible Kimi text for coding, agent, and long-context chat flows. Kimi chat supports non-streaming chat, streaming, tool calls, and strict JSON mode through response_format. | Chat Completions |
| Gemini image | gemini-3.1-flash-image-preview, gemini-3-pro-image-preview, gemini-2.5-flash-image | /images/generations, /images/edits, Gemini :generateContent | Fast image iteration, reference-image edits, Gemini-native image workflows | Gemini 3.1 Flash Image |
| Video | veo-3.1-fast-generate-001, veo-3.0-generate-001, seedance-2.0-fast | /videos | Async product, social, and creative video generation with reference images, first/last-frame controls, optional audio/video references, and task polling | Veo 3.1 Fast and Seedance 2.0 Fast |
Some Claude-enabled keys may also list exact Claude-compatible aliases such as claude-opus-4-1, claude-opus-4-5, or claude-sonnet-4. Other enabled keys may list extended Claude-compatible model ids such as pa/claude-sonnet-4-6-dd, pa/claude-opus-4-6-dd, pa/claude-sonnet-4-5-20250929-dd, pa/claude-opus-4-5-20251101-dd, or pa/claude-haiku-4-5-20251001-dd. Treat those as exact model ids: send the id returned by /models unchanged and use the same endpoint matrix.
For claude-sonnet-5, claude-fable-5, claude-opus-4-8, claude-opus-4-7, and matching Claude-compatible aliases, do not send non-default temperature, top_p, or top_k. Use adaptive thinking and endpoint-specific effort hints instead.
Recommended defaults
| If you are building | Start with | Why |
|---|---|---|
| A tool-capable OpenAI-compatible app or agent | gpt-5.4 with /responses | Strong general default. |
| A low-latency app chat flow | gpt-5.4-mini | Good speed and capability balance. |
| A cost-sensitive lightweight flow | gpt-5.4-nano | Small-model option for simple chat, extraction, and routing. |
| A coding-agent integration | gpt-5.3-codex with /responses | Intended for Codex-style usage. |
| A vector search pipeline | text-embedding-3-small | Good default embedding model. |
| A high-quality image generation or editing app | gpt-image-2 | Most OpenAI-compatible image path. |
| A Gemini reasoning app | gemini-3.1-pro or gemini-3.5-flash | Use /chat/completions for OpenAI-style chat/SSE clients, or generateContent for Gemini-native features such as countTokens and cached content. |
| A GLM chat app | glm-5.2 with /chat/completions | Chat-only OpenAI-compatible text path for keys with GLM access; use messages, streaming, and tools, but do not send strict JSON mode because unsupported requests fail with 400 invalid_request_error. |
| A Kimi coding chat app | kimi-k2.7-code with /chat/completions | Kimi text path for coding, agent, and OpenAI-compatible chat clients that need streaming, tools, or strict JSON mode. |
| A fast image-iteration workflow | gemini-3.1-flash-image-preview | Fast creative iteration with OpenAI-compatible and Gemini-compatible options. |
| An async video workflow | veo-3.1-fast-generate-001 | Fast default for video task generation. |
Validation checklist
- Call
/modelswith the same key and base URL your app will use. - Confirm the desired model id is returned.
- Confirm the endpoint in the matrix matches your request shape.
- Send one small request before enabling production traffic.
- Treat
model_not_foundor unsupported-model errors as configuration errors. - Retry only temporary errors such as
429,503, and network timeouts.