Quotaflow
llms.txtOpenAPIDashboard
Model Library

Quotaflow Model Library — supported AI models by use case

Choose the right Quotaflow model for chat, agents, code, embeddings, image generation, image editing, and video generation. The catalog below is organized like a product model library: start with your use case, pick a curated model family, then open the endpoint-specific reference.

Quotaflow Model Library
Quotaflow Model Library

What is the Quotaflow Model Library?

The Model Library is the customer-facing list of model ids and endpoint families that Quotaflow documents for production integrations. It explains what each model is good for, which protocol surface it uses, and which reference page has copy-pasteable API examples.

Your authenticated GET /models response is still the source of truth for your key. A package, beta flag, or product-scoped key can make your returned list smaller than the public catalog.

Why use Quotaflow model routing?

Quotaflow lets teams keep official-style request shapes while centralizing API keys, team usage, package limits, and model access in one control plane. That means you can point OpenAI-compatible, Anthropic-compatible, Gemini-compatible, and creative-media clients at Quotaflow without teaching every app a new billing or credential system.

Use this page when you need to answer three practical questions before shipping:

Curated models

CategoryStart withEndpoint familyBest forReference
GPT agentsgpt-5.4/openai/v1/responsesProduction agents, tool use, app reasoningResponses API
Fast GPT chatgpt-5.4-mini/responses, /chat/completionsUI chat, extraction, summaries, routingOpenAI-compatible models
Lightweight GPT routinggpt-5.4-nano/responses, /chat/completionsCost-sensitive simple chat, extraction, and routingOpenAI-compatible models
Coding agentsgpt-5.3-codex/responsesCodex-style repository work and agent tasksConnect Coding Agents
Embeddingstext-embedding-3-small, text-embedding-3-large, text-embedding-ada-002/embeddingsSearch, RAG, clustering, semantic matchingEmbeddings
OpenAI-style imagesgpt-image-2/images/generations, /images/editsProduct images, masked edits, marketing creativeGPT Image 2
Fast image iterationgemini-3.1-flash-image-preview/images/*, Gemini :generateContentDrafts, reference-image edits, many variantsGemini 3.1 Flash Image
Higher-quality image workgemini-3-pro-image-preview/images/*, Gemini :generateContentFinal creative candidates and detailed promptsGemini 3 Pro Image
Veo video generationveo-3.1-fast-generate-001/videosVeo-compatible async text-to-video and image-to-video tasksVeo 3.1 Fast
Seedance video generationseedance-2.0-fast/videosSeedance 2.0 text, image, portrait, and reference-media video tasksSeedance 2.0 Fast
Claude-compatible clientsclaude-sonnet-5, claude-sonnet-4-6, claude-opus-4-6, claude-sonnet-4-5, extended ids returned by /models/v1/messagesClaude-style coding and reasoning clientsMessages
GLM chatglm-5.2/openai/v1/chat/completionsOpenAI-compatible chat clients that need GLM text output; supports messages, streaming, and tools; strict JSON mode returns 400 invalid_request_errorChat Completions
Kimi coding chatkimi-k2.7-code/openai/v1/chat/completionsKimi text for coding, agent, long-context chat, streaming, tools, and strict JSON modeChat Completions
Gemini-compatible clientsgemini-3.5-flash, gemini-3.1-pro-preview, gemini-2.5-pro/v1beta/models/{model}:generateContent, /openai/v1/chat/completionsGemini text, multimodal, and reasoning-capable apps; Gemini-native features stay on generateContent/countTokensgenerateContent

Key features

How to choose a model

  1. Pick the protocol your client already speaks: OpenAI-compatible, Anthropic-compatible, or Gemini-compatible.
  2. Call the matching /models endpoint with the exact key your app will use.
  3. Choose the first curated model in the table for your category.
  4. Send a small non-streaming test request.
  5. Add a streaming, multipart, or async polling test if your production flow uses that capability.

Pricing and access

Model availability depends on your Quotaflow package and enabled product surfaces. If a model appears in this catalog but not in your authenticated /models response, ask your Quotaflow admin to enable that model family for the key or create a key scoped to the right product.

For creative media workloads, budget for longer runtimes than text calls. Image and video jobs should use client timeouts, retry policies, and UI pending states that match media-generation latency.

Use cases

Use caseRecommended path
Build a coding-agent gatewaygpt-5.3-codex with /responses, then follow Codex setup.
Add image editing to an ecommerce toolgpt-image-2 with /images/edits and masks for localized changes.
Create many visual concepts quicklygemini-3.1-flash-image-preview for fast variants, then optionally promote final candidates to a higher-quality image model.
Generate short social clipsveo-3.1-fast-generate-001 or seedance-2.0-fast with async /videos tasks and a polling UI.
Keep an existing Claude clientUse the Anthropic-compatible /v1/messages surface and a Claude-compatible model returned by your key.
Add GLM text chatUse glm-5.2 through /openai/v1/chat/completions after confirming it appears in /models; use messages, streaming, and tools, but do not send strict JSON mode.
Add Kimi coding chatUse kimi-k2.7-code through /openai/v1/chat/completions after confirming it appears in /models; streaming, tools, and strict JSON mode are supported on this chat path.

FAQ

How do I know which models my key can use?

Call GET https://api.quotaflow.ai/openai/v1/models for OpenAI-compatible keys, or the protocol-specific discovery endpoint for Anthropic-compatible and Gemini-compatible clients. Use the same key and base URL that your production app will use.

Are image and video models OpenAI-compatible?

Quotaflow exposes OpenAI-compatible image endpoints for image generation and edits. Video generation uses an OpenAI-style task endpoint where the create call returns a task id and the client polls for completion.

Do all keys include every model?

No. Keys can be scoped by product, package, customer, or beta access. Treat this page as the public catalog and /models as the exact enabled list for a specific key.

What happens if I send an unsupported model id?

The request fails with a model or configuration error. Update the configured model id or enable the model for the key; do not retry unsupported-model errors as transient failures.

Next steps