Documentação técnica

OpenAI-compatible models & endpoints

200+ OpenAI-compatible models and their vendor endpoints - Claude, OpenAI, Azure, Grok, Meta Llama, DeepSeek, AWS Bedrock, Qwen, Z.ai, and more.

Este artigo ainda não tem tradução revisada. O original em inglês é exibido para preservar comandos e etapas operacionais.

The AI-FW Model Inventory accepts any OpenAI-compatible backend URL. This reference lists representative current model IDs and endpoints for the major vendors, checked against each vendor's public model documentation on 2 October 2026. Model IDs change frequently, so always verify against the vendor's live model list before configuring a model.

The live model-list endpoints are the authoritative source when a provider supports them. The lists below are deliberately representative rather than an attempt to freeze every preview, regional deployment, or dated snapshot.

Auth is Authorization: Bearer <key> unless noted. Claude models are reachable from OpenAI-compatible clients through the AI-FW Anthropic facade.

OpenAI#

Base URL: https://api.openai.com/v1

  • Use the live GET https://api.openai.com/v1/models response for the complete account-specific list.
  • GPT-6 family (current generation, 1.05M context, 128K max output):
    • gpt-6-astra: flagship for the most demanding work
    • gpt-6.1-sol: near-Astra performance for complex work at a lower cost
    • gpt-6-sol: earlier GPT-6 Sol release
    • gpt-6-luna: most efficient tier for focused, high-volume work
  • GPT-5.6 family (previous generation, still available): gpt-5.6-sol (alias gpt-5.6), gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.3-codex, gpt-5.2, gpt-5.1, gpt-5
  • Older stable families (verify): gpt-4.1, gpt-4.1-mini, gpt-4o, gpt-4o-mini, o4-mini
  • Specialized: gpt-5.6-cyber, gpt-image-2, gpt-realtime-2.1, gpt-realtime-2.1-mini, gpt-4o-mini-tts, gpt-transcribe, gpt-live-transcribe, gpt-4o-transcribe, gpt-4o-mini-transcribe
  • Embeddings: text-embedding-3-small, text-embedding-3-large
curl https://api.openai.com/v1/chat/completions -H "Authorization: Bearer $OPENAI_KEY" \
  -d '{"model":"gpt-6-luna","messages":[{"role":"user","content":"Hi"}]}'

Azure OpenAI / Microsoft Foundry#

Base URL: https://<resource>.openai.azure.com/openai/v1 (deployment-based, api-version required). Auth: api-key header.

  • Recent OpenAI generations are available as deployments, and Azure documents models through the GPT-5.6 family. Confirm which deployments and versions your subscription offers before pinning, since Foundry roll-outs lag the first-party API: gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.6, gpt-chat-latest, gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.4-nano, gpt-5.4-pro, gpt-5.3-chat, gpt-5.3-codex, gpt-5.2, gpt-5.2-chat, gpt-5.2-codex, gpt-5.1, gpt-5.1-chat, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.1-codex-mini, gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat, gpt-5-codex, sora-2, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, gpt-4o, gpt-4o-mini, gpt-4o-transcribe, gpt-4o-mini-transcribe, gpt-4o-mini-tts, gpt-4-turbo, codex-mini, computer-use-preview
  • Partner models sold by Azure: Grok (grok-4.6, grok-4.3, grok-4-20-reasoning, grok-4-20-non-reasoning, grok-4.1-fast-reasoning, grok-4.1-fast-non-reasoning, grok-4, grok-code-fast-1), Mistral (Mistral-Large-3, mistral-medium-3-5, mistral-document-ai-2512, mistral-ocr-4-0), Moonshot (Kimi-K2.7-Code, Kimi-K2.6, Kimi-K2.5), MAI-Image-2.5

Claude (Anthropic)#

Native base URL: https://api.anthropic.com (Anthropic /v1/messages format; auth x-api-key). Reachable from OpenAI-compatible clients via the AI-FW facade.

  • Current lineup, all 1M context with 128K max output:
    • claude-fable-5-1 (Claude Fable 5.1): most capable class, for demanding reasoning and long-horizon agentic work
    • claude-opus-5-5 (Claude Opus 5.5): Anthropic's recommended starting point for most workloads
    • claude-sonnet-5-5 (Claude Sonnet 5.5): fast, cost-effective tier
    • claude-haiku-5-5 (Claude Haiku 5.5): lowest-cost, highest-throughput tier
  • Legacy (still available): claude-opus-5, claude-sonnet-5, claude-fable-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-opus-4-5, claude-sonnet-4-6, claude-sonnet-4-5, claude-haiku-4-5 (dated claude-haiku-4-5-20251001)
  • A family ID tracks the latest snapshot; a dated ID pins one. Use dated IDs when reproducibility matters, and treat the Anthropic Models API as the authoritative source for exact IDs and capabilities.
  • On Bedrock the IDs carry the anthropic. prefix and differ from the native Anthropic IDs. Verify the enabled model list in the target AWS Region.

X (Grok)#

Base URL: https://api.x.ai/v1

  • grok-4.7, grok-4.6, grok-4.5, grok-4.3, grok-4.20, grok-4.20-0309-reasoning, grok-4.20-0309-non-reasoning, grok-4.20-multi-agent-0309, grok-build-0.1
  • Media: grok-imagine-image-2.0, grok-imagine-image, grok-imagine-image-pro, grok-imagine-image-quality, grok-imagine-video-1.5, grok-imagine-video, grok-voice-think-fast-2.0, grok-voice-transcribe-2.0
  • Aliases: <model> and <model>-latest track the newest release. Live list: GET https://api.x.ai/v1/models.

Meta (Llama)#

Meta has no first-party OpenAI-compatible API; Llama models are served by hosting partners:

  • Groq: https://api.groq.com/openai/v1 with llama-3.1-8b-instant, llama-3.3-70b-versatile
  • AWS Bedrock: meta.llama3-*, meta.llama3.1-*, meta.llama3.2-*, meta.llama3.3-*, meta.llama4-*
  • Together / Fireworks / DeepInfra / SambaNova: meta-llama/llama-3.3-70b-instruct and other Llama 3.x/4 families (verify IDs)

AWS Bedrock#

OpenAI-compatible via the Bedrock Runtime (InvokeModel/Converse) with accept: application/json; model IDs use provider prefixes.

  • Amazon: amazon.nova-* (Nova 2 Lite, Nova 2 Sonic, Nova Pro, Nova Premier, Nova Lite, Nova Micro, Nova Canvas, Nova Reel, Nova Sonic), amazon.titan-* (text embeddings, multimodal embeddings, image)
  • Anthropic: anthropic.claude-* (5.x, 4.x, 3.x as listed above)
  • Meta: meta.llama*; Mistral: mistral.*; Cohere: cohere.command-*, cohere.embed-*, cohere.rerank-*; AI21: ai21.jamba-*; DeepSeek: deepseek.*; xAI: grok-4.6, grok-4.3; Z.AI: zai.glm-*; OpenAI: openai.gpt-*; Qwen: qwen.*; NVIDIA, MiniMax, Moonshot, Stability, Writer, TwelveLabs also available.

DeepSeek#

Base URL (OpenAI format): https://api.deepseek.com (also /anthropic for Anthropic format)

  • Recommended: deepseek-flash (DeepSeek-V4.1-Flash)
  • Pro: deepseek-v4-pro
  • Legacy aliases: deepseek-v4-flash, deepseek-v4-flash-vision-exp may still be accepted but should not be used for new configuration. deepseek-chat and deepseek-reasoner are retired according to the current provider documentation.

Mistral#

Base URL: https://api.mistral.ai/v1

  • Representative current families: mistral-large-4-0, mistral-large-3-25-12, mistral-medium-3-5-26-04, mistral-medium-3-1-25-08, mistral-small-4-0-26-03, mistral-small-creative-25-12, magistral-medium-1-2-25-09, magistral-small-1-2-25-09, devstral-small-2-25-12, ministral-3-14b-25-12, ministral-3-8b-25-12, ministral-3-3b-25-12
  • Code and embeddings: codestral-25-08, codestral-embed-25-05, mistral-embed-23-12
  • Audio, OCR and safety: voxtral-mini-transcribe-26-02, voxtral-small-25-07, voxtral-tts-26-03, mistral-ocr-4-0, mistral-moderation-26-03, shieldstral-1-0
  • Also hosts third-party models, including Z.ai GLM: zai-glm-5-2, zai-glm-5-3
  • Mistral publishes versioned IDs rather than -latest aliases, so pin a dated ID and confirm it in the current catalog before deploying.

Google Gemini#

OpenAI-compatible base URL: https://generativelanguage.googleapis.com/v1beta/openai/

  • Current text families: gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-3.5-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3.1-pro, gemini-3.1-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite
  • Live and media: gemini-3.8-live, gemini-3.8-live-extended-thinking, gemini-3.1-flash-image, gemini-2.5-flash-image, veo-3.1-generate-preview
  • Embeddings: gemini-embedding-2, gemini-embedding-2-preview, gemini-embedding-001

Groq#

Base URL: https://api.groq.com/openai/v1

  • Production: llama-3.1-8b-instant, llama-3.3-70b-versatile, openai/gpt-oss-120b, openai/gpt-oss-20b, whisper-large-v3, whisper-large-v3-turbo; systems: groq/compound, groq/compound-mini
  • Preview: qwen/qwen3.6-27b, qwen/qwen3.8-27b, openai/gpt-oss-safeguard-20b, minimaxai/minimax-m2.7, canopylabs/orpheus-v1-english, meta-llama/llama-prompt-guard-2-*
  • Live list: GET https://api.groq.com/openai/v1/models

Qwen (Alibaba Cloud Model Studio / DashScope)#

OpenAI-compatible base URL: https://dashscope.aliyuncs.com/compatible-mode/v1

  • Text: qwen3.8-max, qwen3.7-plus, qwen3.8-flash
  • Omni/vision: qwen3.5-omni-plus, qwen3.5-omni-plus-realtime
  • Image/video: qwen-image-3.0-pro, wan2.7-image-pro, wan3.0-video, happyhorse-1.1-t2v, happyhorse-1.1-i2v, happyhorse-1.1-r2v
  • Audio: qwen-audio-3.0-tts-plus, qwen-audio-3.0-asr-flash-streaming, qwen-audio-3.0-asr-flash-filetrans, qwen-audio-3.0-realtime-plus
  • Embeddings: text-embedding-v4, qwen3.7-text-embedding, tongyi-embedding-vision-plus, qwen3-rerank
  • Third-party on Model Studio: deepseek-v4-pro, deepseek-v4-flash, kimi-k2.7-code, kimi-k3, glm-5.2, ZHIPU/GLM-5.3, MiniMax-M2.5
  • Also hosted on Groq (qwen/qwen3.6-27b, qwen/qwen3.8-27b) and Bedrock (qwen.*)

Z.ai (GLM)#

OpenAI-compatible base URL: https://open.bigmodel.cn/api/paas/v4 (Z.ai API)

  • Text: glm-5.3, glm-5.3-flash, glm-5.2, glm-5.1, glm-5, glm-4.7, glm-4.7-flash, glm-4.7-flashx, glm-4.6, glm-4.5, glm-4.5-x, glm-4.5-air, glm-4.5-airx, glm-4.5-flash, glm-4-32b-0414-128k
  • Vision: glm-4.6v, glm-4.6v-flash, glm-4.6v-flashx, glm-4.5v, autoglm-phone-multilingual
  • OCR/audio: glm-ocr, glm-asr-2512; media: glm-image, cogview-4, cogvideox-3
  • Also on Bedrock (zai.glm-*) and served by Mistral (zai-glm-5-2, zai-glm-5-3)

Other OpenAI-compatible hosts (verify IDs)#

VendorBase URLRepresentative models
OpenRouterhttps://openrouter.ai/api/v1450+ models: openai/gpt-6-astra, openai/gpt-6-luna, anthropic/claude-opus-5.5, google/gemini-3.8-flash, x-ai/grok-4.7, meta-llama/llama-3.3-70b-instruct, deepseek/deepseek-v4-pro, qwen/qwen3-*. Live list: GET https://openrouter.ai/api/v1/models
Together AIhttps://api.together.xyz/v1meta-llama/Llama-3.3-70B-Instruct-Turbo, Qwen/Qwen2.5-72B-Instruct, deepseek-ai/DeepSeek-V3
Fireworks AIhttps://api.fireworks.ai/inference/v1accounts/fireworks/models/llama-v3p3-70b-instruct, qwen2p5-72b-instruct, deepseek-v3
DeepInfrahttps://api.deepinfra.com/v1/openaimeta-llama/Llama-3.3-70B-Instruct, Qwen/Qwen2.5-72B-Instruct, deepseek-ai/DeepSeek-V3
Cerebrashttps://api.cerebras.ai/v1llama-3.3-70b, llama3.1-8b, gpt-oss-120b
NVIDIA NIMhttps://integrate.api.nvidia.com/v1meta/llama-3.3-70b-instruct, nvidia/llama-3.1-nemotron-*, deepseek-ai/deepseek-r1
SambaNovahttps://api.sambanova.ai/v1Meta-Llama-3.3-70B-Instruct, Qwen/Qwen3-235B-A22B
Novita AIhttps://api.novita.ai/v3/openaimeta-llama/llama-3.3-70b-instruct, qwen/qwen-2.5-72b-instruct
Perplexityhttps://api.perplexity.aisonar-pro, sonar
Ollama (local)http://localhost:11434/v1any pulled tag, e.g. llama3.3, qwen3
LM Studio (local)http://localhost:1234/v1any loaded model
vLLM (self-host)http://<host>:8000/v1any served model
How to use with AI-FW

Register any of these backend URLs in the Model Inventory with the matching model ID and provider key, then route traffic through the gateway. See Configure models & keys.

Where to go next#

Próximas leituras