Certified Models
As of October 2026, the AI Gateway has 268 certified models across 12 providers. Models are loaded from static JSON certification data (certified_models.json) on gateway startup. Models a vendor has retired leave the catalog: in October 2026 that took out OpenAI's GPT-3.5, GPT-4, GPT-4 Turbo, GPT-4.1 nano, o1, o3-mini, o4-mini, GPT Image 1, DALL-E and Sora models, Claude 3 Haiku, Opus 4, Opus 4.1 and Sonnet 4, Gemini 2.0, Gemma 3, Imagen 4 and Veo 2/3.0, and the retired Mistral, Cohere, xAI, DeepSeek, ElevenLabs and Runway models.
Important: The "Vendor Model" column below shows the vendor's model identifier (e.g., gpt-6.1-sol). When calling the AI Gateway API, you must use the Strongly-generated model ID (24-character hex string) assigned when you add a model to your account. Use the /v1/models endpoint to list your configured models and their Strongly IDs.
Model Types
Models are classified into the following types:
| Type | Description | Count |
|---|---|---|
multimodal | Vision Language Models: support both text and image inputs | 115 |
chat | Text-only chat/completion models | 35 |
embedding | Text vectorization for search/RAG | 20 |
text_to_speech | Audio synthesis models | 20 |
speech_to_text | Audio transcription models | 11 |
speech_to_speech | Voice conversion models | 2 |
realtime | Low-latency speech-to-speech conversation models | 8 |
image_generation | Image creation models | 37 |
video_generation | Video creation models | 9 |
music_generation | Music composition models | 1 |
audio_generation | Sound effects models | 1 |
moderation | Content filtering models | 3 |
rerank | Search result ranking models | 3 |
ocr | Document text and layout extraction models | 3 |
Multimodal vs Chat: Models that support image/vision input (GPT-4o, GPT-5, GPT-6, Claude, Gemini 2.5 and later, Mistral Large/Medium/Small, etc.) are classified as multimodal with vision: true in their capabilities. Text-only models remain as chat. Classification is determined dynamically from vendor APIs where possible (Mistral, Cohere, Gemini) and from the vendor's model documentation where APIs don't expose capability data (OpenAI, Anthropic, xAI, DeepSeek).
Who Can Use a Model
A model you connect or deploy is yours. Others reach it only when you share it from its Permissions tab:
| Access | Who | Can |
|---|---|---|
| Owner | You | Use, change and delete it |
| Can edit | Users you add with Can edit | Use, change and delete it |
| Can use | Users you add with Can use | Call it (chat, completions, embeddings, speech...), see its details and usage |
| Allow all users | Everyone on the platform | Call it |
Platform models (for example the built-in embedding model) can be used by everyone, and admins reach every model. On a multi-tenant platform, sharing applies within the model's organization, whose owners and admins can also use and change it.
The rule applies wherever a model is called: the model pickers in the builder, workflows, apps, workspaces, agents, STAN, the SDK and the REST API. A call naming a model you were not given is refused (403, naming the model), including a workflow that saved a model before it was unshared from you. A workflow, app or agent calls models as its owner, so what it may use is what its owner may use.
Summary by Provider
| Provider | Multimodal | Chat | Embedding | TTS | STT | Image | Video | Music | Other | Total |
|---|---|---|---|---|---|---|---|---|---|---|
| OpenAI | 65 | 8 | 3 | 7 | 7 | 9 | - | - | 10 | 109 |
| Anthropic | 14 | - | - | - | - | - | - | - | - | 14 |
| Google Gemini | 16 | 5 | 2 | 4 | - | 6 | 2 | - | - | 35 |
| Mistral | 17 | 4 | 4 | - | 4 | - | - | - | 4 | 33 |
| Cohere | 3 | 8 | 11 | - | - | - | - | - | 3 | 25 |
| Grok / xAI | - | 8 | - | - | - | 3 | - | - | - | 11 |
| DeepSeek | - | 2 | - | - | - | - | - | - | - | 2 |
| ElevenLabs | - | - | - | 9 | - | - | - | 1 | 3 | 13 |
| Stability AI | - | - | - | - | - | 8 | - | - | - | 8 |
| Black Forest Labs | - | - | - | - | - | 11 | - | - | - | 11 |
| Runway | - | - | - | - | - | - | 5 | - | - | 5 |
| Luma AI | - | - | - | - | - | - | 2 | - | - | 2 |
| Total | 115 | 35 | 20 | 20 | 11 | 37 | 9 | 1 | 20 | 268 |
OpenAI (109 models)
Multimodal Models (65)
Vision-capable models that support both text and image inputs. GPT-5 and GPT-6 models use OpenAI's Responses API (/v1/responses); the gateway handles this routing automatically.
| Vendor Model | Display Name | Capabilities |
|---|---|---|
openai/gpt-4.1 | GPT 4.1 | Vision, Function Calling, Web Search |
openai/gpt-4.1-2025-04-14 | GPT 4.1 2025 04 14 | Vision, Function Calling, Web Search |
openai/gpt-4.1-mini | GPT 4.1 mini | Vision, Function Calling, Web Search |
openai/gpt-4.1-mini-2025-04-14 | GPT 4.1 mini 2025 04 14 | Vision, Function Calling, Web Search |
openai/gpt-4o | GPT 4o | Vision, Function Calling, Web Search |
openai/gpt-4o-2024-08-06 | GPT 4o 2024 08 06 | Vision, Function Calling, Web Search |
openai/gpt-4o-2024-11-20 | GPT 4o 2024 11 20 | Vision, Function Calling, Web Search |
openai/gpt-4o-mini | GPT 4o mini | Vision, Function Calling, Web Search |
openai/gpt-4o-mini-2024-07-18 | GPT 4o mini 2024 07 18 | Vision, Function Calling, Web Search |
openai/gpt-4o-mini-search-preview | GPT 4o mini search preview | - |
openai/gpt-4o-mini-search-preview-2025-03-11 | GPT 4o mini search preview 2025 03 11 | - |
openai/gpt-4o-search-preview | GPT 4o search preview | - |
openai/gpt-4o-search-preview-2025-03-11 | GPT 4o search preview 2025 03 11 | - |
openai/gpt-5 | GPT 5 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-2025-08-07 | GPT 5 2025 08 07 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-chat-latest | GPT 5 chat latest | Vision, Function Calling |
openai/gpt-5-codex | GPT 5 codex | Vision, Function Calling, Reasoning |
openai/gpt-5-mini | GPT 5 mini | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-mini-2025-08-07 | GPT 5 mini 2025 08 07 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-nano | GPT 5 nano | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-nano-2025-08-07 | GPT 5 nano 2025 08 07 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-pro | GPT 5 pro | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-pro-2025-10-06 | GPT 5 pro 2025 10 06 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5-search-api | GPT 5 search api | Web Search |
openai/gpt-5-search-api-2025-10-14 | GPT 5 search api 2025 10 14 | Web Search |
openai/gpt-5.1 | GPT 5.1 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.1-2025-11-13 | GPT 5.1 2025 11 13 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.1-chat-latest | GPT 5.1 chat latest | Vision, Function Calling |
openai/gpt-5.1-codex | GPT 5.1 codex | Vision, Function Calling, Reasoning |
openai/gpt-5.1-codex-max | GPT 5.1 codex max | Vision, Function Calling, Reasoning |
openai/gpt-5.1-codex-mini | GPT 5.1 codex mini | Vision, Function Calling, Reasoning |
openai/gpt-5.2 | GPT 5.2 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.2-2025-12-11 | GPT 5.2 2025 12 11 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.2-codex | GPT 5.2 codex | Vision, Function Calling, Reasoning |
openai/gpt-5.2-pro | GPT 5.2 pro | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.2-pro-2025-12-11 | GPT 5.2 pro 2025 12 11 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.3-codex | GPT 5.3 codex | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4 | GPT 5.4 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-2026-03-05 | GPT 5.4 2026 03 05 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-mini | GPT 5.4 mini | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-mini-2026-03-17 | GPT 5.4 mini 2026 03 17 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-nano | GPT 5.4 Nano | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-nano-2026-03-17 | GPT 5.4 Nano (2026-03-17) | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-pro | GPT 5.4 Pro | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.4-pro-2026-03-05 | GPT 5.4 Pro (2026-03-05) | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.5 | GPT 5.5 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.5-2026-04-23 | GPT 5.5 2026 04 23 | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.5-pro | GPT 5.5 Pro | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.5-pro-2026-04-23 | GPT 5.5 Pro (2026-04-23) | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.6-cyber | GPT 5.6 Cyber | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.6-luna | GPT 5.6 Luna | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.6-sol | GPT 5.6 Sol | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-5.6-terra | GPT 5.6 Terra | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-6-astra | GPT 6 Astra | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-6-luna | GPT 6 Luna | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-6-sol | GPT 6 Sol | Vision, Function Calling, Reasoning, Web Search |
openai/gpt-6.1-sol | GPT 6.1 Sol | Vision, Function Calling, Reasoning, Web Search |
openai/o3 | o3 | Vision, Function Calling, Reasoning, Web Search |
openai/o3-2025-04-16 | o3 2025 04 16 | Vision, Function Calling, Reasoning, Web Search |
openai/o3-deep-research | o3 deep research | Vision, Function Calling, Reasoning |
openai/o3-deep-research-2025-06-26 | o3 deep research 2025 06 26 | Vision, Function Calling, Reasoning |
openai/o3-pro | o3 pro | Vision, Function Calling, Reasoning, Web Search |
openai/o3-pro-2025-06-10 | o3 pro 2025 06 10 | Vision, Function Calling, Reasoning, Web Search |
openai/o4-mini-deep-research | o4 mini deep research | Vision, Function Calling, Reasoning |
openai/o4-mini-deep-research-2025-06-26 | o4 mini deep research 2025 06 26 | Vision, Function Calling, Reasoning |
Chat Models (8)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
openai/computer-use-preview | computer use preview | Vision, Function Calling |
openai/computer-use-preview-2025-03-11 | computer use preview 2025 03 11 | Vision, Function Calling |
openai/gpt-audio | GPT audio | Function Calling |
openai/gpt-audio-1.5 | GPT audio 1.5 | Function Calling |
openai/gpt-audio-2025-08-28 | GPT audio 2025 08 28 | Function Calling |
openai/gpt-audio-mini | GPT audio mini | Function Calling |
openai/gpt-audio-mini-2025-10-06 | GPT audio mini 2025 10 06 | Function Calling |
openai/gpt-audio-mini-2025-12-15 | GPT audio mini 2025 12 15 | Function Calling |
Embedding Models (3)
| Vendor Model | Display Name |
|---|---|
openai/text-embedding-3-large | text embedding 3 large |
openai/text-embedding-3-small | text embedding 3 small |
openai/text-embedding-ada-002 | text embedding ada 002 |
Text-to-Speech Models (7)
| Vendor Model | Display Name |
|---|---|
openai/gpt-4o-mini-tts | GPT 4o mini TTS |
openai/gpt-4o-mini-tts-2025-03-20 | GPT 4o mini TTS 2025 03 20 |
openai/gpt-4o-mini-tts-2025-12-15 | GPT 4o mini TTS 2025 12 15 |
openai/tts-1 | TTS 1 |
openai/tts-1-1106 | TTS 1 1106 |
openai/tts-1-hd | TTS 1 hd |
openai/tts-1-hd-1106 | TTS 1 hd 1106 |
Speech-to-Text Models (7)
| Vendor Model | Display Name |
|---|---|
openai/gpt-4o-mini-transcribe | GPT 4o mini transcribe |
openai/gpt-4o-mini-transcribe-2025-03-20 | GPT 4o mini transcribe 2025 03 20 |
openai/gpt-4o-mini-transcribe-2025-12-15 | GPT 4o mini transcribe 2025 12 15 |
openai/gpt-4o-transcribe | GPT 4o transcribe |
openai/gpt-4o-transcribe-diarize | GPT 4o transcribe diarize |
openai/gpt-transcribe | GPT transcribe |
openai/whisper-1 | Whisper 1 |
Realtime Models (8)
| Vendor Model | Display Name |
|---|---|
openai/gpt-realtime | GPT realtime |
openai/gpt-realtime-1.5 | GPT realtime 1.5 |
openai/gpt-realtime-2 | GPT realtime 2 |
openai/gpt-realtime-2.1 | GPT realtime 2.1 |
openai/gpt-realtime-2.1-mini | GPT realtime 2.1 mini |
openai/gpt-realtime-2025-08-28 | GPT realtime 2025 08 28 |
openai/gpt-realtime-mini | GPT realtime mini |
openai/gpt-realtime-mini-2025-12-15 | GPT realtime mini 2025 12 15 |
Image Generation Models (9)
| Vendor Model | Display Name |
|---|---|
openai/chatgpt-image-latest | chatGPT image latest |
openai/gpt-image-1-mini | GPT image 1 mini |
openai/gpt-image-1.5 | GPT image 1.5 |
openai/gpt-image-2 | GPT image 2 |
openai/gpt-image-2-2026-04-21 | GPT image 2 2026 04 21 |
openai/gpt-image-2.5-flare | GPT image 2.5 Flare |
openai/gpt-image-2.5-flare-2026-09-08 | GPT image 2.5 Flare 2026 09 08 |
openai/gpt-image-2.5-sunburst | GPT image 2.5 Sunburst |
openai/gpt-image-2.5-sunburst-2026-09-08 | GPT image 2.5 Sunburst 2026 09 08 |
Moderation Models (2)
| Vendor Model | Display Name |
|---|---|
openai/omni-moderation-2024-09-26 | omni moderation 2024 09 26 |
openai/omni-moderation-latest | omni moderation latest |
Anthropic (14 models)
Multimodal Models (14)
Every current Claude model supports vision (image input).
| Vendor Model | Display Name | Capabilities |
|---|---|---|
anthropic/claude-fable-5 | Claude Fable 5 | Vision, Function Calling, Web Search |
anthropic/claude-fable-5-1 | Claude Fable 5.1 | Vision, Function Calling, Web Search |
anthropic/claude-haiku-4-5-20251001 | Claude Haiku 4.5 | Vision, Function Calling, Web Search |
anthropic/claude-haiku-5-5 | Claude Haiku 5.5 | Vision, Function Calling, Web Search |
anthropic/claude-opus-4-5-20251101 | Claude Opus 4.5 | Vision, Function Calling, Web Search |
anthropic/claude-opus-4-6 | Claude Opus 4.6 | Vision, Function Calling, Web Search |
anthropic/claude-opus-4-7 | Claude Opus 4.7 | Vision, Function Calling, Web Search |
anthropic/claude-opus-4-8 | Claude Opus 4.8 | Vision, Function Calling, Web Search |
anthropic/claude-opus-5 | Claude Opus 5 | Vision, Function Calling, Web Search |
anthropic/claude-opus-5-5 | Claude Opus 5.5 | Vision, Function Calling, Web Search |
anthropic/claude-sonnet-4-5-20250929 | Claude Sonnet 4.5 | Vision, Function Calling, Web Search |
anthropic/claude-sonnet-4-6 | Claude Sonnet 4.6 | Vision, Function Calling, Web Search |
anthropic/claude-sonnet-5 | Claude Sonnet 5 | Vision, Function Calling, Web Search |
anthropic/claude-sonnet-5-5 | Claude Sonnet 5.5 | Vision, Function Calling, Web Search |
Google Gemini (35 models)
Multimodal Models (16)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
gemini/gemini-2.5-flash | Gemini 2.5 Flash | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-2.5-flash-lite | Gemini 2.5 Flash-Lite | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-2.5-pro | Gemini 2.5 Pro | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3-flash-preview | Gemini 3 Flash Preview | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.1-flash-lite | Gemini 3.1 Flash Lite | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.1-pro-preview | Gemini 3.1 Pro Preview | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.1-pro-preview-customtools | Gemini 3.1 Pro Preview Custom Tools | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.5-flash | Gemini 3.5 Flash | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.5-flash-lite | Gemini 3.5 Flash Lite | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.6-flash | Gemini 3.6 Flash | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.7-flash | Gemini 3.7 Flash | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-3.8-flash | Gemini 3.8 Flash | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-flash-latest | Gemini Flash Latest | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-flash-lite-latest | Gemini Flash-Lite Latest | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-pro-latest | Gemini Pro Latest | Vision, Function Calling, Reasoning, Web Search |
gemini/gemini-robotics-er-2-preview | Gemini Robotics-ER 2 Preview | Vision, Function Calling, Reasoning, Web Search |
Chat Models (5)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
gemini/aqa | Model that performs Attributed Question Answering. | - |
gemini/deep-research-pro-preview-12-2025 | Deep Research Pro Preview (Dec-12-2025) | Vision |
gemini/gemini-2.5-flash-native-audio-latest | Gemini 2.5 Flash Native Audio Latest | Function Calling |
gemini/gemini-2.5-flash-native-audio-preview-09-2025 | Gemini 2.5 Flash Native Audio Preview 09-2025 | Function Calling |
gemini/gemini-2.5-flash-native-audio-preview-12-2025 | Gemini 2.5 Flash Native Audio Preview 12-2025 | Function Calling |
Embedding Models (2)
| Vendor Model | Display Name |
|---|---|
gemini/gemini-embedding-001 | Gemini Embedding 001 |
gemini/gemini-embedding-2 | Gemini Embedding 2 |
Text-to-Speech Models (4)
| Vendor Model | Display Name |
|---|---|
gemini/gemini-2.5-flash-preview-tts | Gemini 2.5 Flash Preview TTS |
gemini/gemini-2.5-pro-preview-tts | Gemini 2.5 Pro Preview TTS |
gemini/gemini-3.8-flash-lite-tts | Gemini 3.8 Flash Lite TTS |
gemini/gemini-3.8-flash-tts | Gemini 3.8 Flash TTS |
Image Generation Models (6)
| Vendor Model | Display Name |
|---|---|
gemini/gemini-2.5-flash-image | Nano Banana |
gemini/gemini-3-pro-image | Nano Banana Pro |
gemini/gemini-3.1-flash-image | Nano Banana 2 |
gemini/gemini-3.1-flash-lite-image | Nano Banana 2 Lite |
gemini/gemini-nano-banana-2.1 | Nano Banana 2.1 |
gemini/nano-banana-pro-preview | Nano Banana Pro |
Video Generation Models (2)
| Vendor Model | Display Name |
|---|---|
gemini/veo-3.1-fast-generate-preview | Veo 3.1 fast |
gemini/veo-3.1-generate-preview | Veo 3.1 |
Mistral (33 models)
Multimodal Models (17)
Vision-capable models, classified directly from Mistral's API capabilities.vision field.
| Vendor Model | Display Name | Capabilities |
|---|---|---|
mistral/magistral-medium-latest | mistral-medium-latest | Vision, Function Calling, Reasoning |
mistral/magistral-small-latest | mistral-small-2603 | Vision, Function Calling, Reasoning |
mistral/ministral-14b-2512 | ministral-14b-2512 | Vision, Function Calling |
mistral/ministral-14b-latest | ministral-14b-2512 | Vision, Function Calling |
mistral/ministral-3b-2512 | ministral-3b-2512 | Vision, Function Calling |
mistral/ministral-3b-latest | ministral-3b-2512 | Vision, Function Calling |
mistral/ministral-8b-2512 | ministral-8b-2512 | Vision, Function Calling |
mistral/ministral-8b-latest | ministral-8b-2512 | Vision, Function Calling |
mistral/mistral-large-2512 | mistral-large-2512 | Vision, Function Calling |
mistral/mistral-large-4 | mistral-large-4 | Vision, Function Calling |
mistral/mistral-large-latest | mistral-large-2512 | Vision, Function Calling |
mistral/mistral-medium | mistral-medium-latest | Vision, Function Calling |
mistral/mistral-medium-2604 | mistral-medium-latest | Vision, Function Calling |
mistral/mistral-medium-latest | mistral-medium-latest | Vision, Function Calling |
mistral/mistral-small-2603 | mistral-small-2603 | Vision, Function Calling |
mistral/mistral-small-latest | mistral-small-2603 | Vision, Function Calling |
mistral/mistral-vibe-cli-with-tools | mistral-medium-latest | Vision, Function Calling |
Chat Models (4)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
mistral/codestral-2508 | codestral-2508 | Function Calling |
mistral/codestral-latest | codestral-2508 | Function Calling |
mistral/mistral-vibe-cli-latest | mistral-medium-latest | Function Calling |
mistral/zai-glm-5-3 | zai-glm-5-3 | Function Calling |
Embedding Models (4)
| Vendor Model | Display Name |
|---|---|
mistral/codestral-embed | codestral-embed |
mistral/codestral-embed-2505 | codestral-embed |
mistral/mistral-embed | mistral-embed-2312 |
mistral/mistral-embed-2312 | mistral-embed-2312 |
Speech-to-Text Models (4)
| Vendor Model | Display Name |
|---|---|
mistral/voxtral-mini-2602 | voxtral-mini-2602 |
mistral/voxtral-mini-latest | voxtral-mini-2602 |
mistral/voxtral-small-2507 | voxtral-small-2507 |
mistral/voxtral-small-latest | voxtral-small-2507 |
Moderation Models (1)
| Vendor Model | Display Name |
|---|---|
mistral/mistral-moderation-2603 | mistral-moderation-2603 |
OCR Models (3)
| Vendor Model | Display Name |
|---|---|
mistral/mistral-ocr-2512 | mistral-ocr-2512 |
mistral/mistral-ocr-4-1 | mistral-ocr-latest |
mistral/mistral-ocr-latest | mistral-ocr-latest |
Cohere (25 models)
Multimodal Models (3)
Vision-capable models, classified from Cohere's API features list containing "vision".
| Vendor Model | Display Name | Capabilities |
|---|---|---|
cohere/c4ai-aya-vision-32b | c4ai aya vision 32b | Vision |
cohere/command-a-plus-05-2026 | command a plus 05 2026 | Vision, Function Calling, Reasoning |
cohere/command-a-vision-07-2025 | command a vision 07 2025 | Vision |
Chat Models (8)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
cohere/c4ai-aya-expanse-32b | c4ai aya expanse 32b | - |
cohere/command-a-03-2025 | command a 03 2025 | Function Calling, Reasoning |
cohere/command-a-reasoning-08-2025 | command a reasoning 08 2025 | Function Calling, Reasoning |
cohere/command-a-translate-08-2025 | command a translate 08 2025 | Function Calling, Reasoning |
cohere/command-r-08-2024 | command r 08 2024 | Function Calling |
cohere/command-r-plus-08-2024 | command r plus 08 2024 | Function Calling |
cohere/command-r7b-12-2024 | command r7b 12 2024 | Function Calling |
cohere/command-r7b-arabic-02-2025 | command r7b arabic 02 2025 | Function Calling |
Embedding Models (11)
| Vendor Model | Display Name |
|---|---|
cohere/embed-english-light-v3.0 | embed english light v3.0 |
cohere/embed-english-light-v3.0-image | embed english light v3.0 image |
cohere/embed-english-v3.0 | embed english v3.0 |
cohere/embed-english-v3.0-image | embed english v3.0 image |
cohere/embed-multilingual-light-v3.0 | embed multilingual light v3.0 |
cohere/embed-multilingual-light-v3.0-image | embed multilingual light v3.0 image |
cohere/embed-multilingual-v3.0 | embed multilingual v3.0 |
cohere/embed-multilingual-v3.0-image | embed multilingual v3.0 image |
cohere/embed-v4.0 | embed v4.0 |
cohere/embed-v5.0-fast | embed v5.0 fast |
cohere/embed-v5.0-pro | embed v5.0 pro |
Rerank Models (3)
| Vendor Model | Display Name |
|---|---|
cohere/rerank-multilingual-v3.0 | rerank multilingual v3.0 |
cohere/rerank-v4.0-fast | rerank v4.0 fast |
cohere/rerank-v4.0-pro | rerank v4.0 pro |
Grok / xAI (11 models)
Chat Models (8)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
grok/grok-4.20-0309-non-reasoning | grok 4.20 0309 non reasoning | Vision, Function Calling, Web Search |
grok/grok-4.20-0309-reasoning | grok 4.20 0309 reasoning | Vision, Function Calling, Reasoning, Web Search |
grok/grok-4.3 | grok 4.3 | Vision, Function Calling, Reasoning, Web Search |
grok/grok-4.5 | grok 4.5 | Vision, Function Calling, Reasoning, Web Search |
grok/grok-4.6 | grok 4.6 | Vision, Function Calling, Reasoning, Web Search |
grok/grok-4.7 | grok 4.7 | Vision, Function Calling, Reasoning, Web Search |
grok/grok-build-0.1 | grok build 0.1 | Function Calling, Reasoning, Web Search |
grok/grok-imagine-video | grok imagine video | - |
Image Generation Models (3)
| Vendor Model | Display Name |
|---|---|
grok/grok-imagine-image | grok imagine image |
grok/grok-imagine-image-2.0 | grok imagine image 2.0 |
grok/grok-imagine-image-quality | grok imagine image quality |
DeepSeek (2 models)
Chat Models (2)
| Vendor Model | Display Name | Capabilities |
|---|---|---|
deepseek/deepseek-flash | DeepSeek Flash | Function Calling, Reasoning |
deepseek/deepseek-v4-pro | DeepSeek V4 Pro | Function Calling, Reasoning |
ElevenLabs (13 models)
Text-to-Speech Models (9)
| Vendor Model | Display Name |
|---|---|
elevenlabs/eleven_flash_v2 | Eleven Flash v2 |
elevenlabs/eleven_flash_v2_5 | Eleven Flash v2.5 |
elevenlabs/eleven_multilingual_v2 | Eleven Multilingual v2 |
elevenlabs/eleven_turbo_v2 | Eleven Turbo v2 |
elevenlabs/eleven_turbo_v2_5 | Eleven Turbo v2.5 |
elevenlabs/eleven_v3 | Eleven v3 |
elevenlabs/eleven_v3_conversational | Eleven v3 Conversational |
elevenlabs/eleven_v4 | Eleven v4 |
elevenlabs/eleven_v4_turbo | Eleven v4 Turbo |
Speech-to-Speech Models (2)
| Vendor Model | Display Name |
|---|---|
elevenlabs/eleven_english_sts_v2 | Eleven English v2 |
elevenlabs/eleven_multilingual_sts_v2 | Eleven Multilingual v2 |
Music Generation Models (1)
| Vendor Model | Display Name |
|---|---|
elevenlabs/eleven_music | Eleven Music |
Audio Generation Models (1)
| Vendor Model | Display Name |
|---|---|
elevenlabs/sound-effects-v2 | Sound Effects v2 |
Stability AI (8 models)
Image Generation Models (8)
| Vendor Model | Display Name |
|---|---|
stability/sd3-large | Stable Diffusion 3 Large |
stability/sd3-large-turbo | Stable Diffusion 3 Large Turbo |
stability/sd3-medium | Stable Diffusion 3 Medium |
stability/sd3.5-large | Stable Diffusion 3.5 Large |
stability/sd3.5-large-turbo | Stable Diffusion 3.5 Large Turbo |
stability/sd3.5-medium | Stable Diffusion 3.5 Medium |
stability/stable-image-core | Stable Image Core |
stability/stable-image-ultra | Stable Image Ultra |
Black Forest Labs (11 models)
Image Generation Models (11)
| Vendor Model | Display Name |
|---|---|
bfl/flux-2-flex | FLUX.2 Flex |
bfl/flux-2-klein-4b | FLUX.2 Klein 4B |
bfl/flux-2-klein-9b | FLUX.2 Klein 9B |
bfl/flux-2-max | FLUX.2 Max |
bfl/flux-2-pro | FLUX.2 Pro |
bfl/flux-dev | FLUX Dev |
bfl/flux-kontext-max | FLUX Kontext Max |
bfl/flux-kontext-pro | FLUX Kontext Pro |
bfl/flux-pro | FLUX Pro |
bfl/flux-pro-1.1 | FLUX Pro 1.1 |
bfl/flux-pro-1.1-ultra | FLUX Pro 1.1 Ultra |
Runway (5 models)
Video Generation Models (5)
| Vendor Model | Display Name |
|---|---|
runway/act_two | Act Two |
runway/aleph2 | Aleph 2.0 |
runway/gen4.5 | Gen-4.5 |
runway/gen4_turbo | Gen-4 Turbo |
runway/upscale_v1 | Upscale V1 |
Luma AI (2 models)
Video Generation Models (2)
| Vendor Model | Display Name |
|---|---|
luma/ray-2 | Ray 2 |
luma/ray-flash-2 | Ray 2 Flash |
Model Capabilities Reference
Model Type Classification
| Type | Description | How Classified |
|---|---|---|
multimodal | Vision Language Models -- process text + image inputs | Mistral/Cohere: from API capability fields. OpenAI/Anthropic/Grok: pattern-based (APIs don't expose capabilities). Google: inferred from model version + generateContent support. |
chat | Text-only chat models | Fallback for models without vision capability |
embedding | Text vectorization models | From API or model ID pattern |
text_to_speech | Audio synthesis | From API or model ID pattern |
speech_to_text | Audio transcription | From API or model ID pattern |
image_generation | Image creation | From API or model ID pattern |
video_generation | Video creation | From API or model ID pattern |
moderation | Content filtering | From API or model ID pattern |
rerank | Search result ranking | From API endpoints |
ocr | Document text and layout extraction (Mistral OCR) | From model ID pattern |
realtime | Low-latency speech-to-speech | From model ID pattern |
Capability Definitions
| Capability | Description |
|---|---|
streaming | Supports streaming responses via SSE |
function_calling | Supports tool/function calling |
vision | Can process image inputs (set on all multimodal type models) |
json_mode | Guarantees valid JSON output |
structured_output | Supports structured output schemas |
reasoning | Extended thinking/reasoning capability |
code | Optimized for code generation |
rag | Optimized for retrieval-augmented generation |
Provider Capability Matrix
| Provider | Streaming | Functions | Vision/Multimodal | JSON | Reasoning |
|---|---|---|---|---|---|
| OpenAI | Yes | Yes | GPT-4o/4.1/5/6, o3/o4 | Yes | GPT-5/6, o3/o4 |
| Anthropic | Yes | Yes | All current Claude models | Yes | Adaptive thinking |
| Yes | Yes | Gemini 2.5/3.x | Yes | Thinking | |
| Mistral | Yes | Yes | Large 4/Medium 3.5/Small 4/Ministral | Yes | - |
| Cohere | Yes | Yes | Aya Vision 32B, Command A Vision, Command A Plus | Yes | Command A Reasoning |
| Grok | Yes | Yes | Grok 4.x | Yes | Grok 4.x |
| DeepSeek | Yes | Yes | - | Yes | V4 Pro, Flash (thinking) |
How Models Are Loaded
The certified models list is maintained as static JSON data:
- Models are discovered dynamically from vendor APIs via
run_discovery.py - Discovery classifies each model's type and capabilities using API data where available, pattern matching as fallback
- Results are written to
certified_models.json - On gateway startup, this JSON file is loaded into the database
- Organizations then add specific models to their account, receiving unique Strongly IDs
- Each model instance can have its own API key and configuration
To check for the latest models, use the /v1/models endpoint with no filters.