Holo3 35B A3b
oah/kimi-k2.5Deploy Holo3 35B A3b with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
by Multiple Providers (Open / Closed)
Beyond the major model families, AI Security Gateway supports a growing catalog of specialized and emerging models — Gemma, Kimi, MiniMax, Nvidia Nemotron, GLM, Sarvam, Devstral, and more. Every model gets the same enterprise-grade PII redaction, budget enforcement, and observability. Compare pricing across providers and deploy with two lines of code.
Every Other request is scanned for 30+ PII entity types — SSNs, credit cards, emails, API keys, and more — before it reaches any provider.
Other is available across 5 providers. Our Smart Router picks the cheapest one per-request. 25% managed markup / 0% on Pro BYOK.
Use the AISG SDK (pip install aisg) for typed metadata and error handling, or change two lines in your OpenAI SDK. Both work.
Per-request logging of token counts, latency, DLP violations, and cost. Never wonder what your AI spend is again.
oah/kimi-k2.5Deploy Holo3 35B A3b with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/lfm2Deploy LFM2-24B-A2B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m1-40kDeploy Minimax M1 40K with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m1-80kDeploy Minimax M1 80K with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m2Deploy MiniMax M2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m2.5-fp4Deploy MiniMax M2.5 FP4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m2.7Deploy MiniMax M2.7 FP4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m3Deploy MiniMax M3 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/deepcoder-14b-previewDeploy Deepcoder 14B Preview with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/molmo-7b-dDeploy Molmo 7B D 0924 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/trinity-miniDeploy Trinity Mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/cogito-v2-1Deploy Cogito v2.1 671B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/rnj-1Deploy EssentialAI Rnj-1 Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-2-27b-itDeploy Gemma-2 Instruct (27B) with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-2-9b-itDeploy Gemma 2 9B It with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-2b-itDeploy Gemma 2B It with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-1b-itDeploy Gemma 3 1b it with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-1b-ptDeploy Gemma 3 1B Pt with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-270m-itDeploy Gemma 3 270M It with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-270m-it-loraDeploy Gemma 3 270M It Lora with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-27b-itDeploy Gemma 3 27B It with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-27b-it-loraDeploy Gemma 3 27B It Lora with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-27b-ptDeploy Gemma 3 27B Pt with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-4b-itDeploy Gemma 3 4b it with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3n-e4b-itDeploy Gemma 3N E4B Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-4-26b-a4b-itDeploy Gemma 4 26B A4b It with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-4-31b-itDeploy Gemma 4 31B-it FP8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-4-31b-it-loraDeploy Gemma 4 31B It Lora with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-4-e2b-itDeploy Gemma 4 E2B-it with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-4-e4b-itDeploy Gemma 4 E4B-it with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/medgemma-27b-text-itDeploy Medgemma 27B Text It with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/kimi-k2.5-fp4Deploy Kimi K2.5 FP4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/kimi-k2.6Deploy Kimi K2.6 Fp4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/kimi-k2.7-codeDeploy Kimi K2.7 Code with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-3-nano-30b-a3b-bf16Deploy Nvidia Nemotron 3 Nano 30B A3b Bf16 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-3-super-120b-a12b-bf16Deploy Nvidia Nemotron 3 Super 120B A12b Bf16 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-3-superDeploy Nvidia Nemotron 3 Super 120B A12b Fp8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-nano-9b-v2Deploy Nvidia Nemotron Nano 9B V2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nemotron-3-nano-omni-30b-a3b-reasoningDeploy Nemotron 3 Nano Omni 30B A3b Reasoning Fp8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nemotron-3-ultraDeploy NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/sarvam-mDeploy Sarvam M with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/essentialai-rnj-1Deploy EssentialAI Rnj-1 Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-4.5-airDeploy Glm 4.5 Air Fp8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-4.5vDeploy GLM 4.5V with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-4.6Deploy GLM 4.6 Fp8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-4.7Deploy GLM 4.7 FP8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-4.7-fp4Deploy GLM 4.7 FP4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-5Deploy GLM 5 Fp4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-5-fp4Deploy GLM 5 Fp4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-5.1Deploy GLM 5.1 FP4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-ocrDeploy GLM OCR with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/voxtral-mini-transcribeDeploy devstral-2512 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/devstralDeploy devstral-latest with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/devstral-mediumDeploy devstral-medium-2507 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/labs-leanstralDeploy labs-leanstral-2603 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/magistral-mediumDeploy magistral-medium-2509 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/ministralDeploy ministral-14b-2512 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/voxtral-miniDeploy voxtral-mini-2507 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/voxtral-mini-realtimeDeploy voxtral-mini-realtime-2602 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/voxtral-mini-transcribe-realtimeDeploy voxtral-mini-transcribe-realtime-2602 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/voxtral-mini-ttsDeploy voxtral-mini-tts-2603 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/voxtral-smallDeploy voxtral-small-2507 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/antigravity-preview-05Deploy Antigravity Agent Preview with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/deep-research-preview-04Deploy Deep Research Preview (Apr-21-2026) with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/deep-research-pro-preview-12Deploy Deep Research Pro Preview (Dec-12-2025) with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/lyria-3-clip-previewDeploy Lyria 3 Clip Preview with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/lyria-3-pro-previewDeploy Lyria 3 Pro Preview with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nano-banana-pro-previewDeploy Nano Banana Pro with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-nano-9bDeploy BAAI/bge-base-en-v1.5 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/bge-en-iclDeploy BAAI/bge-en-icl with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/bge-large-enDeploy BAAI/bge-large-en-v1.5 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/bge-m3Deploy BAAI/bge-m3 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/bge-m3-multiDeploy BAAI/bge-m3-multi with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/bria-3.2Deploy Bria/Bria-3.2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/bria-3.2-vectorDeploy Bria/Bria-3.2-vector with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/fiboDeploy Bria/fibo with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/seed-1.8Deploy ByteDance/Seed-1.8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/seed-2.0-codeDeploy ByteDance/Seed-2.0-code with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/seed-2.0-miniDeploy ByteDance/Seed-2.0-mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/seed-2.0-proDeploy ByteDance/Seed-2.0-pro with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/seedream-4Deploy ByteDance/Seedream-4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/mythomax-l2Deploy Gryphe/MythoMax-L2-13b with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/minimax-m2.5Deploy MiniMaxAI/MiniMax-M2.5 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/p-imageDeploy PrunaAI/p-image with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/chatterbox-multilingualDeploy ResembleAI/chatterbox-multilingual with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/chatterboxDeploy ResembleAI/chatterbox-turbo with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/l3-8b-lunarisDeploy Sao10K/L3-8B-Lunaris-v1-Turbo with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/l3.1-70b-euryaleDeploy Sao10K/L3.1-70B-Euryale-v2.2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/wan2.6-t2iDeploy Wan-AI/Wan2.6-T2I with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/mimoDeploy XiaomiMiMo/MiMo-V2.5 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/mimo-v2.5-proDeploy XiaomiMiMo/MiMo-V2.5-Pro with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/mimo-v2.5-tts-voicedesignDeploy XiaomiMiMo/MiMo-V2.5-tts-voicedesign with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gemma-3-12b-itDeploy google/gemma-3-12b-it with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/e5-baseDeploy intfloat/e5-base-v2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/e5-largeDeploy intfloat/e5-large-v2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/multilingual-e5-largeDeploy intfloat/multilingual-e5-large with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/phi-4Deploy microsoft/phi-4 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-3-ultraDeploy nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nvidia-nemotron-3-ultra-550b-a55b-bf16Deploy nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nemotron-3-nanoDeploy nvidia/Nemotron-3-Nano-30B-A3B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nemotron-3.5-asr-streaming-multilingual-0.6bDeploy nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/nemotron-content-safety-3.5Deploy nvidia/Nemotron-Content-Safety-3.5 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/whisper-large-v3Deploy openai/whisper-large-v3 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/all-minilm-l12Deploy sentence-transformers/all-MiniLM-L12-v2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/all-minilm-l6Deploy sentence-transformers/all-MiniLM-L6-v2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/all-mpnet-baseDeploy sentence-transformers/all-mpnet-base-v2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/clip-vit-b-32Deploy sentence-transformers/clip-ViT-B-32 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/clip-vit-b-32-multilingualDeploy sentence-transformers/clip-ViT-B-32-multilingual-v1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/multi-qa-mpnet-base-dotDeploy sentence-transformers/multi-qa-mpnet-base-dot-v1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/paraphrase-minilm-l6Deploy sentence-transformers/paraphrase-MiniLM-L6-v2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/csmDeploy sesame/csm-1b with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/text2vec-base-chineseDeploy shibing624/text2vec-base-chinese with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/step-3.5-flashDeploy stepfun-ai/Step-3.5-Flash with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/step-3.7-flashDeploy stepfun-ai/Step-3.7-Flash with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gte-baseDeploy thenlper/gte-base with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/gte-largeDeploy thenlper/gte-large with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/glm-4.7-flashDeploy zai-org/GLM-4.7-Flash with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/dall-e-3Deploy babbage-002 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/chatDeploy chat-latest with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/davinci-002Deploy davinci-002 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o1Deploy o1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o1-2024-12-17Deploy o1-2024-12-17 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o1-proDeploy o1-pro with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o1-pro-2025-03-19Deploy o1-pro-2025-03-19 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o3Deploy o3 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o3-2025-04-16Deploy o3-2025-04-16 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o3-miniDeploy o3-mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o3-mini-2025-01-31Deploy o3-mini-2025-01-31 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o4-miniDeploy o4-mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o4-mini-2025-04-16Deploy o4-mini-2025-04-16 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o4-mini-deep-researchDeploy o4-mini-deep-research with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/o4-mini-deep-research-2025-06-26Deploy o4-mini-deep-research-2025-06-26 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/sora-2Deploy sora-2 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
oah/sora-2-proDeploy sora-2-pro with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Input / Output pricing by provider. Managed Mode adds a 25% managed markup. Pro BYOK = 0% markup.
| Model | Params | Context | Vision | Together.ai | DeepInfra | Mistral AI | Google Gemini | OpenAI |
|---|---|---|---|---|---|---|---|---|
Holo3 35B A3b oah/kimi-k2.5 | — | 262K | No | — | — | — | — | — |
LFM2-24B-A2B oah/lfm2 | — | 33K | No | $0.03/$0.12 | — | — | — | — |
Minimax M1 40K oah/minimax-m1-40k | — | 1.0M | No | — | — | — | — | — |
Minimax M1 80K oah/minimax-m1-80k | — | 1.0M | No | — | — | — | — | — |
MiniMax M2 oah/minimax-m2 | — | 197K | No | — | — | — | — | — |
MiniMax M2.5 FP4 oah/minimax-m2.5-fp4 | — | 8K | No | — | — | — | — | — |
MiniMax M2.7 FP4 oah/minimax-m2.7 | — | 197K | No | $0.30/$1.20 | — | — | — | — |
MiniMax M3 oah/minimax-m3 | — | 524K | No | $0.30/$1.20 | — | — | — | — |
Deepcoder 14B Preview oah/deepcoder-14b-preview | — | 131K | No | — | — | — | — | — |
Molmo 7B D 0924 oah/molmo-7b-d | — | 4K | No | — | — | — | — | — |
Trinity Mini oah/trinity-mini | — | 128K | No | $0.05/$0.15 | — | — | — | — |
Cogito v2.1 671B oah/cogito-v2-1 | — | 164K | No | $1.25/$1.25 | — | — | — | — |
EssentialAI Rnj-1 Instruct oah/rnj-1 | — | 33K | No | $0.15/$0.15 | — | — | — | — |
Gemma-2 Instruct (27B) oah/gemma-2-27b-it | — | 8K | No | $0.80/$0.80 | — | — | — | — |
Gemma 2 9B It oah/gemma-2-9b-it | — | 8K | No | — | — | — | — | — |
Gemma 2B It oah/gemma-2b-it | — | 8K | No | — | — | — | — | — |
Gemma 3 1b it oah/gemma-3-1b-it | — | 33K | No | — | — | — | — | — |
Gemma 3 1B Pt oah/gemma-3-1b-pt | — | 33K | No | — | — | — | — | — |
Gemma 3 270M It oah/gemma-3-270m-it | — | 33K | No | — | — | — | — | — |
Gemma 3 270M It Lora oah/gemma-3-270m-it-lora | — | 33K | No | — | — | — | — | — |
Gemma 3 27B It oah/gemma-3-27b-it | — | 66K | No | — | $0.09/$0.16 | — | — | — |
Gemma 3 27B It Lora oah/gemma-3-27b-it-lora | — | — | No | — | — | — | — | — |
Gemma 3 27B Pt oah/gemma-3-27b-pt | — | — | No | — | — | — | — | — |
Gemma 3 4b it oah/gemma-3-4b-it | — | 66K | No | — | $0.04/$0.08 | — | — | — |
Gemma 3N E4B Instruct oah/gemma-3n-e4b-it | — | 33K | No | $0.06/$0.12 | — | — | — | — |
Gemma 4 26B A4b It oah/gemma-4-26b-a4b-it | — | 262K | No | — | — | — | — | — |
Gemma 4 31B-it FP8 oah/gemma-4-31b-it | — | 262K | No | $0.28/$0.86 | — | — | — | — |
Gemma 4 31B It Lora oah/gemma-4-31b-it-lora | — | 262K | No | — | — | — | — | — |
Gemma 4 E2B-it oah/gemma-4-e2b-it | — | 131K | No | — | — | — | — | — |
Gemma 4 E4B-it oah/gemma-4-e4b-it | — | 131K | No | — | — | — | — | — |
Medgemma 27B Text It oah/medgemma-27b-text-it | — | 131K | No | — | — | — | — | — |
Kimi K2.5 FP4 oah/kimi-k2.5-fp4 | — | 262K | No | $0.50/$2.80 | — | — | — | — |
Kimi K2.6 Fp4 oah/kimi-k2.6 | — | 262K | No | $1.20/$4.50 | — | — | — | — |
Kimi K2.7 Code oah/kimi-k2.7-code | — | 262K | No | $0.95/$4.00 | — | — | — | — |
Nvidia Nemotron 3 Nano 30B A3b Bf16 oah/nvidia-nemotron-3-nano-30b-a3b-bf16 | — | 262K | No | — | — | — | — | — |
Nvidia Nemotron 3 Super 120B A12b Bf16 oah/nvidia-nemotron-3-super-120b-a12b-bf16 | — | 262K | No | — | — | — | — | — |
Nvidia Nemotron 3 Super 120B A12b Fp8 oah/nvidia-nemotron-3-super | — | 262K | No | — | — | — | — | — |
Nvidia Nemotron Nano 9B V2 oah/nvidia-nemotron-nano-9b-v2 | — | 131K | No | $0.06/$0.25 | — | — | — | — |
Nemotron 3 Nano Omni 30B A3b Reasoning Fp8 oah/nemotron-3-nano-omni-30b-a3b-reasoning | — | 131K | No | — | — | — | — | — |
NVIDIA Nemotron 3 Ultra 550B A55B NVFP4 oah/nemotron-3-ultra | — | 512K | No | $0.60/$3.60 | — | — | — | — |
Sarvam M oah/sarvam-m | — | 33K | No | — | — | — | — | — |
EssentialAI Rnj-1 Instruct oah/essentialai-rnj-1 | — | 33K | No | — | — | — | — | — |
Glm 4.5 Air Fp8 oah/glm-4.5-air | — | 131K | No | $0.20/$1.10 | — | — | — | — |
GLM 4.5V oah/glm-4.5v | — | 66K | No | — | — | — | — | — |
GLM 4.6 Fp8 oah/glm-4.6 | — | 203K | No | $0.60/$2.20 | — | — | — | — |
GLM 4.7 FP8 oah/glm-4.7 | — | 203K | No | $0.45/$2.00 | — | — | — | — |
GLM 4.7 FP4 oah/glm-4.7-fp4 | — | 203K | No | — | — | — | — | — |
GLM 5 Fp4 oah/glm-5 | — | 203K | No | $1.00/$3.20 | — | — | — | — |
GLM 5 Fp4 oah/glm-5-fp4 | — | 203K | No | — | — | — | — | — |
GLM 5.1 FP4 oah/glm-5.1 | — | 203K | No | $1.40/$4.40 | — | — | — | — |
GLM OCR oah/glm-ocr | — | 131K | No | — | — | — | — | — |
devstral-2512 oah/voxtral-mini-transcribe | — | — | No | — | — | $0.40/$2.00 | — | — |
devstral-latest oah/devstral | — | — | No | — | — | $0.40/$2.00 | — | — |
devstral-medium-2507 oah/devstral-medium | — | — | No | — | — | $0.40/$2.00 | — | — |
labs-leanstral-2603 oah/labs-leanstral | — | — | Yes | — | — | — | — | — |
magistral-medium-2509 oah/magistral-medium | — | — | Yes | — | — | $2.00/$5.00 | — | — |
ministral-14b-2512 oah/ministral | — | — | Yes | — | — | — | — | — |
voxtral-mini-2507 oah/voxtral-mini | — | — | No | — | — | — | — | — |
voxtral-mini-realtime-2602 oah/voxtral-mini-realtime | — | — | No | — | — | — | — | — |
voxtral-mini-transcribe-realtime-2602 oah/voxtral-mini-transcribe-realtime | — | — | No | — | — | — | — | — |
voxtral-mini-tts-2603 oah/voxtral-mini-tts | — | — | No | — | — | — | — | — |
voxtral-small-2507 oah/voxtral-small | — | — | No | — | — | — | — | — |
Antigravity Agent Preview oah/antigravity-preview-05 | — | 131K | Yes | — | — | — | — | — |
Deep Research Preview (Apr-21-2026) oah/deep-research-preview-04 | — | 131K | Yes | — | — | — | — | — |
Deep Research Pro Preview (Dec-12-2025) oah/deep-research-pro-preview-12 | — | 131K | Yes | — | — | — | $2.00/$12.00 | — |
Lyria 3 Clip Preview oah/lyria-3-clip-preview | — | 1.0M | Yes | — | — | — | Free/Free | — |
Lyria 3 Pro Preview oah/lyria-3-pro-preview | — | 1.0M | Yes | — | — | — | Free/Free | — |
Nano Banana Pro oah/nano-banana-pro-preview | — | 131K | Yes | — | — | — | — | — |
BAAI/bge-base-en-v1.5 oah/nvidia-nemotron-nano-9b | — | — | No | — | — | — | — | — |
BAAI/bge-en-icl oah/bge-en-icl | — | — | No | — | — | — | — | — |
BAAI/bge-large-en-v1.5 oah/bge-large-en | — | — | No | — | — | — | — | — |
BAAI/bge-m3 oah/bge-m3 | — | — | No | — | — | — | — | — |
BAAI/bge-m3-multi oah/bge-m3-multi | — | — | No | — | — | — | — | — |
Bria/Bria-3.2 oah/bria-3.2 | — | — | No | — | — | — | — | — |
Bria/Bria-3.2-vector oah/bria-3.2-vector | — | — | No | — | — | — | — | — |
Bria/fibo oah/fibo | — | — | No | — | — | — | — | — |
ByteDance/Seed-1.8 oah/seed-1.8 | — | — | No | — | — | — | — | — |
ByteDance/Seed-2.0-code oah/seed-2.0-code | — | — | No | — | — | — | — | — |
ByteDance/Seed-2.0-mini oah/seed-2.0-mini | — | — | No | — | — | — | — | — |
ByteDance/Seed-2.0-pro oah/seed-2.0-pro | — | — | No | — | — | — | — | — |
ByteDance/Seedream-4 oah/seedream-4 | — | — | No | — | — | — | — | — |
Gryphe/MythoMax-L2-13b oah/mythomax-l2 | — | — | No | — | $0.08/$0.09 | — | — | — |
MiniMaxAI/MiniMax-M2.5 oah/minimax-m2.5 | — | — | No | — | — | — | — | — |
PrunaAI/p-image oah/p-image | — | — | No | — | — | — | — | — |
ResembleAI/chatterbox-multilingual oah/chatterbox-multilingual | — | — | No | — | — | — | — | — |
ResembleAI/chatterbox-turbo oah/chatterbox | — | — | No | — | — | — | — | — |
Sao10K/L3-8B-Lunaris-v1-Turbo oah/l3-8b-lunaris | — | — | No | — | $0.04/$0.05 | — | — | — |
Sao10K/L3.1-70B-Euryale-v2.2 oah/l3.1-70b-euryale | — | — | No | — | $0.65/$0.75 | — | — | — |
Wan-AI/Wan2.6-T2I oah/wan2.6-t2i | — | — | No | — | — | — | — | — |
XiaomiMiMo/MiMo-V2.5 oah/mimo | — | — | No | — | — | — | — | — |
XiaomiMiMo/MiMo-V2.5-Pro oah/mimo-v2.5-pro | — | — | No | — | — | — | — | — |
XiaomiMiMo/MiMo-V2.5-tts-voicedesign oah/mimo-v2.5-tts-voicedesign | — | — | No | — | — | — | — | — |
google/gemma-3-12b-it oah/gemma-3-12b-it | — | — | No | — | $0.05/$0.10 | — | — | — |
intfloat/e5-base-v2 oah/e5-base | — | — | No | — | — | — | — | — |
intfloat/e5-large-v2 oah/e5-large | — | — | No | — | — | — | — | — |
intfloat/multilingual-e5-large oah/multilingual-e5-large | — | — | No | — | — | — | — | — |
microsoft/phi-4 oah/phi-4 | — | — | No | — | $0.07/$0.14 | — | — | — |
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B oah/nvidia-nemotron-3-ultra | — | — | No | — | — | — | — | — |
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 oah/nvidia-nemotron-3-ultra-550b-a55b-bf16 | — | — | No | — | — | — | — | — |
nvidia/Nemotron-3-Nano-30B-A3B oah/nemotron-3-nano | — | — | No | — | — | — | — | — |
nvidia/Nemotron-3.5-ASR-Streaming-Multilingual-0.6b oah/nemotron-3.5-asr-streaming-multilingual-0.6b | — | — | No | — | — | — | — | — |
nvidia/Nemotron-Content-Safety-3.5 oah/nemotron-content-safety-3.5 | — | — | No | — | — | — | — | — |
openai/whisper-large-v3 oah/whisper-large-v3 | — | — | No | — | — | — | — | — |
sentence-transformers/all-MiniLM-L12-v2 oah/all-minilm-l12 | — | — | No | — | — | — | — | — |
sentence-transformers/all-MiniLM-L6-v2 oah/all-minilm-l6 | — | — | No | — | — | — | — | — |
sentence-transformers/all-mpnet-base-v2 oah/all-mpnet-base | — | — | No | — | — | — | — | — |
sentence-transformers/clip-ViT-B-32 oah/clip-vit-b-32 | — | — | No | — | — | — | — | — |
sentence-transformers/clip-ViT-B-32-multilingual-v1 oah/clip-vit-b-32-multilingual | — | — | No | — | — | — | — | — |
sentence-transformers/multi-qa-mpnet-base-dot-v1 oah/multi-qa-mpnet-base-dot | — | — | No | — | — | — | — | — |
sentence-transformers/paraphrase-MiniLM-L6-v2 oah/paraphrase-minilm-l6 | — | — | No | — | — | — | — | — |
sesame/csm-1b oah/csm | — | — | No | — | — | — | — | — |
shibing624/text2vec-base-chinese oah/text2vec-base-chinese | — | — | No | — | — | — | — | — |
stepfun-ai/Step-3.5-Flash oah/step-3.5-flash | — | — | No | — | — | — | — | — |
stepfun-ai/Step-3.7-Flash oah/step-3.7-flash | — | — | No | — | — | — | — | — |
thenlper/gte-base oah/gte-base | — | — | No | — | — | — | — | — |
thenlper/gte-large oah/gte-large | — | — | No | — | — | — | — | — |
zai-org/GLM-4.7-Flash oah/glm-4.7-flash | — | — | No | — | — | — | — | — |
babbage-002 oah/dall-e-3 | — | — | No | — | — | — | — | $0.40/$0.40 |
chat-latest oah/chat | — | — | No | — | — | — | — | — |
davinci-002 oah/davinci-002 | — | — | No | — | — | — | — | $2.00/$2.00 |
o1 oah/o1 | — | — | No | — | — | — | — | $15.00/$60.00 |
o1-2024-12-17 oah/o1-2024-12-17 | — | — | No | — | — | — | — | $15.00/$60.00 |
o1-pro oah/o1-pro | — | — | No | — | — | — | — | $150.00/$600.00 |
o1-pro-2025-03-19 oah/o1-pro-2025-03-19 | — | — | No | — | — | — | — | $150.00/$600.00 |
o3 oah/o3 | — | — | No | — | — | — | — | $2.00/$8.00 |
o3-2025-04-16 oah/o3-2025-04-16 | — | — | No | — | — | — | — | $2.00/$8.00 |
o3-mini oah/o3-mini | — | — | No | — | — | — | — | $1.10/$4.40 |
o3-mini-2025-01-31 oah/o3-mini-2025-01-31 | — | — | No | — | — | — | — | $1.10/$4.40 |
o4-mini oah/o4-mini | — | — | No | — | — | — | — | $1.10/$4.40 |
o4-mini-2025-04-16 oah/o4-mini-2025-04-16 | — | — | No | — | — | — | — | $1.10/$4.40 |
o4-mini-deep-research oah/o4-mini-deep-research | — | — | No | — | — | — | — | $2.00/$8.00 |
o4-mini-deep-research-2025-06-26 oah/o4-mini-deep-research-2025-06-26 | — | — | No | — | — | — | — | $2.00/$8.00 |
sora-2 oah/sora-2 | — | — | No | — | — | — | — | — |
sora-2-pro oah/sora-2-pro | — | — | No | — | — | — | — | — |
What you get at each pricing tier. Hub adds security, governance, and multi-provider routing on top of raw API access.
| Mode | What You Pay | PII Redaction | Budget Caps | Routing | Audit Trail |
|---|---|---|---|---|---|
| Direct to Multiple Providers | Provider pricing only | None | None | Manual | None |
| Hub — Managed Mode | Provider + 25% markup | 30+ PII types | Per-key hard caps | Smart Router | Full compliance log |
| Hub — Pro BYOK ($29/mo) | Direct to provider (0% markup) | 30+ PII types | Per-key hard caps | Smart Router | Full compliance log |
Exploring emerging models for cost-optimized workloads
Specialized tasks (OCR, multilingual, code) from niche providers
Testing new open-source releases with built-in governance
Diversified model strategy beyond the top model families
# pip install aisg
from aisg import AISG
client = AISG(api_key="your_hub_api_key")
response = client.chat.create(
model="oah/kimi-k2.5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.content)
print(response.aisg_metadata.pii_detected)
print(response.aisg_metadata.cost_usd)Use any virtual model name from the pricing table above (prefixed with oah/). Also works with the standard OpenAI SDK — just change base_url. Every request is PII-scanned before reaching Multiple Providers (Open / Closed).
These models have been retired by the provider. Migrate to a current variant above.
Get started with 1,000,000 free credits. Every Other request is PII-scanned, cost-optimized, and fully logged — zero configuration.
Not ready yet? Get notified about Other updates:
Meta's open-weights Llama family is the most widely deployed open-source LLM series. Compare Llama API pricing across Gr…
OpenAI's GPT family powers the majority of commercial AI applications. Compare GPT-4 API cost and OpenAI API pricing acr…
Google's Gemini family offers powerful multimodal capabilities with large context windows. Compare Gemini API pricing an…
Anthropic's Claude family is built with safety and reliability at its core. Compare Claude API pricing and Claude Sonnet…
DeepSeek has rapidly risen as a leading open-source model family, known for exceptional coding performance and cost effi…
Model registry last updated: . Pricing shown is the lowest available rate across providers (per 1M tokens, USD). Actual pricing depends on provider and plan.