Oracle Cloud models & pricing
Oracle Cloud hosts 37 models (37 with public pricing) covering 2 modalities. Oracle Cloud Generative AI — Llama, Cohere, on OCI. Cheapest input starts at $0.0750/M tokens; the most premium goes up to $10.68/M. Use Future AGI's Agent Command Center to route any Oracle Cloud model with cost-optimized fallback and unified observability.
chat 29
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| Google Gemini 2.5 Flash Lite | $0.0750/M | $0.300/M | 1,048,576 | tools · vision |
| Cohere Command A Translate 08.2025 | $0.0900/M | $0.0900/M | 256,000 | |
| Cohere Command R 08.2024 | $0.150/M | $0.150/M | 128,000 | tools |
| Google Gemini 2.5 Flash | $0.150/M | $0.600/M | 1,048,576 | tools · vision |
| Xai Grok 3 mini | $0.300/M | $0.500/M | 131,072 | tools |
| Xai Grok 3 mini Fast | $0.600/M | $4.00/M | 131,072 | tools |
| Meta Llama 3.1 70B Instruct | $0.720/M | $0.720/M | 128,000 | tools |
| Meta Llama 3.3 70B Instruct | $0.720/M | $0.720/M | 128,000 | tools |
| Meta Llama 3.3 70B Instruct Fp8 Dynamic | $0.720/M | $0.720/M | 128,000 | tools |
| Meta Llama 4 Maverick 17B 128e Instruct Fp8 | $0.720/M | $0.720/M | 512,000 | tools |
| Meta Llama 4 Scout 17B 16e Instruct | $0.720/M | $0.720/M | 192,000 | tools |
| Google Gemini 2.5 Pro | $1.25/M | $10.00/M | 1,048,576 | tools · vision |
| Cohere Command A 03.2025 | $1.56/M | $1.56/M | 256,000 | tools |
| Cohere Command A Reasoning 08.2025 | $1.56/M | $1.56/M | 256,000 | tools |
| Cohere Command A Vision 07.2025 | $1.56/M | $1.56/M | 128,000 | tools · vision |
| Cohere Command latest | $1.56/M | $1.56/M | 128,000 | tools |
| Cohere Command Plus latest | $1.56/M | $1.56/M | 128,000 | tools |
| Cohere Command R Plus 08.2024 | $1.56/M | $1.56/M | 128,000 | tools |
| Meta Llama 3.2 11B Vision Instruct | $2.00/M | $2.00/M | 128,000 | tools · vision |
| Meta Llama 3.2 90B Vision Instruct | $2.00/M | $2.00/M | 128,000 | tools · vision |
| Xai Grok 3 | $3.00/M | $15.00/M | 131,072 | tools |
| Xai Grok 4 | $3.00/M | $15.00/M | 128,000 | tools |
| Xai Grok 4.20 | $3.00/M | $15.00/M | 131,072 | tools |
| Xai Grok 4.20 Multi Agent | $3.00/M | $15.00/M | 131,072 | tools |
| Xai Grok 3 Fast | $5.00/M | $25.00/M | 131,072 | tools |
| Xai Grok 4.1 Fast | $5.00/M | $25.00/M | 131,072 | tools |
| Xai Grok 4 Fast | $5.00/M | $25.00/M | 131,072 | tools |
| Xai Grok Code Fast 1 | $5.00/M | $25.00/M | 131,072 | tools |
| Meta Llama 3.1 405B Instruct | $10.68/M | $10.68/M | 128,000 | tools |
embedding 8
| Model ↕ | Input / 1M ↕ | Output / 1M ↕ | Context ↕ | Caps |
|---|---|---|---|---|
| Cohere Embed English Image v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed English Light Image v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed English Light v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed English v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed Multilingual Light Image v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed Multilingual Light v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed Multilingual v3.0 | $0.1000/M | — | 512 | |
| Cohere Embed v4.0 | $0.120/M | — | 128,000 |
FAQ
How many Oracle Cloud models are there?
37 Oracle Cloud models are listed across 2 modalities on this page. 37 have public per-token pricing.
How is Oracle Cloud pricing verified?
Pricing is aggregated from BerriAI/litellm, models.dev, and OpenRouter and refreshed weekly. Each row shows a per-model "verified" date. If a price is wrong, click the row to open the model page and use the inline "suggest edit" link — submissions go into a public review queue.
Which Oracle Cloud model is cheapest?
Input pricing on Oracle Cloud starts at $0.0750 per 1M tokens. Sort the table by price (or use the in-page filter at the top) to find the cheapest model that matches your capability requirements.
Can I route to Oracle Cloud via an OpenAI-compatible API?
Yes — point your OpenAI client at Future AGI's Agent Command Center, configure a Oracle Cloud target, and call Oracle Cloud models with the standard /v1/chat/completions surface. The same gateway can route to other providers as fallback. Free for the first 100K requests/month.