Cloud model platform
OCI Generative AI
Model prices vs the direct API
oracle.comUnverified
- Fee on tokens
- Not published
- Mixed: per 1M tokens for Google, xAI and OpenAI gpt-oss models; per 10,000 transactions (1 transaction = 1 character of prompt plus response) for Meta and Cohere; dedicated AI clusters per unit hour
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
Models on OCI Generative AI
4 model routes. 3 of 3 at the lab's own list price; the rest shown as a premium or discount.
ModelHere, in / outDirectPremium
Grok 4.3default region · direct $1.25 / $2.5$1.25 / $2.5same as direct$1.25 / $2.5None
gpt-oss-120bdefault region$0.15 / $0.6n/an/a
Gemini 2.5 Prodefault region · direct $1.25 / $10$1.25 / $10same as direct$1.25 / $10None
Gemini 2.5 Flashdefault region · direct $0.3 / $2.5$0.3 / $2.5same as direct$0.3 / $2.5None
Premium: blended price (3 input to 1 output) on this platform against the lab's own API. Regions are separate routes.
Features
- Fallbacks
- Load balancing
- Caching
- Guardrails
- Observability
- Rate limits
- Budgets
- Prompts
- OpenAI-compatible
- Bring your own key
- Data residency
- Private networking
What it costs on real workloads
Claude Sonnet 5n/avs $400.00 direct
GPT-6 Soln/avs $400.00 direct
Gemini 3.8 Flashn/avs $150.00 direct
DeepSeek V4.1 Flashn/avs $27.00 direct
100M input and 20M output tokens a month, paying with gateway credits.
The terms, in their words
Oracle Cloud Infrastructure's managed generative AI service offering Cohere, Meta Llama, Google Gemini, xAI Grok and OpenAI gpt-oss models on demand or on dedicated AI clusters.
- Markup
- Mixed: per 1M tokens for Google, xAI and OpenAI gpt-oss models; per 10,000 transactions (1 transaction = 1 character of prompt plus response) for Meta and Cohere; dedicated AI clusters per unit hour
- Providers
- Oracle price list shows Cohere, Meta (Llama 3.x, Llama 4 Scout/Maverick), Google Gemini 2.5 Pro/Flash/Flash Lite, xAI Grok 4.2 to 4.7, OpenAI gpt-oss-20b/120b
- The pricing page lists the price for 10,000 on-demand transactions or 1,000,000 tokens when using the playground, API, or CLI for inferencing.
- 10,000 transactions = 10,000 characters, so 1 transaction = 1 character
- OCI Generative AI - Large Meta | 10,000 Transactions | 0.0018
OCI Generative AI vs
Pricing as read from the gateway's own pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.