Oracle Cloud Pricing
Oracle Cloud charges between $0.090 and $25.00 per 1 million output tokens, depending on the model. Cohere.command A Translate 08 2025 is the cheapest at $0.090/1M output and $0.090/1M input; Xai.grok 3 Fast is the most expensive at $25.00/1M output. The largest context window is 10.5M tokens (Meta.llama 4 Scout 17B 16e Instruct). Prices are USD, current as of July 20, 2026.
Last updated · synced weekly from the upstream model catalog
Cheapest input
$0.050/1M
Openai.gpt 5 Nano
Cheapest output
$0.090/1M
Cohere.command A Translate 08 2025
Longest context
10.5M
Meta.llama 4 Scout 17B 16e Instruct
Models priced
35
Avg $6.27/1M output
Pricing by model
All prices in USD per 1 million tokens. All 35 priced models, cheapest first.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| Cohere.command A Translate 08 2025 | $0.090 | $0.090 | 256K |
| Cohere.command R 08 2024 | $0.150 | $0.150 | 128K |
| Google.gemini 2.5 Flash Lite | $0.075 | $0.300 | 1.0M |
| Openai.gpt 5 Nano | $0.050 | $0.400 | 272K |
| Xai.grok 3 Mini | $0.300 | $0.500 | 131K |
| Google.gemini 2.5 Flash | $0.150 | $0.600 | 1.0M |
| Meta.llama 3.1 70B Instruct | $0.720 | $0.720 | 128K |
| Meta.llama 3.1 8B Instruct | $0.720 | $0.720 | 128K |
| Meta.llama 3.3 70B Instruct | $0.720 | $0.720 | 128K |
| Meta.llama 3.3 70B Instruct Fp8 Dynamic | $0.720 | $0.720 | 128K |
| Meta.llama 4 Maverick 17B 128e Instruct Fp8 | $0.720 | $0.720 | 1.0M |
| Meta.llama 4 Scout 17B 16e Instruct | $0.720 | $0.720 | 10.5M |
| Cohere.command A 03 2025 | $1.56 | $1.56 | 256K |
| Cohere.command A Reasoning | $1.56 | $1.56 | 256K |
| Cohere.command A Reasoning 08 2025 | $1.56 | $1.56 | 256K |
| Cohere.command A Vision | $1.56 | $1.56 | 256K |
| Cohere.command A Vision 07 2025 | $1.56 | $1.56 | 128K |
| Cohere.command Latest | $1.56 | $1.56 | 128K |
| Cohere.command Plus Latest | $1.56 | $1.56 | 128K |
| Cohere.command R Plus 08 2024 | $1.56 | $1.56 | 128K |
| Meta.llama 3.2 11B Vision Instruct | $2.00 | $2.00 | 128K |
| Meta.llama 3.2 90B Vision Instruct | $2.00 | $2.00 | 128K |
| Openai.gpt 5 Mini | $0.250 | $2.00 | 272K |
| Xai.grok 3 Mini Fast | $0.600 | $4.00 | 131K |
| Google.gemini 2.5 Pro | $1.25 | $10.00 | 1.0M |
| Openai.gpt 5 | $1.25 | $10.00 | 272K |
| Meta.llama 3.1 405B Instruct | $10.68 | $10.68 | 128K |
| Xai.grok 3 | $3.00 | $15.00 | 131K |
| Xai.grok 4 | $3.00 | $15.00 | 128K |
| Xai.grok 4.20 | $3.00 | $15.00 | 131K |
| Xai.grok 4.20 Multi Agent | $3.00 | $15.00 | 131K |
| Xai.grok 3 Fast | $5.00 | $25.00 | 131K |
| Xai.grok 4 Fast | $5.00 | $25.00 | 131K |
| Xai.grok 4.1 Fast | $5.00 | $25.00 | 131K |
| Xai.grok Code Fast 1 | $5.00 | $25.00 | 131K |
Frequently asked questions
How much does Oracle Cloud cost per 1M tokens?
Oracle Cloud pricing ranges from $0.090 to $25.00 per 1 million output tokens across 35 models. Input tokens are cheaper than output on every model. Rates current as of July 20, 2026.
What is the cheapest Oracle Cloud model?
Cohere.command A Translate 08 2025 is the cheapest Oracle Cloud model on output tokens at $0.090 per 1M, while Openai.gpt 5 Nano is cheapest on input at $0.050 per 1M. Which wins for you depends on your input-to-output ratio.
What is the largest Oracle Cloud context window?
Meta.llama 4 Scout 17B 16e Instruct has the largest context window in the Oracle Cloud catalog at 10.5M input tokens, with up to 8K output tokens per response.
How do I calculate my actual Oracle Cloud bill?
Multiply your input tokens by the input rate and your output tokens by the output rate, both per million, then add retries and any conversation history resent on each turn. Calcaas does this against your real usage pattern and shows the margin left at your price point.
Other providers
What will this actually cost you?
Per-token rates only tell you half the story. Calcaas multiplies them by your real usage — prompt size, response length, retries and conversation history — then shows the margin left at your price point.
Open the free cost calculator