Cloud model platform
IBM watsonx.ai
Model prices vs the direct API
ibm.comChecked Sep 23, 2026
- Fee on tokens
- Not published
- Per 1M tokens (billed as Resource Units, 1 RU = 1,000 tokens incl. input and output); Essentials plan from USD 0/month, Standard from USD 1110/month
- BYOK fee
- No BYOK
- Entry plan
- Usage based
- Hosting
- Hosted
Models on IBM watsonx.ai
3 model routes.
ModelHere, in / outDirectPremium
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
IBM's AI studio and inference platform serving IBM Granite and third-party models (Meta, Mistral, OpenAI gpt-oss, others) with pay-as-you-go per-token pricing.
- Markup
- Per 1M tokens (billed as Resource Units, 1 RU = 1,000 tokens incl. input and output); Essentials plan from USD 0/month, Standard from USD 1110/month
- Free tier
- Free Toolbox playground: up to 300,000 tokens per month
- Providers
- IBM Granite family plus third-party models from Meta, Google, DeepSeek, Mistral, OpenAI and more
- For foundation model inference, charges are based on a Resource Unit (RU) metric equivalent to 1000 tokens (including both input and output tokens).
- Foundation Models : Up to 300,000 tokens per month
- Starting at USD 1110/month*
IBM watsonx.ai vs
AWS Bedrock
Azure AI Foundry
Google Vertex AI
OCI Generative AI
Helicone
Kong AI GatewayPricing 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.