Model provider
watsonx.ai
Explore models served by watsonx.ai.
5models
Pricing & endpoints
5 offers · USD per million tokens| Model | Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Route |
|---|---|---|---|---|---|---|---|---|---|
| Granite-4.0-H-Small | watsonx.ai | ibm/granite-4-h-small | 131,072 | 131,072 | $0.0636 / $0.265 | No | Yes | Yes | View route |
| Mistral Small 3.1 24B | watsonx.ai | mistralai/mistral-small-3-1-24b-instruct-2503 | 131,072 | 16,384 | $0.106 / $0.318 | No | Yes | Yes | View route |
| GPT OSS 120B | watsonx.ai | openai/gpt-oss-120b | 131,072 | 32,768 | $0.159 / $0.636 | Yes | Yes | Yes | View route |
| Llama 4 Maverick 17B Instruct | watsonx.ai | meta-llama/llama-4-maverick-17b-128e-instruct-fp8 | 131,072 | 8,192 | $0.371 / $1.484 | No | Yes | — | View route |
| Llama-3.3-70B-Instruct | watsonx.ai | meta-llama/llama-3-3-70b-instruct | 131,072 | 4,096 | $0.7526 / $0.7526 | No | Yes | — | View route |
1–5 of 5
Prices, limits and configurations apply to each serving offer. Open a model for its complete specifications and provider comparison.