Text model
ibm/granite-ttm-1024-96-r2 pricing
IBM watsonx charges $0.38 per million input tokens and $0.38 per million output tokens for ibm/granite-ttm-1024-96-r2. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.38/ 1M
- Output
- $0.38/ 1M
- Context
- 512tokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.38 | $0.38 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.000722 | 100,000 | $72.20 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00247 | 100,000 | $247.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00486 | 250,000 | $1,216.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with ibm/granite-ttm-1024-96-r2, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| watsonx/openai/gpt-oss-120b | $0.000493 | 32% |
| watsonx/ibm/granite-3-3-8b-instruct | $0.00038 | 47% |
| azure-ai/Llama-4-Scout-17B-16E-Instruct | $0.000612 | 15% |
| deepinfra/Qwen/Qwen3.5-35B-A3B | $0.00061 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: IBM watsonx pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.