Granite Ttm 512.96 R2
granite-ttm-512-96-r2Pricing
List prices at IBM watsonx.ai, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.38 | $0.38 |
What it costs a month
At IBM watsonx.ai list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$143
- RAG over documents2,000 requests a day, 8K in / 0.6K out$196
- Coding agent1,000 requests a day, 40K in / 2K out$479
- Overnight batch20,000 requests a day, 4K in / 0.4K out$1,003
Where to run it
1 host serve Granite Ttm 512.96 R2. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
IBM watsonx.aiCloud granite-ttm-512-96-r2 | $0.38 / $0.38 | granite-ttm-512-96-r2 |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Apache-2.0Runtimes: Ollama, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than IBM watsonx.ai.
Smaller IBM models
No cheaper IBM model keeps its key capabilities.
Other frontier labs
- 47% less
- 47% less
- 31% less
Open-weight picks
- 3% less
- 8% less
- 31% less
- 53% less
Model line
Newer and older versions, at each lab's own price.
- UndatedGranite Ttm 1536.96 R2Latest$0.38 / $0.38
- UndatedGranite Ttm 1024.96 R2$0.38 / $0.38
- UndatedGranite Ttm 512.96 R2This page$0.38 / $0.38
Call it
Using IBM watsonx.ai's API.
from litellm import completion
response = completion(
model="watsonx/granite-ttm-512-96-r2",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Granite Ttm 512.96 R2 cost?
On IBM watsonx.ai, Granite Ttm 512.96 R2 costs $0.38 per million input tokens and $0.38 per million output tokens.
Which APIs offer Granite Ttm 512.96 R2?
Granite Ttm 512.96 R2 runs on 1 API: IBM watsonx.ai.
What is Granite Ttm 512.96 R2's context window?
512 tokens, with up to 512 tokens in one reply.
Is Granite Ttm 512.96 R2 being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of Granite Ttm 512.96 R2?
Yes. Granite Ttm 1536.96 R2 is the newest model in this line.
What are cheaper alternatives to Granite Ttm 512.96 R2?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (47% less), GPT-6 Luna on OpenAI (47% less) and Qwen3.5 397B A17B on AIHubMix (3% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Granite Ttm 512.96 R2's API model id?
Use granite-ttm-512-96-r2 with IBM watsonx.ai.
Sources
Raw catalog entry for granite-ttm-512-96-r2 on IBM watsonx.ai
{
"max_input_tokens": 512,
"max_output_tokens": 512,
"input_cost_per_token": 3.8e-7,
"output_cost_per_token": 3.8e-7,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false
}