Mt0 Xxl 13B
mt0-xxl-13bPricing
List prices at IBM watsonx.ai, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $1.91 | $1.91 |
What it costs a month
At IBM watsonx.ai list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$716
- RAG over documents2,000 requests a day, 8K in / 0.6K out$985
- Coding agent1,000 requests a day, 40K in / 2K out$2,404
- Overnight batch20,000 requests a day, 4K in / 0.4K out$5,037
Where to run it
1 host serve Mt0 Xxl 13B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
IBM watsonx.aiCloud mt0-xxl-13b | $1.91 / $1.91 | mt0-xxl-13b |
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
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 Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
- 12% less
- 18% less
- 21% less
- 90% less
Open-weight picks
- 10% less
- 55% less
- 57% less
- 58% less
Call it
Using IBM watsonx.ai's API.
from litellm import completion
response = completion(
model="watsonx/mt0-xxl-13b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Mt0 Xxl 13B cost?
On IBM watsonx.ai, Mt0 Xxl 13B costs $1.91 per million input tokens and $1.91 per million output tokens.
Which APIs offer Mt0 Xxl 13B?
Mt0 Xxl 13B runs on 1 API: IBM watsonx.ai.
What is Mt0 Xxl 13B's context window?
4K tokens, with up to 4K tokens in one reply.
Is Mt0 Xxl 13B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Mt0 Xxl 13B?
Models that cost less and keep most of what it can do: GPT-5.4 Mini on OpenAI (12% less), Grok 4.20 Multi Agent on xAI (18% less) and Inkling on DeepInfra (10% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Mt0 Xxl 13B's API model id?
Use mt0-xxl-13b with IBM watsonx.ai.
Sources
Raw catalog entry for mt0-xxl-13b on IBM watsonx.ai
{
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000001908,
"output_cost_per_token": 0.000001908,
"litellm_provider": "watsonx",
"mode": "chat",
"supports_function_calling": false,
"supports_parallel_function_calling": false,
"supports_vision": false,
"source": "https://dataplatform.cloud.ibm.com/docs/content/wsj/analyze-data/fm-models.html?context=wx"
}