Lfm2.5.1 2B Instruct
LFM2.5-1.2B-InstructPricing
List prices at ZeroGPU, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.02 | $0.05 |
What it costs a month
At ZeroGPU list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$9.75
- RAG over documents2,000 requests a day, 8K in / 0.6K out$11.40
- Coding agent1,000 requests a day, 40K in / 2K out$27.00
- Overnight batch20,000 requests a day, 4K in / 0.4K out$60.00
Where to run it
1 host serve Lfm2.5.1 2B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
ZeroGPUCloud LFM2.5-1.2B-Instruct | $0.02 / $0.05 | LFM2.5-1.2B-Instruct |
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 ZeroGPU.
Smaller Independent models
No cheaper Independent model keeps its key capabilities.
Other frontier labs
No cheaper match from another frontier lab.
Open-weight picks
- 9% less
- 9% less
- 45% less
- 27% less
Call it
Using ZeroGPU's API.
from litellm import completion
response = completion(
model="zerogpu/LFM2.5-1.2B-Instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Lfm2.5.1 2B Instruct cost?
On ZeroGPU, Lfm2.5.1 2B Instruct costs $0.02 per million input tokens and $0.05 per million output tokens.
Which APIs offer Lfm2.5.1 2B Instruct?
Lfm2.5.1 2B Instruct runs on 1 API: ZeroGPU.
What is Lfm2.5.1 2B Instruct's context window?
33K tokens, with up to 8K tokens in one reply.
Is Lfm2.5.1 2B Instruct being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Lfm2.5.1 2B Instruct?
Models that cost less and keep most of what it can do: DeepSeek R1 Distill Llama 8B on Nscale (9% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Lfm2.5.1 2B Instruct's API model id?
Use LFM2.5-1.2B-Instruct with ZeroGPU.
Sources
Raw catalog entry for LFM2.5-1.2B-Instruct on ZeroGPU
{
"input_cost_per_token": 2e-8,
"litellm_provider": "zerogpu",
"max_input_tokens": 32768,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 5e-8,
"source": "https://docs.zerogpu.ai/docs/model-catalog"
}