LFM2.5-8B-A1B

Open weights

LFM2.5-8B-A1B is a language model from LiquidAI with a 32K-token context window. Provider list price is $0.03 per million input tokens and $0.12 per million output; on Allocate you pay $0.032 and $0.13 with the 7% transaction fee. The weights are open under Custom license, so you can fine-tune it and own the result.

Route LFM2.5-8B-A1B Talk to sales

Pricing

Provider listOn Allocate

Input, per M tokens$0.03$0.032

Output, per M tokens$0.12$0.13

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

Price against its peers

Qwen 2 Instruct (1.5B)$0.02$0.02

LFM2.5-8B-A1B$0.03$0.12

Trinity Mini$0.045$0.15

OpenAI GPT-OSS 20B$0.05$0.20

Gemma 3N E4B Instruct$0.06$0.12

Meta Llama 3.2 1B Instruct$0.06$0.06

Meta Llama 3.2 3B Instruct$0.06$0.06

Arize AI Qwen 2 1.5B Instruct$0.10$0.10

InputOutput

Provider list prices per M tokens, LFM2.5-8B-A1B against its nearest language peers by price.

What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.03 + 350 × $0.12 = $78 a month. Billed on Allocate it is $83.46 with the 7% transaction fee.

LFM2.5-8B-A1B is an open-weights model under the Custom license license. Read the license terms once before you build on it; fine-tuned weights on Allocate stay inside your boundary.

Example usage

Point a route at liquid/lfm2.5-8b-a1b and the endpoint never changes; swap the model behind it whenever you want.

api.allocate.network

curl https://api.allocate.network/v1/chat/completions \
  -H "Authorization: Bearer $ALLOCATE_KEY" \
  -d '{
    "model": "liquid/lfm2.5-8b-a1b",
    "messages": [{"role": "user",
      "content": "Summarise the attached contract."}]
  }'

200 · liquid/lfm2.5-8b-a1b · inside your boundary

Common questions

How much does LFM2.5-8B-A1B cost per million tokens?

Provider list price is $0.03 per million input tokens and $0.12 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.032 in and $0.13 out.

What context window does LFM2.5-8B-A1B have?

32,768 tokens (32K). At roughly 0.75 words per token, that is about 25k words of English text per request.

Can I fine-tune LFM2.5-8B-A1B?

Yes. LFM2.5-8B-A1B is an open-weights model under the Custom license license. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.

How do I call LFM2.5-8B-A1B on Allocate?

Send liquid/lfm2.5-8b-a1b in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.