Choose a model to open its comparison page.
LFM 2.5 1.2B Thinking API pricing covers 6 API providers, from $0.0050/request to $0.100/request. LFM 2.5 1.2B Thinking free API options are available from 1 provider.
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K...
Input and output token limits for this model, plus how it ranks on long-context understanding.
Compare LFM 2.5 1.2B Thinking API pricing across 5 providers. Prices range from $0.0050/request to $0.100/request. OpenRouter Fans offers the lowest rate at $0.0050/request. 1 provider offers free API credits or a free tier.
| Провайдер | Работоспособность | Вариант модели | Группа | Входные данные ($/M) | Выходные данные ($/M) | Скорость (т/с) | Первый токен | Аудит |
|---|---|---|---|---|---|---|---|---|
L1 100% | liquid/lfm-2.5-1.2b-thinking:free | default | $0.0050/request | - | — | — | — | |
Dext API Бесплатно | L1 100% | lfm-2.5-1.2b-thinking | 公益 | Бесплатно | Бесплатно | — | — | — |
L1 98% | lfm-2.5-1.2b-thinking | default | $0.010/request | - | — | — | — | |
L1 96% | lfm-2.5-1.2b-thinking | 小叶币 | $0.050/request | - | — | — | — | |
L1 0% | liquid/lfm-2.5-1.2b-thinking:free | default | $0.010/request | - | — | — | — |
gpt-oss
GPT-OSS is an open-weight language model family designed for self-hosted inference, research, and cost-efficient alternatives to proprietary GPT-class models.
glm-4-5-air
Zhipu AI GLM-4.5 Air is a lightweight GLM-4.5 variant optimized for low-latency Chinese and English dialogue, retrieval-augmented apps, and edge deployments.
lfm-2-5-1-2b-instruct
LFM 2.5 1.2B Instruct is a compact language model in the LFM series, optimized for low-latency responses and efficient inference.
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
qwen3
Alibaba Qwen3 is the Qwen family's flagship LLM series with dense and MoE variants, seamless thinking/non-thinking modes, and leading open-source performance in math, code, and agent tasks.
qwen3-5
Alibaba Qwen3.5 is a Qwen3 generation model with improved reasoning, multilingual support, and efficient inference for chat, coding, and agent applications.
