Neither wins outright: LiquidAI: LFM2.5-2.6B is the pick when you need log-probabilities, OpenAI: gpt-oss-120b (exacto) when cost matters at scale.
| Spec | LiquidAI: LFM2.5-2.6B | OpenAI: gpt-oss-120b (exacto) |
|---|---|---|
| Provider | Liquid | OpenAI |
| Input price (per 1M tokens) | $0.35 | $0.04 |
| Output price (per 1M tokens) | $0.50 | $0.19 |
| Blended price (3:1 input/output) | $0.39 | $0.08 |
| Cheaper than … of all models we track | 58% | 83% |
| Context window | 128K tokens (~192 pages) | 131K tokens (~197 pages) |
| Larger context than … of all models | 14% | 22% |
| Max output per response | 8K tokens (~6,100 words) | n/a |
| Input types | text | text |
| Output types | text | text |
| Free variant | Yes | No |
| Listed since | 2026-08-11 | 2025-08-05 |
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | LiquidAI: LFM2.5-2.6B | OpenAI: gpt-oss-120b (exacto) | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $36.25 | $6.72 | OpenAI: gpt-oss-120b (exacto) saves $29.52 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $47.00 | $6.58 | OpenAI: gpt-oss-120b (exacto) saves $40.42 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $48.00 | $6.96 | OpenAI: gpt-oss-120b (exacto) saves $41.04 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $31.00 | $4.26 | OpenAI: gpt-oss-120b (exacto) saves $26.74 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $18.00 | $2.14 | OpenAI: gpt-oss-120b (exacto) saves $15.86 |
| Capability | LiquidAI: LFM2.5-2.6B | OpenAI: gpt-oss-120b (exacto) | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | ✓ Yes | spend extra tokens thinking before answering hard problems |
| Image input | — | — | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | ✓ Yes | repeat a generation for tests and evals |
| Log-probabilities | ✓ Yes | — | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Neither wins outright: LiquidAI: LFM2.5-2.6B is the pick when you need log-probabilities, OpenAI: gpt-oss-120b (exacto) when cost matters at scale. In short: LiquidAI: LFM2.5-2.6B when you need log-probabilities, you want to prototype at zero cost, you want the newer model; OpenAI: gpt-oss-120b (exacto) when cost matters at scale.
OpenAI: gpt-oss-120b (exacto) is cheaper: $0.08 vs $0.39 per 1M tokens at a typical 3:1 input/output mix, 80% less. For 50,000 support conversations a month that is $6.72 against $36.25.
LiquidAI: LFM2.5-2.6B costs $0.35 per 1M input tokens and $0.50 per 1M output tokens; OpenAI: gpt-oss-120b (exacto) costs $0.04 input and $0.19 output. Output tokens are billed separately, so long answers shift the gap.
OpenAI: gpt-oss-120b (exacto): 131K tokens, about 197 pages, against 128K (about 192 pages) for LiquidAI: LFM2.5-2.6B.
Tool calling — LiquidAI: LFM2.5-2.6B: yes, OpenAI: gpt-oss-120b (exacto): yes. JSON-schema structured output — LiquidAI: LFM2.5-2.6B: yes, OpenAI: gpt-oss-120b (exacto): yes.
Neither accepts image input — both are text-in models.
LiquidAI: LFM2.5-2.6B has a free variant (liquid/lfm-2.5-2.6b:free). Free variants usually carry tighter rate limits.
LiquidAI: LFM2.5-2.6B was listed on 2026-08-11; OpenAI: gpt-oss-120b (exacto) on 2025-08-05.
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Full LiquidAI: LFM2.5-2.6B specs →gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Full OpenAI: gpt-oss-120b (exacto) specs →