Is LFM2.5-1.2B-Thinking (free) or GPT-5.3 Codex cheaper?

LFM2.5-1.2B-Thinking (free) is cheaper on output tokens ($0.00 vs $14.00 per 1M).

Which has the larger context window, LFM2.5-1.2B-Thinking (free) or GPT-5.3 Codex?

GPT-5.3 Codex has the larger context window (400K tokens).

LFM2.5-1.2B-Thinking (free) vs GPT-5.3 Codex

LFM2.5-1.2B-Thinking (free) is cheaper on output tokens, while GPT-5.3 Codex offers a larger context window. Choose LFM2.5-1.2B-Thinking (free) or GPT-5.3 Codex based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	LFM2.5-1.2B-Thinking (free)	GPT-5.3 Codex
Provider	OpenRouter	OpenRouter
Input / 1M tokens	$0.00	$1.75
Output / 1M tokens	$0.00	$14.00
Context window	33K	400K
Parameters	—	—
Open weights	Yes	No
Released	Jan 2026	Feb 2026

LFM2.5-1.2B-Thinking (free) details →GPT-5.3 Codex details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.