Cheapest Language Models in 2026
Updated
When input-token cost is a key constraint, these text models offer a catalogue you can filter and sort by price. Compare the listed input prices, while checking whether a router or a named model best fits how your application selects and uses language models. Auto Router, Body Builder (beta), and DeepSeek V4 Flash Latest are among the entries shown, with options such as Fusion and Jev Router also included. Free models are excluded, so this selection focuses on paid text-model options. Use the price ordering as a starting point, then consider the fit of each entry for your stack and the tasks you need to support.
437 on record. Sorted by input price; every figure comes from the OpenRouter model catalogue, with the page it was read from on each entry.
Context bars share one log scale, 1K to 2M tokens. Prices are what each provider publishes per million tokens; 'varies' is a router that bills the model it picks.