Cost guide

Cheapest AI models

This shortlist favors low combined input and output price first, then keeps enough context and capability signal to make the models usable in real traffic instead of just cheap on paper.

Live signalLowest combined TVP input and output price among paid models
Live signalEnough context to stay practical for chat, support, and content tasks
Live signalLive catalog availability instead of stale benchmark pricing
Live signalVisible capabilities to avoid choosing a model that cannot handle your route
Fast answer

Start with the live shortlist, then validate the route

This page is tuned for production buying. It focuses on paid, billable models so traffic planning is based on routes you can reliably meter, forecast, and scale.

Data source and freshness

Catalog-backed, not a static price sheet

TVP refreshes this page from the live OpenRouter model catalog. This render used 625 public model records and was synchronized Sep 29, 2026, 1:37 PM UTC. Pricing, availability, and context values can change.

Verify the exact route before sending production traffic, then use the linked model and provider pages as the source for current values. Read the TVP data methodology.

Shortlist

Top live candidates right now

mistralai

Mistral: Mistral Nemo

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Context131,072
Input$0.019
Output$0.03

$0.019 input and $0.03 output keeps traffic cost low while preserving usable context for production routes.

  • text
  • tools
  • structured
inclusionai

inclusionAI: Ling 3.0 Flash VL

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...

Context262,144
Input$0.021
Output$0.0616

$0.021 input and $0.0616 output keeps traffic cost low while preserving usable context for production routes.

  • text
  • image
  • video
  • tools
  • structured
inclusionai

inclusionAI: Ling 3.0 Flash

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

Context262,144
Input$0.021
Output$0.063

$0.021 input and $0.063 output keeps traffic cost low while preserving usable context for production routes.

  • text
  • tools
  • structured
sao10k

Sao10K: Llama 3 8B Lunaris

Lunaris 8B is a versatile generalist and roleplaying model based on Llama 3. It's a strategic merge of multiple models, designed to balance creativity with improved logic and general knowledge....

Context8,192
Input$0.04
Output$0.05

$0.04 input and $0.05 output keeps traffic cost low while preserving usable context for production routes.

  • text
  • structured
openai

OpenAI: gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Context131,072
Input$0.018
Output$0.09

$0.018 input and $0.09 output keeps traffic cost low while preserving usable context for production routes.

  • text
  • tools
  • structured
FAQ

What buyers usually ask

Why do free models not dominate this list?

This page is tuned for production buying. It focuses on paid, billable models so traffic planning is based on routes you can reliably meter, forecast, and scale.

What should I compare after price?

Context length and capability support usually matter next. A slightly more expensive model can save money if it reduces retries, prompt splitting, or fallback traffic.

Next step

Use the guide, then validate the route in live TVP data.

TVP keeps the shortlist connected to the current catalog, provider coverage, and token pricing so buyers can move from research to routing without starting over.