Best free LLM APIs (2026)

Which models can you call for $0 today, and what are you giving up?

Rebuilt from live model data · August 3, 2026

How we ranked

Models priced at $0 for both input and output on OpenRouter, ranked by Intelligence Index.

Top 3 for best free llm apis

  1. 1

    Nemotron 3 Ultra (free)

    Intelligence index: 37.8 Free in / Free out per 1M 1M context 1 provider

    NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Open weights Tool calling Reasoning Released Jun 4, 2026
  2. 2

    Gemma 4 31B (free)

    Intelligence index: 29.4 Free in / Free out per 1M 262K context 1 provider

    Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

    Open weights Vision Tool calling Reasoning Released Apr 2, 2026
  3. 3

    Gemma 4 26B A4B (free)

    Intelligence index: 25.7 Free in / Free out per 1M 262K context 2 providers

    Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

    Open weights Vision Tool calling Reasoning Released Apr 3, 2026

Full ranking

#ModelIntelligence indexOutput / 1M ContextProvidersWeights
1 Nemotron 3 Ultra (free) 37.8 Free 1M 1 Open
2 Gemma 4 31B (free) 29.4 Free 262K 1 Open
3 Gemma 4 26B A4B (free) 25.7 Free 262K 2 Open
4 Nemotron 3 Super (free) 25.4 Free 262K 1 Open
5 North Mini Code (free) 19.8 Free 256K 1 Open
6 gpt-oss-20b (free) 14.9 Free 131K 1 Open
7 Nemotron 3 Nano 30B A3B (free) 14.2 Free 256K 1 Open
8 Free Models Router Free 200K 0 Closed
9 Lyria 3 Clip Preview Free 1.0M 1 Closed
10 Lyria 3 Pro Preview Free 1.0M 1 Closed
11 Ling-3.0-flash (free) Free 262K 1 Closed
12 Nemotron 3 Nano Omni (free) Free 256K 1 Open

FAQ

Which models can you call for $0 today, and what are you giving up?

Nemotron 3 Ultra (free) leads for Best free LLM APIs with intelligence index 37.8, at Free per 1M output tokens. Gemma 4 31B (free) (29.4) and Gemma 4 26B A4B (free) (25.7) follow. Models priced at $0 for both input and output on OpenRouter, ranked by Intelligence Index.

How is this ranking produced?

Models priced at $0 for both input and output on OpenRouter, ranked by Intelligence Index. The list rebuilds from the live model catalogue on every deploy, so a model that launches or changes price appears here without an editor rewriting the page. Last rebuild: August 3, 2026.

What does the top pick cost to run?

Pricing for Nemotron 3 Ultra (free) is not published through OpenRouter.