Free Models

openrouter
Free/1M

Free Models Router

The simplest way to get free inference. openrouter/free is a router that selects free mode...

📝 200,000 ctx Compare →
stepfun
Free/1M

StepFun: Step 3.5 Flash (free)

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse M...

📝 256,000 ctx Compare →
arcee-ai
Free/1M

Arcee AI: Trinity Large Preview (free)

Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as ...

📝 131,000 ctx Compare →
liquid
Free/1M

LiquidAI: LFM2.5-1.2B-Thinking (free)

LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks,...

📝 32,768 ctx Compare →
liquid
Free/1M

LiquidAI: LFM2.5-1.2B-Instruct (free)

LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast...

📝 32,768 ctx Compare →
nvidia
Free/1M

NVIDIA: Nemotron 3 Nano 30B A3B (free)

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficien...

📝 256,000 ctx Compare →
arcee-ai
Free/1M

Arcee AI: Trinity Mini (free)

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featu...

📝 131,072 ctx Compare →
nvidia
Free/1M

NVIDIA: Nemotron Nano 12B 2 VL (free)

NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model design...

📝 128,000 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 VL 30B A3B Thinking

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with v...

📝 131,072 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 VL 235B A22B Thinking

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with...

📝 131,072 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 Next 80B A3B Instruct (free)

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series op...

📝 262,144 ctx Compare →
nvidia
Free/1M

NVIDIA: Nemotron Nano 9B V2 (free)

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA,...

📝 128,000 ctx Compare →
openai
Free/1M

OpenAI: gpt-oss-120b (free)

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model fro...

📝 131,072 ctx Compare →
openai
Free/1M

OpenAI: gpt-oss-20b (free)

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 ...

📝 131,072 ctx Compare →
z-ai
Free/1M

Z.ai: GLM 4.5 Air (free)

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-b...

📝 131,072 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 235B A22B Thinking 2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) ...

📝 131,072 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 Coder 480B A35B (free)

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model develop...

📝 262,000 ctx Compare →
cognitivecomputations
Free/1M

Venice: Uncensored (free)

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Sm...

📝 32,768 ctx Compare →
google
Free/1M

Google: Gemma 3n 2B (free)

Gemma 3n E2B IT is a multimodal, instruction-tuned model developed by Google DeepMind, des...

📝 8,192 ctx Compare →
google
Free/1M

Google: Gemma 3n 4B (free)

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, s...

📝 8,192 ctx Compare →
qwen
Free/1M

Qwen: Qwen3 4B (free)

Qwen3-4B is a 4 billion parameter dense language model from the Qwen3 series, designed to ...

📝 40,960 ctx Compare →
mistralai
Free/1M

Mistral: Mistral Small 3.1 24B (free)

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring...

📝 128,000 ctx Compare →
google
Free/1M

Google: Gemma 3 4B (free)

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It ha...

📝 32,768 ctx Compare →
google
Free/1M

Google: Gemma 3 12B (free)

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It ha...

📝 32,768 ctx Compare →
google
Free/1M

Google: Gemma 3 27B (free)

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It ha...

📝 131,072 ctx Compare →
meta-llama
Free/1M

Meta: Llama 3.3 70B Instruct (free)

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction...

📝 128,000 ctx Compare →
meta-llama
Free/1M

Meta: Llama 3.2 3B Instruct (free)

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for adv...

📝 131,072 ctx Compare →
nousresearch
Free/1M

Nous: Hermes 3 405B Instruct (free)

Hermes 3 is a generalist language model with many improvements over Hermes 2, including ad...

📝 131,072 ctx Compare →