Best Free LLM APIs for Reasoning

22 free models available for reasoning.

Provider Model Context Max Output Modality Rate Limit
OpenRouter NVIDIA: Nemotron 3 Nano Omni (free) 256K 66K textimageaudio See provider page Details
OpenRouter NVIDIA: Nemotron 3 Super (free) 262K 262K text See provider page Details
OpenRouter LiquidAI: LFM2.5-1.2B-Thinking (free) 33K 8K textreasoning See provider page Details
OpenRouter NVIDIA: Nemotron 3 Nano 30B A3B (free) 256K 8K text See provider page Details
OpenRouter NVIDIA: Nemotron Nano 12B 2 VL (free) 128K 128K textimage See provider page Details
OpenRouter NVIDIA: Nemotron Nano 9B V2 (free) 128K 8K text See provider page Details
Cloudflare Workers AI @cf/deepseek-ai/deepseek-r1-distill-qwen-32b 32K 131K text 10K neurons/day (shared) Details
GitHub Models DeepSeek-R1 64K 8K text 15 RPM, 150 RPD Details
Groq deepseek-r1-distill-70b 131K 8K text 30 RPM, 14,400 RPD Details
Kilo Code nvidia/nemotron-3-super-120b-a12b:free 262K 32K text ~200 req/hr Details
Kilo Code arcee-ai/trinity-large-thinking:free 131K 131K text ~200 req/hr Details
LLM7.io deepseek-r1-0528 131K 131K text 30 RPM (120 with token) Details
NVIDIA NIM deepseek-ai/deepseek-r1 128K 163K text ~40 RPM Details
NVIDIA NIM nvidia/llama-3.1-nemotron-ultra-253b-v1 128K 4K text ~40 RPM Details
NVIDIA NIM nvidia/nemotron-3-super-120b-a12b 262K 262K text ~40 RPM Details
NVIDIA NIM nvidia/nemotron-3-nano-30b-a3b 128K 32K text ~40 RPM Details
NVIDIA NIM nvidia/nemotron-nano-2-vl 128K 8K textimage ~40 RPM Details
Ollama Cloud deepseek-r1:cloud 128K 131K text Session/weekly limits (unpublished) Details
OVHcloud AI Endpoints DeepSeek-R1-Distill-Llama-70B 131K 32K text 2 RPM (anonymous) Details
SiliconFlow deepseek-ai/DeepSeek-R1-0528-Qwen3-8B 33K 16K text 1,000 RPM, 50K TPM Details
SiliconFlow deepseek-ai/DeepSeek-R1-Distill-Qwen-7B 131K 131K text 1,000 RPM, 50K TPM Details
SiliconFlow THUDM/GLM-4.1V-9B-Thinking 66K 66K text 1,000 RPM, 50K TPM Details