🌐All Models💬Text Generation💻Code & Reasoning👁️Vision & Multimodal🎨Image Generation🎙️Audio & Speech🤖Agents & Tools📄Long Context🆓Free & Open🧠Reasoning🌍Multilingual
🆓 Free & Open
837 models · Page 8 of 24
zai-org/GLM-4.7
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
allenai/Olmo-3.1-32B-Instruct
deepinfra
textinstructfree
ctxFree in
Explore specs and pricingView details →
google/gemini-2.5-flash
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
Bria/expand
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
nvidia/Nemotron-3-Nano-30B-A3B
deepinfra
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
textagentsfree
256,000 ctxFree in
Explore specs and pricingView details →
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
deepinfra
textinstructfree
ctxFree in
Explore specs and pricingView details →
Qwen/Qwen3-Embedding-4B-batch
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
deepinfra
textinstructfree
ctxFree in
Explore specs and pricingView details →
ClarityAI/creative
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
NousResearch/Hermes-3-Llama-3.1-405B
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
zai-org/GLM-5.1
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
google/gemini-1.5-flash-8b
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
mistralai/Mixtral-8x7B-Instruct-v0.1
deepinfra
Mixtral 8×7B Instruct on DeepInfra — popular MoE model with 32K context and strong multilingual performance.
textmultilingualinstruct
ctxFree in
Explore specs and pricingView details →
ClarityAI/crystal
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
nvidia/NVIDIA-Nemotron-Nano-9B-v2
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
Qwen/Qwen3.5-35B-A3B
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
mistralai/Mistral-Small-3.2-24B-Instruct-2506
deepinfra
textinstructfree
ctxFree in
Explore specs and pricingView details →
embed-multilingual-light-v3.0-image
cohere
textmultilingualfree
ctxFree in
Explore specs and pricingView details →
black-forest-labs/FLUX-pro
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
Qwen/Qwen3-Embedding-0.6B
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
PaddlePaddle/PaddleOCR-VL-0.9B
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
Qwen/Qwen3-Embedding-0.6B-batch
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
google/gemma-3-27b-it
deepinfra
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
textvisionreasoning
131,072 ctxFree in
Explore specs and pricingView details →
Sao10K/L3-8B-Lunaris-v1-Turbo
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
Bria/fibo_edit
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
embed-english-light-v3.0
cohere
textfree
512 ctxFree in
Explore specs and pricingView details →
Qwen/Qwen2.5-VL-32B-Instruct
deepinfra
textinstructfree
ctxFree in
Explore specs and pricingView details →
thenlper/gte-large
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
Wan-AI/Wan2.6-Image-Edit
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
BAAI/bge-m3-multi
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
black-forest-labs/FLUX-2-klein-4b
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
embed-multilingual-light-v3.0
cohere
textmultilingualfree
512 ctxFree in
Explore specs and pricingView details →
black-forest-labs/FLUX-1-dev
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →
openai/gpt-oss-120b
deepinfra
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
textreasoningagents
131,072 ctxFree in
Explore specs and pricingView details →
black-forest-labs/FLUX-2-pro
deepinfra
textfree
ctxFree in
Explore specs and pricingView details →