What free AI models are available right now?

ModelBench tracks 101 free AI models from 29 providers including OpenAI, Google, Cohere, NVIDIA, and more. Each model has a verified source where you can access its free tier with no upfront payment required.

Are free AI models actually free to use?

Yes. The models listed on this page have verified zero-price hosting offerings from at least one provider. Free tiers usually have rate limits or daily usage caps but require no payment or credit card to get started.

Which providers offer free AI models via API?

ModelBench tracks free model tiers from 29 providers. These include both model creators (Google with Gemini, Cohere, xAI with Grok) and inference gateways (OpenRouter, Poe) that serve a range of open and closed models at zero cost.

How do I get API access to a free model?

Click a model name to open its detail page, then view the Providers & pricing table for provider-specific API endpoints, documentation links, and rate limit details. Each row links directly to that provider's docs.

How often is the free models list updated?

ModelBench refreshes model data every 5 minutes from the models.dev catalog. When providers add, remove, or reprice a free tier, this page reflects the change within minutes.

Free AI Models: 101 Models with Free API Access

Free models101

Providers offering free tiers29

Catalog total4166

Catalog

All free AI models

Source-verified models with free API access. Data refreshes every 5 minutes from publicly listed pricing.

Source-verified free AI model tiers by provider
Model	Free providers	Context	Performance	Speed	Capabilities	Released
GLM-5.3-Flash zhipuai/glm-5.3-flash	ollama-cloud nan	1M	-	-	T Reasoning Tools Structured output	2026-08-26	Details
Qwen3.8 Flash alibaba/qwen3.8-flash	nan	1M	-	-	T Reasoning Tools Structured output	2026-08-26	Details
GLM-5.3 zhipuai/glm-5.3	ollama-cloud	1M	-	-	T Reasoning Tools Structured output	2026-08-14	Details
DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813	nvidia	1M	36	-	T Reasoning Tools Structured output	2026-08-12	Details
Grok 4.6 xai/grok-4.6	azure neon	500K	-	-	T Reasoning Tools Structured output	2026-08-12	Details
Nemotron 3.5 Lightning 30B A3B nvidia/nemotron-3.5-lightning-30b-a3b	nvidia	262.144K	-	-	T Reasoning Tools Structured output	2026-08-11	Details
Nemotron 3.5 Lightning 30B A3B nvidia/nemotron-3.5-lightning	nvidia	262.144K	14	-	T Reasoning Tools	2026-08-11	Details
Muse Glimmer 30B meta/muse-glimmer-30b	requesty nvidia	131.072K	-	-	T Reasoning Tools Structured output	2026-08-10	Details
Grok Imagine Image 2.0 xai/grok-imagine-image-2.0	xai	8K	-	-	T	2026-08-07	Details
DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731	nvidia hetzner ollama-cloud	1M	34	-	T Reasoning Tools Structured output	2026-07-31	Details
Claude Opus 5 anthropic/claude-opus-5	agentrouter	1M	51	-	T Reasoning Tools	2026-07-24	Details
Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite	sap-ai-core	1.04858M	23	-	T Reasoning Tools Structured output	2026-07-21	Details
Laguna S 2.1 poolside/laguna-s-2.1	opencode	1.04858M	-	-	T Reasoning Tools	2026-07-21	Details
Kimi K3 moonshotai/kimi-k3	sensenova nvidia	1.04858M	44	-	T Reasoning Tools Structured output	2026-07-16	Details
Inkling thinkingmachines/inkling	nvidia	1.04858M	26	-	T Tools Structured output	2026-07-15	Details
GPT-5.6 Sol openai/gpt-5.6-sol	agentrouter	1.05M	47	48 tps	T Reasoning Tools Structured output	2026-07-09	Details
Hy3 tencent/hy3	tencent-tokenhub	256K	-	59 tps	T Reasoning Tools Structured output	2026-07-06	Details
Laguna XS 2.1 poolside/laguna-xs-2.1	llmtr nvidia	262.144K	-	130 tps	T Reasoning Tools	2026-07-02	Details
GLM-5.2 zhipuai/glm-5.2	nan ollama-cloud sensenova nvidia	1M	-	-	T Reasoning Tools Structured output	2026-06-13	Details
Kimi K2.7 Code moonshotai/kimi-k2.7-code	hetzner	262.144K	26	177 tps	T Reasoning Tools Structured output	2026-06-12	Details
North Mini Code cohere/north-mini-code-1-0	cohere	256K	-	-	T Reasoning Tools Structured output	2026-06-09	Details
Nemotron 3.5 Content Safety nvidia/nemotron-3.5-content-safety	requesty	128K	-	-	T Reasoning	2026-06-04	Details
Nemotron 3 Ultra 550B A55B nvidia/nemotron-3-ultra-550b-a55b	requesty	1M	23	126 tps	T Reasoning Tools	2026-06-04	Details
MiniMax-M3 minimax/MiniMax-M3	nvidia	1.04858M	-	136 tps	T Reasoning Tools	2026-06-01	Details
Grok Imagine Video 1.5 xai/grok-imagine-video-1.5	xai	1.024K	-	-	T	2026-05-30	Details
Step 3.7 Flash stepfun/step-3.7-flash	nvidia	256K	31	120 tps	T Reasoning Tools Structured output	2026-05-29	Details
Claude Opus 4.8 anthropic/claude-opus-4-8	agentrouter	1M	-	66 tps	T Reasoning Tools	2026-05-28	Details
Mistral Medium 3.5 mistral/mistral-medium-2604	sap-ai-core nvidia	262.144K	-	-	T Reasoning Tools Structured output	2026-04-29	Details
Nemotron 3 Nano Omni 30B A3B Reasoning nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	requesty nvidia	256K	-	-	T Reasoning Tools	2026-04-28	Details
Laguna M.1 poolside/laguna-m.1	requesty	262.144K	-	74 tps	T Reasoning Tools	2026-04-28	Details
Laguna XS.2 poolside/laguna-xs.2	requesty	262.144K	-	-	T Reasoning	2026-04-28	Details
DeepSeek V4 Flash deepseek/deepseek-v4-flash	sensenova pendra nan	1M	25	79 tps	T Reasoning Tools Structured output	2026-04-24	Details
DeepSeek V4 Pro deepseek/deepseek-v4-pro	sensenova	1M	31	73 tps	T Reasoning Tools Structured output	2026-04-24	Details
Gemini Embedding 2 google/gemini-embedding-2	sap-ai-core	8.192K	-	-	T	2026-04-22	Details
MiMo-V2.5 xiaomi/mimo-v2.5	nan	1.04858M	22	44 tps	T Reasoning Tools Structured output	2026-04-22	Details
Qwen3.6 27B alibaba/qwen3.6-27b	pendra qvac	262.144K	-	-	T Tools	2026-04-22	Details
Kimi K2.6 moonshotai/kimi-k2.6	nvidia	262.144K	45	209 tps	T Reasoning Tools Structured output	2026-04-21	Details
Hy3 preview tencent/hy3-preview	tencent-tokenhub	256K	26	75 tps	T Reasoning Tools	2026-04-20	Details
Qwen3.6 35B-A3B alibaba/qwen3.6-35b-a3b	nan qvac	262.144K	-	-	T Reasoning Tools Structured output	2026-04-17	Details
Nemotron 3 Content Safety nvidia/nemotron-3-content-safety	nvidia	128K	-	-	T	2026-04-16	Details
Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it	nan cloudflare-ai-gateway google	262.144K	26	64 tps	T Reasoning Tools Structured output	2026-04-02	Details
Gemma 4 31B IT google/gemma-4-31b-it	cloudflare-ai-gateway qvac requesty nvidia google	262.144K	15	135 tps	T Reasoning Tools Structured output	2026-04-02	Details
Llama Nemotron Rerank VL 1B v2 nvidia/llama-nemotron-rerank-vl-1b-v2	nvidia	128K	-	-	T	2026-03-31	Details
Veo 3.1 Lite Preview google/veo-3.1-lite-generate-preview	google	1.024K	-	-	T	2026-03-31	Details
Lyria 3 Clip Preview google/lyria-3-clip-preview	edenai google openrouter	131.072K	-	6 tps	T	2026-03-25	Details
Lyria 3 Pro Preview google/lyria-3-pro-preview	google openrouter	131.072K	-	12 tps	T	2026-03-25	Details
MiniMax-M2.7 minimax/MiniMax-M2.7	nvidia	204.8K	-	206 tps	T Reasoning Tools	2026-03-18	Details
Nemotron VoiceChat nvidia/nemotron-voicechat	nvidia	128K	-	-	T Tools	2026-03-16	Details
Nemotron 3 Super 120B A12B nvidia/nemotron-3-super-120b-a12b	requesty	262.144K	14	70 tps	T Reasoning	2026-03-11	Details
Qwen3.5 9B alibaba/qwen3.5-9b	qvac	262.144K	-	-	T Reasoning Tools	2026-02-23	Details
Qwen3.5 122B-A10B alibaba/qwen3.5-122b-a10b	nvidia	262.144K	-	-	T Reasoning Tools Structured output	2026-02-23	Details
Llama Nemotron Embed VL 1B v2 nvidia/llama-nemotron-embed-vl-1b-v2	nvidia	32.768K	-	-	T	2026-02-10	Details
GPT-5.3 Codex Spark openai/gpt-5.3-codex-spark	poe	128K	-	-	T Reasoning Tools	2026-02-05	Details
Step 3.5 Flash stepfun/step-3.5-flash	nvidia	256K	-	46 tps	T	2026-01-29	Details
Trinity Large Preview arcee-ai/trinity-large-preview	opencode	524.288K	-	-	T Tools	2026-01-27	Details
DeepSeek OCR 2 deepseek/deepseek-ocr-2	regolo-ai	8.192K	-	-	T	2026-01-27	Details
Nemotron Content Safety Reasoning 4B nvidia/nemotron-content-safety-reasoning-4b	nvidia	128K	-	-	T Reasoning	2026-01-22	Details
GLM-4.7-Flash zhipuai/glm-4.7-flash	pendra zhipuai zai	200K	-	-	T Reasoning Tools	2026-01-19	Details
Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b	nvidia	262.144K	9	132 tps	T	2025-12-15	Details
GPT-Image-1.5 openai/gpt-image-1.5	poe	Not documented	-	-	T	2025-11-25	Details
Grok 4.1 Fast (Reasoning) xai/grok-4.1-fast-reasoning	poe	2M	-	-	T Reasoning Tools Structured output	2025-11-19	Details
Nemotron Nano 12B v2 VL nvidia/nemotron-nano-12b-v2-vl	nvidia	128K	-	-	T Reasoning Tools	2025-10-28	Details
Llama 3.1 Nemotron Safety Guard 8B v3 nvidia/llama-3.1-nemotron-safety-guard-8b-v3	nvidia	128K	-	-	T	2025-10-28	Details
Veo 3.1 Preview google/veo-3.1-generate-preview	google	1.024K	-	-	T	2025-10-15	Details
Veo 3.1 Fast Preview google/veo-3.1-fast-generate-preview	google	1.024K	-	-	T	2025-10-15	Details
GLM-4.6 zhipuai/glm-4.6	poe	204.8K	-	-	T Reasoning Tools	2025-09-30	Details
GPT OSS 120B openai/gpt-oss-120b	pendra nvidia qvac	131.072K	12	734 tps	T Reasoning Tools Structured output	2025-08-05	Details
GPT OSS 20B openai/gpt-oss-20b	nvidia qvac lmstudio	131.072K	9	374 tps	T Reasoning Tools	2025-08-05	Details
GLM-4.5-Flash zhipuai/glm-4.5-flash	zhipuai zai	131.072K	-	-	T Reasoning Tools	2025-07-28	Details
Llama 3.3 Nemotron Super 49B v1.5 nvidia/llama-3.3-nemotron-super-49b-v1.5	nvidia	131.072K	-	46 tps	T Reasoning Tools	2025-07-25	Details
Gemini Embedding 001 google/gemini-embedding-001	sap-ai-core	2.048K	-	-	T	2025-05-20	Details
Mistral Medium 3 mistral/mistral-medium-2505	nvidia	131.072K	-	-	T	2025-05-07	Details
GPT-Image-1 openai/gpt-image-1	poe	Not documented	-	89 tps	T Tools	2025-04-24	Details
o3 openai/o3	github-models	200K	-	90 tps	T Reasoning	2025-04-16	Details
o4-mini openai/o4-mini	github-models	200K	-	132 tps	T Reasoning Tools Structured output	2025-04-16	Details
Llama 3.1 Nemotron 70B Instruct nvidia/llama-3.1-nemotron-70b-instruct	nvidia	128K	-	-	T Tools	2025-04-15	Details
GPT-4.1 mini openai/gpt-4.1-mini	github-models	1.04758M	15	84 tps	T	2025-04-14	Details
GPT-4.1 openai/gpt-4.1	github-models	1.04758M	-	58 tps	T Tools Structured output	2025-04-14	Details
GPT-4.1 nano openai/gpt-4.1-nano	github-models	1.04758M	10	75 tps	T	2025-04-14	Details
Llama 3.1 Nemotron Ultra 253B nvidia/llama-3.1-nemotron-ultra-253b	nvidia	128K	-	-	T Reasoning Tools	2025-04-07	Details
Llama 3.3 Nemotron Super 49B v1 nvidia/llama-3.3-nemotron-super-49b-v1	nvidia	131.072K	-	-	T Reasoning Tools	2025-04-07	Details
Gemma 3 12B IT google/gemma-3-12b-it	nvidia	131.072K	4	38 tps	T	2025-03-12	Details
Gemma 3 4B IT google/gemma-3-4b-it	nvidia	131.072K	-	28 tps	T Tools Structured output	2025-03-12	Details
Aya Vision 32B cohere/c4ai-aya-vision-32b	cohere	16K	-	-	T	2025-03-04	Details
Aya Vision 8B cohere/c4ai-aya-vision-8b	cohere	16K	-	-	T	2025-03-04	Details
ALLaM-2-7b sdaia/allam-2-7b	groq	4.096K	-	-	T	2025-01-23	Details
DeepSeek-R1 deepseek/deepseek-r1	github-models	128K	11	78 tps	T Reasoning Tools	2025-01-20	Details
o3-mini openai/o3-mini	github-models	200K	-	240 tps	T Reasoning Tools Structured output	2024-12-20	Details
Llama-3.3-70B-Instruct meta/llama-3.3-70b-instruct	pendra nvidia llama github-models	128K	-	-	T Tools	2024-12-06	Details
o1 openai/o1	github-models	200K	-	153 tps	T Reasoning	2024-12-05	Details
Aya Expanse 32B cohere/c4ai-aya-expanse-32b	cohere	128K	-	-	T	2024-10-24	Details
Aya Expanse 8B cohere/c4ai-aya-expanse-8b	cohere	8K	-	-	T	2024-10-24	Details
Whisper 3 Large openai/whisper-large-v3	nvidia	448	-	-		2024-10-01	Details
Llama-3.2-11B-Vision-Instruct meta/llama-3.2-11b-vision-instruct	nvidia	128K	-	-	T Tools Structured output	2024-09-25	Details
Nemotron Mini 4B Instruct nvidia/nemotron-mini-4b-instruct	nvidia	128K	-	-	T Tools	2024-08-21	Details
Llama-3.1-70B-Instruct meta/llama-3.1-70b-instruct	nvidia	128K	-	-	T Tools Structured output	2024-07-23	Details
Llama-3.1-8B-Instruct meta/llama-3.1-8b-instruct	nvidia	128K	-	-	T Tools Structured output	2024-07-23	Details
GPT-4o mini openai/gpt-4o-mini	github-models	128K	-	36 tps	T	2024-07-18	Details
Mistral Nemo mistral/mistral-nemo	github-models	128K	-	-	T	2024-07-01	Details
GPT-4o openai/gpt-4o	github-models poe	128K	-	53 tps	T Tools	2024-05-13	Details
Qwen3-Coder 30B-A3B Instruct alibaba/qwen3-coder-30b-a3b-instruct	pendra	262.144K	-	-	T Tools	2025-04	Details

How to get free API access

Using free AI models

1. Pick a model from the list

The table above shows 101 free models with their providers, context lengths, and capabilities. Sort by context, performance, or featured provider to find what fits your use case.

2. Open the model detail page

Click any model name to see the full Providers & pricing table — the provider name links directly to that provider's documentation page where you can sign up and get an API key.

3. No credit card required

Every free provider on this list offers API access without requiring a payment method upfront. Rate limits vary — see the individual provider docs for specifics.

Free AI models you can use right now.

All free AI models

Using free AI models

1. Pick a model from the list

2. Open the model detail page

3. No credit card required

Free API providers tracked here