Awesome Free LLM APIs

PProvider APIs

APIs run by the companies that train or fine-tune the models themselves.

01 Aion Labs 🇮🇱 key page api.aionlabs.ai/v1

Permanent free tier, no credit card required. 15 RPM, 20K tokens/day. Specialized for roleplay and storytelling.

Base URLhttps://api.aionlabs.ai/v1

Model Name	Context	Max Output	Modality	Rate Limit
`aion-labs/aion-2.0`	128K	32K	Text (reasoning)	15 RPM, 20K TPD
`aion-labs/aion-rp-llama-3.1-8b`	32K	32K	Text	15 RPM, 20K TPD
`aion-labs/aion-3.0`	128K	32K	Text (reasoning)	15 RPM, 20K TPD
`aion-labs/aion-3.0-mini`	128K	32K	Text (reasoning)	15 RPM, 20K TPD

02 Cohere 🇨🇦 key page api.cohere.com/v2

Free "Trial" API key, no credit card. 1,000 API calls/month. Non-commercial use only.

Native API base URLhttps://api.cohere.com/v2

OpenAI-compatible base URLhttps://api.cohere.ai/compatibility/v1

Model Name	Context	Max Output	Modality	Rate Limit
Command A+ (218B)	128K	64K	Text + Image	20 RPM
Command A (111B)	256K	8K	Text	20 RPM
Command R+	128K	4K	Text	20 RPM
Command R	128K	4K	Text	20 RPM
Command R7B	128K	4K	Text	20 RPM
Command A Reasoning	256K	32K	Text (reasoning)	20 RPM
Command A Translate	8K	8K	Text	20 RPM
Command A Vision	128K	8K	Text + Image	20 RPM
Command R7B Arabic	128K	~4K	Text	20 RPM
Aya Expanse 32B	128K	4K	Text	20 RPM
Aya Vision 32B	16K	4K	Text + Image	20 RPM

03 Google Gemini 🇺🇸 key page generativelanguage.googleapis.com/v1beta

Free tier, no credit card. Free-tier prompts may be used by Google to improve products. ¹

Native API base URLhttps://generativelanguage.googleapis.com/v1beta

OpenAI-compatible base URLhttps://generativelanguage.googleapis.com/v1beta/openai/

Model Name	Context	Max Output	Modality	Rate Limit
Gemini 3.8 Flash	1M	65K	Text + Image + Audio + Video	—
Gemini 3.6 Flash	1M	65K	Text + Image + Audio + Video	—
Gemini 3.5 Flash-Lite	1M	65K	Text + Image + Audio + Video	—
Gemini 3.1 Flash-Lite	1M	65K	Text + Image + Audio + Video	—
Gemini 2.5 Flash	1M	65K	Text + Image + Audio + Video	—
Gemini 2.5 Flash-Lite	1M	65K	Text + Image + Audio + Video	—
Gemma 4 31B	256K	32K	Text + Image	—
Gemma 4 26B A4B	256K	32K	Text + Image	—

04 Mistral AI 🇫🇷 key page api.mistral.ai/v1

Free mode, enabled by default, no credit card required. Free-mode prompts may be used to train Mistral models unless you opt out. ¹³

Base URLhttps://api.mistral.ai/v1

Model Name	Context	Max Output	Modality	Rate Limit
Mistral Medium 3.5 (128B)	256K	—	Text + Image + Code	~1 RPS, 500K TPM
Mistral Small 4	256K	—	Text + Image + Code	~1 RPS, 500K TPM
Mistral Large 3	256K	—	Multimodal	~1 RPS, 500K TPM
Ministral 3 8B	256K	—	Text + Vision	~1 RPS, 500K TPM
Codestral	128K	—	Code	~1 RPS, 500K TPM
Ministral 3 3B	256K	—	Text + Vision	~1 RPS, 500K TPM
Ministral 3 14B	256K	—	Text + Vision	~1 RPS, 500K TPM

05 Z AI (Zhipu AI) 🇨🇳 key page open.bigmodel.cn/api/paas/v4

Permanent free models, no credit card required. ¹²

Base URLhttps://open.bigmodel.cn/api/paas/v4

Model Name	Context	Max Output	Modality	Rate Limit
GLM-4.7-Flash	200K	128K	Text (reasoning)	1 concurrent request
GLM-4.5-Flash (retirement announced)	128K	96K	Text (reasoning)	1 concurrent request
GLM-4.6V-Flash	128K	32K	Multimodal	1 concurrent request

IInference providers

Third-party platforms that host open-weight models from various sources.

06 Cloudflare Workers AI 🇺🇸 key page api.cloudflare.com/client/v4/accounts/{account_id}/ai/run

10,000 Neurons/day free, no credit card required. 60+ models available on the free tier. ¹¹

Native API base URLhttps://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run

OpenAI-compatible base URLhttps://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1

Model Name	Context	Max Output	Modality	Rate Limit
`@cf/meta/llama-3.3-70b-instruct-fp8-fast`	24K	Shared w/ context	Text	10K neurons/day (shared)
`@cf/meta/llama-4-scout-17b-16e-instruct`	131K	Shared w/ context	Multimodal	10K neurons/day (shared)
`@cf/openai/gpt-oss-120b`	128K	Shared w/ context	Text	10K neurons/day (shared)
`@cf/google/gemma-4-26b-a4b-it`	256K	Shared w/ context	Text + Vision	10K neurons/day (shared)
`@cf/zai-org/glm-4.7-flash`	131K	Shared w/ context	Text	10K neurons/day (shared)
`@cf/mistralai/mistral-small-3.1-24b-instruct`	128K	Shared w/ context	Text + Vision	10K neurons/day (shared)
`@cf/deepseek-ai/deepseek-r1-distill-qwen-32b`	80K	Shared w/ context	Text (reasoning)	10K neurons/day (shared)
+ 55 more models	Varies	Varies	Text, Image, Audio, Embeddings	10K neurons/day (shared)

07 Gonka Broker 🇺🇸 key page proxy.gonkabroker.com/v1

Permanent free tier, no credit card required; phone verification required. ~1M tokens/month (shared, varies by model), resets monthly. Model lineup rotates with network governance — live list at /v1/models. ¹⁴

Base URLhttps://proxy.gonkabroker.com/v1

Model Name	Context	Max Output	Modality	Rate Limit
`MiniMaxAI/MiniMax-M2.7`	200K	16K	Text (reasoning)	~1M tokens/month (shared, varies by model)
`deepseek-ai/DeepSeek-V4-Flash-0731`	400K	16K	Text (reasoning)	~1M tokens/month (shared, varies by model)
`zai-org/GLM-5.3-Flash`	400K	16K	Text (reasoning)	~1M tokens/month (shared, varies by model)
`BAAI/bge-m3`	8K	—	Embeddings	~1M tokens/month (shared, varies by model)

08 Groq 🇺🇸 key page api.groq.com/openai/v1

Free tier, no credit card. Ultra-fast LPU inference. ²

Base URLhttps://api.groq.com/openai/v1

Model Name	Context	Max Output	Modality	Rate Limit
`openai/gpt-oss-120b`	131K	65K	Text	30 RPM, 1,000 RPD
`openai/gpt-oss-20b`	131K	65K	Text	30 RPM, 1,000 RPD
`qwen/qwen3.8-27b`	131K	16K	Text + Image	30 RPM, 1,000 RPD

09 Kilo Code 🇺🇸 key page api.kilo.ai/api/gateway

Free models with no credit card and no API key required. kilo-auto/free auto-router dynamically routes to models in the free pool. ⁵

Base URLhttps://api.kilo.ai/api/gateway

Model Name	Context	Max Output	Modality	Rate Limit
`nvidia/nemotron-3-ultra-550b-a55b:free`	1M	65K	Text	200 req/hr
`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`	256K	65K	Multimodal	200 req/hr
`cohere/north-mini-code:free`	256K	64K	Text (code)	200 req/hr
`openrouter/free`	Varies	Varies	Text	200 req/hr
`nvidia/nemotron-3.5-lightning:free`	1M	65K	Text	200 req/hr
`liquid/lfm-2.5-2.6b:free`	64K	8K	Text	200 req/hr
`kilo-auto/free`	256K	32K	Text	200 req/hr
`dots-studio/dots-3-note-preview:free`	512K	460K	Text + Vision	200 req/hr
`recursive/flint-v1.0:free`	262K	235K	Text (code)	200 req/hr
`xingchen-agi/xing4.0-29b-a4b:free`	262K	235K	Text	200 req/hr
`nvidia/nemotron-3.5-super-vl:free`	1M	131K	Multimodal	200 req/hr
`reflection/beam-free`	1M	131K	Text	200 req/hr
`stealth/glyph-cluster`	256K	256K	Text (code)	200 req/hr

10 LLM7.io 🇬🇧 key page api.llm7.io/v1

API gateway with a free tier. Anonymous access needs no key and reaches the turbo models; a free token from token.llm7.io raises the rate and token limits but reaches the same models. ¹⁰

Base URLhttps://api.llm7.io/v1

Model Name	Context	Max Output	Modality	Rate Limit
`gpt-oss:20b`	128K	—	Text	60 RPM, 250 req/hr (free token)
mistral-Nemo-Instruct-2407	128K	—	Text	60 RPM, 250 req/hr (free token)
`nemotron-3-nano:30b`	1M	—	Text (reasoning)	60 RPM, 250 req/hr (free token)
codestral-latest	32K	—	Text	60 RPM, 250 req/hr (free token)

11 ModelScope 🇨🇳 key page api-inference.modelscope.cn/v1

Free API-Inference for registered users. Requires Alibaba Cloud account binding + real-name verification. ⁶

Base URLhttps://api-inference.modelscope.cn/v1

Model Name	Context	Max Output	Modality	Rate Limit
`Qwen/Qwen3.5-35B-A3B`	256K	—	Text	2,000 RPD total; <=500 RPD/model (dynamic)
`Qwen/Qwen3.5-27B`	256K	—	Text	2,000 RPD total; <=500 RPD/model (dynamic)
+ API-Inference-enabled models	Varies	Varies	LLM, MLLM	Dynamic quotas + dynamic concurrency

12 NVIDIA NIM 🇺🇸 key page integrate.api.nvidia.com/v1

Free with NVIDIA Developer Program membership. 100+ models. Rate-limited per model.

Base URLhttps://integrate.api.nvidia.com/v1

Model Name	Context	Max Output	Modality	Rate Limit
`google/gemma-4-31b-it`	262K	8K	Text + Image + Video	40 RPM, 10,000 RPD
`nvidia/nemotron-3-ultra-550b-a55b`	1M	262K	Text	40 RPM, 10,000 RPD
`openai/gpt-oss-20b`	131K	131K	Text	40 RPM, 10,000 RPD
+ 92 more models	Varies	Varies	Text, Image, Video, Speech, Embeddings	40 RPM, 10,000 RPD

13 OpenRouter 🇺🇸 key page openrouter.ai/api/v1

17 free models (marked with :free suffix). OpenAI SDK-compatible. ⁴

Base URLhttps://openrouter.ai/api/v1

Model Name	Context	Max Output	Modality	Rate Limit
`cohere/north-mini-code:free`	256K	64K	Text (code)	20 RPM, 50 RPD
`google/gemma-4-26b-a4b-it:free`	262K	32K	Text + Image + Video	20 RPM, 50 RPD
`google/gemma-4-31b-it:free`	262K	32K	Text + Image + Video	20 RPM, 50 RPD
`dots-studio/dots-3-note-preview:free`	512K	460K	Text + Image	20 RPM, 50 RPD
`liquid/lfm-2.5-2.6b:free`	64K	8K	Text	20 RPM, 50 RPD
`nvidia/nemotron-3.5-lightning:free`	1M	65K	Text	20 RPM, 50 RPD
`thinkingmachines/inkling:free`	1M	262K	Text + Image + Audio	20 RPM, 50 RPD
`nvidia/nemotron-3-ultra-550b-a55b:free`	1M	65K	Text	20 RPM, 50 RPD
`recursive/flint-v1.0:free`	262K	235K	Text	20 RPM, 50 RPD
`xingchen-agi/xing4.0-29b-a4b:free`	262K	235K	Text	20 RPM, 50 RPD
`nvidia/nemotron-3.5-super-vl:free`	1M	131K	Text + Image + Video	20 RPM, 50 RPD
`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free`	256K	65K	Text + Image + Audio + Video	20 RPM, 50 RPD
`thinkingmachines/inkling-small:free`	1M	262K	Text + Image + Audio	20 RPM, 50 RPD

14 OVHcloud AI Endpoints 🇫🇷 key page oai.endpoints.kepler.ai.cloud.ovh.net/v1

Free anonymous tier (no API key, no signup): 2 RPM per IP per model. 20+ open-weight models hosted in EU. OpenAI SDK-compatible. ⁷

Base URLhttps://oai.endpoints.kepler.ai.cloud.ovh.net/v1

Model Name	Context	Max Output	Modality	Rate Limit
Qwen3.5-397B-A17B	262K	~32K	Text + Vision	2 RPM (anonymous)
gpt-oss-120b	131K	~32K	Text	2 RPM (anonymous)
gpt-oss-20b	131K	~8K	Text	2 RPM (anonymous)
Meta-Llama-3_3-70B-Instruct	131K	~4K	Text	2 RPM (anonymous)
Qwen3.8-27B	262K	—	Text + Vision	2 RPM (anonymous)
Qwen3.6-27B	262K	~32K	Text + Vision	2 RPM (anonymous)
Qwen3.5-9B	262K	~8K	Text + Vision	2 RPM (anonymous)
Qwen2.5-VL-72B-Instruct	32K	~8K	Text + Vision	2 RPM (anonymous)
Mistral-Small-3.2-24B-Instruct	128K	~4K	Text + Vision	2 RPM (anonymous)
Mistral-Nemo-Instruct-2407	118K	~4K	Text	2 RPM (anonymous)

15 SiliconFlow 🇨🇳 key page api.siliconflow.cn/v1

Permanently free models, no credit card required. Identity verification required. 100+ models in the catalog, most of them paid. ⁹

Base URLhttps://api.siliconflow.cn/v1

Model Name	Context	Max Output	Modality	Rate Limit
`tencent/Hunyuan-MT-7B`	—	—	Text	—
`XingChenAGI/Xing4.0-29B`	—	—	Text	—

GGlossary

Abbreviation	Meaning
RPM	Requests per minute
RPD	Requests per day
TPM	Tokens per minute
TPD	Tokens per day
RPS	Requests per second

CContributing

Know a free tier that's missing? Open a PR. Include the provider, endpoint, rate limits (link to their docs), and a few notable models. Trial credits and time-limited promos don't count.

[1] The Gemini API free tier is available to developers in the EU, UK, and Switzerland; the available regions page lists these regions. The terms still require you to use only Paid Services when you make an API Client available to users in the European Economic Area, Switzerland, or the UK. Google no longer publishes per-model free-tier rate limits; check your quotas in AI Studio. Free-tier prompts may be used by Google to improve products, except for users in the EEA, Switzerland and the UK, where the paid-services data terms also govern the unpaid quota, so those prompts are not used to improve Google products. gemini-3.1-flash-lite is on the deprecation schedule, with a shutdown date of May 7, 2027 and gemini-3.5-flash-lite as its replacement; the row stays because the model is live and free today.

[2] Groq shut down qwen/qwen3.6-27b on September 14, 2026 (replaced by qwen/qwen3.8-27b) and groq/compound and groq/compound-mini on September 21, 2026 (deprecations). Free-plan limits vary by model; the chat models listed get 1,000 RPD (rate limits).

[4] Free models allow 20 requests per minute and 50 requests per day, counted across all free models. Accounts that bought at least 10 credits get 1,000 requests per day (limits). OpenRouter also offers a Free Models Router (openrouter/free) and model fallbacks for chaining models in priority order. Free providers may log prompts for training.

[5] Kilo Code's free pool changes frequently, and the /api/gateway/models catalog can lag what is actually served: probe results have confirmed models absent from the catalog still answering. Rows through liquid/lfm-2.5-2.6b:free answered a live request between 2026-08-19 and 2026-08-21; the rows after it were added on 2026-10-05 (through dots-studio/dots-3-note-preview:free), 2026-10-23 and 2026-10-25 from the catalog, where they are priced at $0, and have not been probed. The catalog describes reflection/beam-free as served through Vercel AI Gateway and notes that prompts may be retained for training. Free models are reachable with no API key, at 200 requests per hour per IP (authentication). The kilo-auto/free router picks a model from the free pool, and Kilo's docs warn it "may route your requests to providers that log prompts and outputs". The NVIDIA free endpoints carry NVIDIA's own condition, quoted on Kilo's models page: "Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services."

[6] API-Inference is free for registered users. Current published limits are 2,000 requests/day per user (total across models), with per-model daily quotas dynamically adjusted and capped at 500; concurrency is also dynamically rate-limited. Requires Alibaba Cloud account binding and real-name verification (limits, intro). This entry is based on ModelScope's documentation. It cannot be tested from outside mainland China.

[7] OVHcloud AI Endpoints offers a permanent free anonymous tier (2 requests per minute per IP, per model) with no signup or API key required. Higher rate limits (400 RPM per Public Cloud project per model) require an API key and are billed pay-as-you-go per token; new Public Cloud accounts get up to $200 in free trial credits. Models are hosted in EU data centers. The catalog lists an end of life on November 4, 2026 for Mistral-Small-3.2-24B-Instruct-2506 and Mistral-Nemo-Instruct-2407.

[9] SiliconFlow requires real-name identity verification to use free models (effective May 15, 2026, per the release notes). Verification supports mainland-Chinese documents; international users must contact support. This entry is based on SiliconFlow's pricing page, which marks these models free. It cannot be tested from outside mainland China.

[10] LLM7.io rotates its catalog frequently, so the model list changes between checks. Access is tier-based, not token-based: turbo models are reachable anonymously or with a free token, pro models need the paid plan (models API). A free token is capped at 1 RPS, 60 RPM, 250 requests per hour and 100,000 tokens per 24 hours, and the free quota may be reduced without notice (limits). A paid Pro plan is available at $12/month. The docs no longer list anonymous (no-key) limits; anonymous access was last confirmed by live request on 2026-08-21.

[11] The 10,000 free Neurons are shared across all Workers AI usage, not per model, and all limits reset daily at 00:00 UTC. Going over does not bill you, the request fails. Seven models are excluded from Workers Free billing and need the Workers Paid plan or prepaid AI Gateway credits: @cf/moonshotai/kimi-k2.6, @cf/moonshotai/kimi-k2.7-code, @cf/zai-org/glm-5.2, @cf/zai-org/glm-5.3, @cf/zai-org/glm-5.3-flash, @cf/deepseek-ai/deepseek-v4-flash-0731, @cf/deepseek-ai/deepseek-v4-pro-0813 (pricing).

[12] Registration accepts overseas phone numbers (registration FAQ) and the chat API does not require real-name verification: 目前调用 API 并不强制要求实名认证 (authentication FAQ). The Batch API does require it (batch FAQ). The same free models are served from the international platform at https://api.z.ai/api/paas/v4 (endpoint), where GLM-4.7-Flash, GLM-4.5-Flash and GLM-4.6V-Flash are all priced Free (pricing). Z AI has announced that GLM-4.5-Flash will be retired and its requests auto-routed to GLM-4.7-Flash (model page); the announced date has already passed while the model is still catalogued and still priced Free, so treat that row as living on borrowed time.

[13] Mistral plans are global: the monthly allowance is shared across Studio, the API, and Vibe Code, so CLI usage eats the same budget (subscriptions). Free mode is the default for new accounts and needs no credit card (quickstart), and the Free plan card on the pricing page lists no API credit amount. Free-mode inputs and outputs may be used to train Mistral models, and you can opt out at any time (data usage). Mistral no longer publishes numeric free-tier rate limits and points you at the Limits page of the admin panel instead (rate limits); the rate limit column is kept from the last published values.

[14] The free grant is issued only after SMS verification with a real (non-VoIP) phone number, one grant per number (billing docs). Unused free tokens do not carry over to the next month. The grant is sized as at least 1M tokens of the most expensive model; cheaper models stretch further (e.g. ~6M tokens for BGE-M3) (free tier page). While running on free-tier funds only, requests are capped at a lower rate; the current cap is returned as maxRpm by /test-auth (limits).