Best Free AI APIs: Which Ones Still Work, Tested

On this page
  1. How to choose
  2. Free LLM APIs compared
  3. Model IDs that answered
  4. Speed: tokens per second, measured 2026-08-31
  5. How we check
  6. One code pattern for almost all of them
  7. Frequently asked questions
Quick answer (data last checked ): of the 14 LLM APIs we track that have (or had) a free tier, 6 have a free tier you can use today without paying: Groq, Google Gemini, Mistral, OpenRouter, NVIDIA NIM and Cloudflare Workers AI. Zhipu GLM and Gonka Broker are free too, but only after you verify a phone number. Cohere offers only a rate-limited trial key, meant for testing. Cerebras and SambaNova Cloud need a card before the API works. Gone entirely: DeepSeek API (closed 2026-08-31), Together AI (closed 2026-08-31) and GitHub Models (closed 2026-07-30). Every row below shows the date we last checked it, and the model IDs are the ones that actually answered a call — not the ones the provider still lists.

Most "best free AI API" lists copy each vendor's marketing page once and never look again. Free tiers in 2026 do not sit still: in the last few months DeepSeek and Together stopped giving free credit, SambaNova refused our free account without a card, GitHub Models shut down, Cerebras put its trial behind a card, and model IDs that the providers still list started returning 404. This page is built from a data file that we re-check by calling every provider's API, so each row carries the date it was last confirmed.

How to choose

Pick by what your app needs, not by brand. Each line below drops off automatically if that provider's free tier closes or starts asking for a card.

  • Fastest replies (chat, voice, agents) → Groq. The fastest generation we have measured on any free tier. (checked 2026-10-11)
  • Long documents, PDFs, images → Google Gemini. Flash models are free with a very large context window; expect slow first tokens on thinking models. (checked 2026-10-09)
  • Trying many models with one key → OpenRouter. One OpenAI-compatible key for every :free model; the free list changes often, so check the model table. (checked 2026-10-09)
  • Code completion and small multilingual models → Mistral. Codestral and the Ministral models answer on a free key; the small and medium models do not. (checked 2026-10-09)
  • Large open models (Nemotron, gpt-oss) for free → NVIDIA NIM. Hosts big models free for prototyping, but most of its listed models no longer answer. (checked 2026-10-11)
  • Chinese-language apps → Zhipu GLM. Free Flash models with strong Chinese; sign-up needs a phone number. (checked 2026-10-09)
  • DeepSeek V4 Flash without paying DeepSeek → Gonka Broker. Free monthly tokens on DeepSeek, GLM and MiniMax models, after a phone check. (checked 2026-10-09)
  • AI inside a Cloudflare Worker → Cloudflare Workers AI. Free daily Neurons on the edge; useful if your app already runs on Workers. (checked 2026-10-11)
  • Embeddings and reranking for RAG → Cohere. Trial key includes Embed and Rerank; not for production traffic. (checked 2026-10-09)

Free LLM APIs compared

"Free allowance" and "Rate limit" are the provider's own published figures; where a provider does not publish one, we say so rather than repeat a number from another list. "Models that answered" counts the chat models that returned a reply when we called them, not the length of the provider's model list. Use the buttons to narrow the table.

ProviderStatusFree allowanceRate limitCard?Phone check?Models that answeredVerified
Groq ✅ Free, works 1,000 requests/day and 200K tokens/day per model 30 requests/min, 8K tokens/min per model No Not stated 4 · fastest first token: qwen/qwen3.8-27b 0.88 s review due
Google Gemini ✅ Free, works Not published — shown only in AI Studio Not published — shown only in AI Studio No
Free tier needs no billing account
Not stated 10 · fastest first token: gemini-3.5-flash-lite 1.25 s review due
Mistral ✅ Free, works Not published — shown in your console Not published; small/medium/magistral models get 0 requests/min on free keys No Not stated in the docs 12 · fastest first token: ministral-8b-latest 0.69 s review due
OpenRouter ✅ Free, works 50 requests/day on :free models; 1,000/day after $10 of credits ever bought 20 requests/min on :free models No Not stated 8 · fastest first token: nvidia/nemotron-3-super-120b-a12b:free 1.22 s review due
NVIDIA NIM ✅ Free, works Free for Developer Program members, for prototyping; no number published Not published in the docs No Not stated 13 · fastest first token: nvidia/nemotron-3-super-120b-a12b 0.54 s review due
Zhipu GLM ✅ Free, phone check Free Flash models: GLM-4.7-Flash, GLM-4.5-Flash, GLM-4-Flash-250414 Concurrency limit per account, shown only in the console No Yes
Sign-up is by SMS code; overseas numbers accepted
3 · fastest first token: glm-4-flash-250414 0.65 s review due
Gonka Broker ✅ Free, phone check At least 1M tokens/month, renewed on the 1st 6 requests/min per account No
The free-tier page says no card; the homepage says 'add a card'
Yes 3 · fastest first token: deepseek-ai/DeepSeek-V4-Flash-0731 2 s review due
Cloudflare Workers AI ✅ Free, works 10,000 Neurons/day Per-model limits; not compared here Workers Free is the default plan; card rule not stated, and we did not sign up a fresh account to check Not stated 6 review due
Cohere ⏳ Trial only 1,000 API calls/month on a trial key 20 chat requests/min (trial key) Trial key on sign-up; card rule not stated Not stated We hold no key: not called by us review due
Cerebras 💳 Card required $5 trial credit, expires after 30 days; 1M tokens/day 5 requests/min (trial) Yes
API stays inactive until a payment method is added
Not stated We hold no key: not called by us. Trial tier lists gpt-oss-120b and qwen-3.8-27b review due
SambaNova Cloud 💳 Card required Docs list 20 requests/day per model with no payment method; our key got 402 PAYMENT_METHOD_REQUIRED Docs: 20 requests/min per model (free tier) Yes Not stated Our key now returns 401; not re-tested since 2026-08-31 review due
DeepSeek API ❌ Closed
since 2026-08-31
No free credit for new accounts on the pricing page — Yes
Prepaid balance required
Not stated Both models return 402 Insufficient Balance review due
Together AI ❌ Closed
since 2026-08-31
No free trial; $15 minimum first purchase, $5 minimum later — Yes Not stated Account read-only until you deposit
GitHub Models ❌ Closed
since 2026-07-30
Service retired — Not stated Not stated Retired: playground, catalog and inference API shut down review due

Model IDs that answered

A model appearing in a provider's /models list is not proof you can call it. On our last pass, NVIDIA listed dozens of models that returned 404 "Function not found", Gemini still listed 2.5-series models that answer "no longer available to new users", and Mistral lists models that free keys are allowed 0 requests per minute on. These are the IDs that actually replied. "First token" is the time until the first visible text of a one-line reply, measured once from our test machine in Asia, some providers through a proxy, so compare rows within a provider rather than across providers. Reasoning models spend most of that time thinking.

ProviderModel ID that answeredFirst tokenChecked
Groqqwen/qwen3.8-27b free tier also caps output at 1,000 tokens/min (429 OTPM, 2026-10-11)0.88 s2026-10-11
Groqopenai/gpt-oss-120b1.95 s2026-10-11
Groqallam-2-7b4.76 s2026-10-11
Groqopenai/gpt-oss-20b5.94 s2026-10-11
Google Geminigemini-3.5-flash-lite1.25 s2026-10-09
Google Geminigemini-3-flash-preview1.52 s2026-10-09
Google Geminigemini-3.6-flash2.15 s2026-10-09
Google Geminigemini-3.5-flash2.66 s2026-10-09
Google Geminigemini-3.1-flash-lite-preview2.73 s2026-10-09
Google Geminigemini-3.1-flash-lite2.91 s2026-10-09
Google Geminigemini-flash-lite-latest5.94 s2026-10-09
Google Geminigemini-flash-latest17.56 s2026-10-09
Google Geminigemini-3.7-flash36.58 s2026-10-09
Google Geminigemini-3.8-flash40.79 s2026-10-09
Mistralministral-8b-latest0.69 s2026-10-09
Mistralmistral-code-fim-latest0.73 s2026-10-09
Mistralmistral-code-latest0.95 s2026-10-09
Mistralvoxtral-small-latest0.96 s2026-10-09
Mistralcodestral-25080.97 s2026-10-09
Mistralvoxtral-small-25071.27 s2026-10-09
Mistralministral-8b-25121.28 s2026-10-09
Mistralministral-3b-25122.69 s2026-10-09
Mistralministral-3b-latest2.77 s2026-10-09
Mistralministral-14b-latest3.59 s2026-10-09
Mistralministral-14b-25124.08 s2026-10-09
Mistralcodestral-latest4.98 s2026-10-09
OpenRouternvidia/nemotron-3-super-120b-a12b:free1.22 s2026-10-09
OpenRouternvidia/nemotron-3-ultra-550b-a55b:free1.63 s2026-10-09
OpenRouterliquid/lfm-2.5-2.6b:free1.76 s2026-10-09
OpenRoutercohere/north-mini-code:free2.9 s2026-10-09
OpenRouterapodex/apodex-1.1-mini:free2.99 s2026-10-09
OpenRouternvidia/nemotron-3.5-lightning:free11.35 s2026-10-09
OpenRouterdots-studio/dots-3-note-preview:free11.47 s2026-10-09
OpenRouternvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free answered, but the timed streaming call returned no textnot timed2026-10-09
NVIDIA NIMnvidia/nemotron-3-super-120b-a12b0.54 s2026-10-11
NVIDIA NIMnvidia/nemotron-3.5-lightning-30b-a3b0.64 s2026-10-11
NVIDIA NIMz-ai/glm-5.3-flash0.68 s2026-10-11
NVIDIA NIMmeta/llama-3.2-11b-vision-instruct0.68 s2026-10-11
NVIDIA NIMnvidia/riva-translate-4b-instruct-v20.69 s2026-10-11
NVIDIA NIMopenai/gpt-oss-20b0.73 s2026-10-11
NVIDIA NIMnvidia/ising-calibration-1.5-31b0.76 s2026-10-11
NVIDIA NIMmeta/muse-glimmer-30b1.3 s2026-10-11
NVIDIA NIMnvidia/nemotron-3-ultra-550b-a55b1.31 s2026-10-11
NVIDIA NIMdeepseek-ai/deepseek-v4.1-flash1.38 s2026-10-11
NVIDIA NIMnvidia/nemotron-3-nano-omni-30b-a3b-reasoning1.45 s2026-10-11
NVIDIA NIMgoogle/diffusiongemma-26b-a4b-it8.41 s2026-10-11
NVIDIA NIMgoogle/gemma-4-31b-it answered on a retry; the timed streaming call was droppednot timed2026-10-11
Zhipu GLMglm-4-flash-2504140.65 s2026-10-09
Zhipu GLMglm-4.5-flash5.22 s2026-10-09
Zhipu GLMglm-4.7-flash answered once; the timed call got 429not timed2026-10-09
Gonka Brokerdeepseek-ai/DeepSeek-V4-Flash-07312 s2026-10-09
Gonka BrokerMiniMaxAI/MiniMax-M2.72.61 s2026-10-09
Gonka Brokerzai-org/GLM-5.3-Flash12.59 s2026-10-09
Cloudflare Workers AI@cf/meta/llama-3.1-8b-instruct answered; 579 tokens for 20.4 neurons (~490 such replies/day), 5.5 s non-streamingnot timed2026-10-11
Cloudflare Workers AI@cf/meta/llama-3.2-3b-instruct answered; 536 tokens for 16.6 neurons, 3.1 s non-streamingnot timed2026-10-11
Cloudflare Workers AI@cf/openai/gpt-oss-20b answered; 600 tokens for 17.9 neurons, 7.2 s non-streamingnot timed2026-10-11
Cloudflare Workers AI@cf/meta/llama-3.3-70b-instruct-fp8-fast answered on the free plan; 578 tokens for 119.7 neurons (~83/day)not timed2026-10-11
Cloudflare Workers AI@cf/google/gemma-4-26b-a4b-it answered; 600 tokens for 16.7 neuronsnot timed2026-10-11
Cloudflare Workers AI@cf/zai-org/glm-4.7-flash answered; 600 tokens for 22.0 neuronsnot timed2026-10-11

Speed: tokens per second, measured 2026-08-31

The table above answers "can I call it". This one answers "how fast is it once it starts". We sent the same ~250-word prompt to each free API with one streaming request (temperature 0.3, 500-token cap) from a US GitHub Actions runner, and computed generation speed from each API's own usage token count, excluding the time to first token. These numbers are from 2026-08-31 and have not been re-run since; the model IDs marked as changed no longer answer the same way today.

ProviderModel testedFirst tokenGeneration speedSince then
Groqopenai/gpt-oss-120b0.38 s~521–527 tok/sStill answers
Mistralmistral-small-latest0.43 s~161–179 tok/sFree keys now get 0 requests/min on this model
Google Geminigemini-3.6-flash17–34.5 s (thinking)141 tok/sSee the model table for what answers now
OpenRouternvidia/nemotron-3-super-120b-a12b:free2.6–2.7 s~38–77 tok/sStill answers
NVIDIA NIMnvidia/nemotron-3-super-120b-a12b3.5–7.6 s~26–100 tok/s, wildly inconsistent between runsStill answers
Zhipu GLMglm-4-flash2.6 s~20–23 tok/sStill answers, but is no longer in GLM's model list; the listed free ID is glm-4-flash-250414

Groq was not slightly faster; it was about 3× the next one. If generation speed matters at all, that settles it.

Re-tested 2026-10-11

We re-ran the two fastest free APIs and the Nemotron comparison on 11 October 2026, same prompt and method, but from a machine in Asia through a proxy rather than the US runner — so read the absolute numbers as rough and the direction as the finding.

Provider and modelRunsGeneration speedChange since 2026-08-31
Groq openai/gpt-oss-20b3813–885 tok/s (median 839)Still the fastest free model we have measured
Groq openai/gpt-oss-120b3261–454 tok/s (median 353)Slower than August's ~521–527 and less steady
Groq qwen/qwen3.8-27b3445–563 tok/s (median 544)New; free tier also caps output at 1,000 tokens/min
NVIDIA NIM nvidia/nemotron-3-super-120b-a12b2136.5 and 200.5 tok/sUp from ~26–100 tok/s
OpenRouter nvidia/nemotron-3-super-120b-a12b:free1 (2nd dropped by our proxy)38.2 tok/s, only ~36 visible tokensDown from 45.7 tok/s

Groq still leads, but the gap to NVIDIA's own endpoint has narrowed from 3× to roughly 2–3× on these runs.

In August, the same model was faster through OpenRouter than from NVIDIA itself — in October it was the reverse (200.5 vs 38.2 tok/s, table above). NVIDIA's nemotron-3-super-120b is served both by NVIDIA's own free API and by OpenRouter's free tier. Same model, same prompt, same runner on 2026-08-31:

Serving nemotron-3-super-120bTime to first tokenGeneration speed
OpenRouter (free)2.7 s45.7 tok/s
NVIDIA (own API)7.6 s36.7 tok/s

Free capacity is shared and unevenly provisioned, and it moves: neither the first-party endpoint nor a router is reliably the faster route to a model, so time both before you commit.

How we check

  • Can it be called: for every provider we hold a free key for, we fetch the /models list and call each chat model once with a one-line prompt. A row only counts as answered on an HTTP 200 with a reply. Connection drops on our side are retried and are never counted as a model failure.
  • Rate limits that look like errors: a Mistral 429 is checked against the x-ratelimit-limit-req-minute header. A limit of 0 means the free tier does not include that model, which is different from "try again later".
  • First token: one streaming request per model that answered, timing the first visible text.
  • Allowances, limits, card and phone rules: from each provider's own pricing and rate-limit pages, linked from the data file. Gemini and Mistral do not publish free-tier limits (they show them only inside your console), so we do not print one.
  • Providers we have no working key for (Cerebras, Cohere, Cloudflare Workers AI, and SambaNova since our old key started returning 401) are described from their official pages and our earlier tests only, and the table says so.
  • The benchmark harness is open source: free-ai-api-benchmark.

One code pattern for almost all of them

Groq, Gemini, Mistral, OpenRouter, NVIDIA NIM, GLM and Gonka Broker all accept the OpenAI chat format, so switching provider means changing the base URL, the key and the model ID. Take the model ID from the "Model IDs that answered" table above, not from an old tutorial.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_KEY",
    base_url="https://openrouter.ai/api/v1",   # swap per provider
)
response = client.chat.completions.create(
    model="nvidia/nemotron-3-super-120b-a12b:free",   # an ID from the table above
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)
print(response.choices[0].message.content)

Base URLs: Groq https://api.groq.com/openai/v1, Gemini https://generativelanguage.googleapis.com/v1beta/openai, Mistral https://api.mistral.ai/v1, NVIDIA https://integrate.api.nvidia.com/v1, GLM https://open.bigmodel.cn/api/paas/v4, Gonka Broker https://proxy.gonkabroker.com/v1. Cloudflare Workers AI runs inside a Worker via env.AI.run(...) or over its REST API.

Frequently asked questions

Can I use several free APIs in one app?

Yes, and with free tiers this unstable you should keep at least one fallback. Because the call shape is shared, a router such as LiteLLM can fail over from one provider to the next when a free quota runs out.

Why do some rows say "Not published"?

Because the provider does not publish that number. Google and Mistral show free-tier limits only inside your own console, and they change them without notice. Other lists quote a figure anyway; we would rather tell you where to look.

Is DeepSeek still free?

The DeepSeek models are, on other providers: check the model table for DeepSeek IDs on NVIDIA NIM and Gonka Broker. DeepSeek's own API is not: it returned 402 Insufficient Balance to a free account, see the table for the date.