aigratis
deepseek-v4-flashFree/1M×7
north-mini-codeFree/1M×6
laguna-xs-2-1Free/1M×6
nemotron-3-ultra-550b-a55bFree/1M×6
laguna-s-2-1Free/1M×6
dots-3-noteFree/1M×5
space-bunny-alphaFree/1M×5
nemotron-3-super-120b-a12bFree/1M×5
nemotron-3-nano-omni-30b-a3b-reasoningFree/1M×5
apodex-1-1-miniFree/1M×5
muse-spark-1-3-contributor-freeFree/1M×5
qwen3-8-27bFree/1M×5
agnes-2-5-flashFree/1M×5
space-bunny-freeFree/1M×5
ling-3-0-flash-santeFree/1M×5
laguna-s-2-1-freeFree/1M×5
nemotron-3-ultra-freeFree/1M×4
nemotron-3-5-lightning-freeFree/1M×4
mimo-v2-5-freeFree/1M×4
deepseek-v4-1-flashFree/1M×4
ling-3-0-flash-fin-freeFree/1M×4
nemotron-3-5-lightningFree/1M×4
lfm-2-5-2-6bFree/1M×4
deepseek-v4-flash-freeFree/1M×4
deepseek-v4-flashFree/1M×7
north-mini-codeFree/1M×6
laguna-xs-2-1Free/1M×6
nemotron-3-ultra-550b-a55bFree/1M×6
laguna-s-2-1Free/1M×6
dots-3-noteFree/1M×5
space-bunny-alphaFree/1M×5
nemotron-3-super-120b-a12bFree/1M×5
nemotron-3-nano-omni-30b-a3b-reasoningFree/1M×5
apodex-1-1-miniFree/1M×5
muse-spark-1-3-contributor-freeFree/1M×5
qwen3-8-27bFree/1M×5
agnes-2-5-flashFree/1M×5
space-bunny-freeFree/1M×5
ling-3-0-flash-santeFree/1M×5
laguna-s-2-1-freeFree/1M×5
nemotron-3-ultra-freeFree/1M×4
nemotron-3-5-lightning-freeFree/1M×4
mimo-v2-5-freeFree/1M×4
deepseek-v4-1-flashFree/1M×4
ling-3-0-flash-fin-freeFree/1M×4
nemotron-3-5-lightningFree/1M×4
lfm-2-5-2-6bFree/1M×4
deepseek-v4-flash-freeFree/1M×4
AI handouts · refreshed every 6 hours

Find the AI models you can use for free.

We collect the models AI gateways give away, along with where you can actually use them. Everything below costs nothing. Click any row to see which gateways serve it.

Need a paid model? Turn off the Free filter below, or open the full price board, which lines up every gateway in USD per 1 million tokens.

294
free models
3.2K
models total
81
gateways
ModelVendorContextCheapest / 1M input (USD)Gateway
DeepSeek V4 Flash Latest
~deepseek1.0M
FREE
cohere262K
FREE
poolside262K
FREE
NVIDIA: Nemotron 3 Ultra
nvidia1.0M
FREE
poolside1.0M
FREE
dots-studio512K
FREE
Space Bunny Alpha
stealth1M
FREE
NVIDIA: Nemotron 3 Super
nvidia262K
FREE
NVIDIA: Nemotron 3 Nano Omni (free)
nvidia262K
FREE
Apodex 1.1 Mini
Apodex262K
FREE
Muse Spark 1 3 Contributor Free
—1M
FREE
qwen262K
FREE
Agnes 2 5 Flash
—524K
FREE
Space Bunny Free
—1M
FREE
inclusionai262K
FREE
Laguna S 2 1 Free
—1.0M
FREE
Nemotron 3 Ultra Free
—1M
FREE
Nemotron 3 5 Lightning Free
—1.0M
FREE
Mimo V2 5 Free
—1M
FREE
Deepseek V4 1 Flash
deepseek1.0M
FREE
Ling 3 0 Flash Fin Free
—262K
FREE
NVIDIA: Nemotron 3.5 Lightning
nvidia1M
FREE
liquid128K
FREE
Deepseek V4 Flash Free
deepseek—
FREE
Hy3 Free
—256K
FREE

1–25 of 294 models

Most generous gateways

Ranked by how many models each gateway gives away — computed from price data, not from likes or any deal. The same model listed twice on one gateway counts once.

  1. 1
    105 free models
    of 257 models
  2. 2
    55 free models
    of 129 models
  3. 3
    54 free models
    of 866 models
  4. 4
    22 free models
    of 466 models
  5. 5
    17 free models
    of 466 models
Visitors' picks

Ranked by the like button visitors press on this site — not by price, and not by any deal with a gateway.

Gateways we track

Every gateway's prices are pulled automatically from its official API, never retyped by hand.

Detail per gateway
See 69 more gateways

Prices here are re-pulled every 6 hours and can change at any time without notice. Before you pay, check the gateway's own pricing page directly.

How are these prices collected?

Every 6 hours we call each gateway's model-list endpoint with our own API key.

Not every gateway includes prices in its API response — the model list endpoint sometimes returns model names with no numbers. For those, prices are filled in by hand: their official pricing page is read by an AI, and the result is checked before it is saved. We re-check them periodically, but numbers from that route are the most likely to be off or out of date, because they only change when their page is read again.

The units differ — some quote per token, some per thousand, some per million, in USD or in Rupiah. Everything is converted to USD per 1 million tokens so it is comparable. Rupiah figures use the daily market rate, not the rate a gateway uses when it bills you.

Model names are normalised too: anthropic/claude-opus-5 and claude-opus-5 are the same model, so they share one row.

More in the Terms of Service, under Price accuracy.