onomeoonomeoBeta

Models

Use them in the browser, or call them through one OpenAI-compatible API key. No card needed.

Top up

Left right now

Site-wide calls

Free-model calls per 5 hours, shared by all accounts

About 70% left

Frees up as time passes

All models

Last 7 days

33 models, all reachable with one key. Free models are counted in calls; big models are charged by usage in US dollars, shown as 30-day averages.

How these figures are worked out

Updated Oct 17, 2026, 01:19 UTCAvailability is the share of all calls made through the site over the last 7 days, scheduled tests included, that got a reply. Response time averages the successful scheduled tests.Big models first, lowest price first; then the other models, by availability, then response time

#ModelAvailabilityResponseCost/replyLeft
1gpt-6-lunaOpenAI100%1.4savg.——Chat
2claude-haiku-5.5NewAnthropic100%2.7savg.——Chat
3mistral-large-4NewMistral AI100%1.3savg.——Chat
4glm-5.3Zhipu AI100%1.6savg.——Chat
5qwen3.8-maxNewQwen100%1.9savg.——Chat
6gemini-4-argonNewGoogle75%4.3savg.——Chat
7claude-sonnet-5.5NewAnthropic100%1.4savg.——Chat
8kimi-k3Moonshot AI100%1.9savg.——Chat
9gpt-6.1-solNewOpenAI66%2.3savg.——Chat
10grok-4.7xAI100%1.7savg.——Chat
11claude-opus-5.5Anthropic100%1.6savg.——Chat
12muse-wonder-1.0NewMeta100%2.0savg.——Chat
13gpt-6-astraOpenAI100%1.9savg.——Chat
14claude-fable-5.1NewAnthropic85%7.3savg.——Chat
15ministral-14b-latestMistral AI99%0.5savg.Free—Chat
16deepseek-flashDeepSeek99%0.9savg.——Chat
17gpt-oss-20bOpenAI99%1.2savg.Free—Chat
18codestral-latestMistral AI98%0.8savg.Free—Chat
19hy4-previewNewTencent98%3.0savg.FreeUsed upChat
20glm-5.2Zhipu AI97%2.3savg.Free—Chat
21glm-4.5-flashZhipu AI97%6.2savg.Free—Chat
22deepseek-v4-flashDeepSeek95%2.4savg.Free—Chat
23gemini-3.5-flash-liteGoogle94%1.5savg.Free—Chat
24muse-glimmer-30bMeta92%7.5savg.Free—Chat
25glyph-clusterNewStealth91%5.2savg.Free99% leftChat
26glm-5.3-flashZhipu AI91%11savg.FreeUsed upChat
27gemini-3.1-flash-liteGoogle87%3.8savg.Free—Chat
28gemini-3.6-flashGoogle55%1.5savg.Free95% leftChat
29gemini-3.5-flashGoogle52%1.3savg.Free90% leftChat
30gemini-3.7-flashGoogle43%5.9savg.Free100% leftChat
31gemini-3.8-flashGoogle42%8.6savg.Free90% leftChat
32glm-4.7-flashZhipu AI41%7.0savg.Free—Chat
33glm-4.6v-flashZhipu AI31%1.2savg.Free—Chat
—autoRecommended: picks for you——avg.Free—Chat

In dollars, counted from the visible text sent and received in each call.“One reply, about” is the average of recent calls, counting a call as at least 250 characters. Long conversations and coding tools send more text in each call and cost more. “Per million characters” is the price of returned text; sent text is charged at 20% of it, and the part the provider bills as cached at 10% of the sent price.

This week's model changes

This week's changes

Removed
deepseek-v4.1-flashgemini-3.1-pro-previewminimax-m2.7qwen3.5-397b-a17bqwen3.8-flash-next

No successful replies

Every model answered at least once this week.

Which one to pick

Start with a fast general model. Move to a larger reasoning or coding model when the first answer is not good enough.

Use the cheap one for

  • Classification, tagging, yes-or-no questions.
  • Rewriting, summarising, translating short text.
  • Anything you are going to run in a loop over many rows.
  • Prototyping, while you are still changing the prompt every two minutes.

Use the careful one for

  • Multi-step reasoning where a wrong middle step ruins the answer.
  • Code that has to run, not code that has to look right.
  • Long instructions with several constraints at once.
  • The final pass, after the cheap one got you most of the way.

A practical pattern: draft with a free model, and only send the cases it got wrong to Claude, GPT or another big model. Free models are not charged, so your balance goes only where a big model is needed.

Pricing

The basics are free. Big models, premium pictures and video are charged by usage.

Free

$0

  • Free models: 30 calls every 5 hours
  • 10 pictures a day on the basic drawing models, with a small onomeo mark in the bottom-right corner
  • OpenAI-compatible API: one key for Cline, OpenCode, SillyTavern and other tools
  • API answers end with the line "— via onomeo.com"
  • No credit card required

Free models from Google, Zhipu AI, Mistral AI, DeepSeek and more

Pay as you go

One payment. What you pay becomes your balance.

Amount
  • Big modelsUnlocks every big modelIncluding GPT-6.1 Sol, GPT-6 Astra, Gemini 4 Argon, Muse Wonder 1.0, Mistral Large 4 and more, charged to the balance by actual usage.In a coding tool, about1,000calls on the coding line, DeepSeek FlashThe coding line count is on the average of its recent calls. A big model in a coding tool is sent the whole conversation again with every call and usually costs far more than the coding line; before the first large call the site states the estimated cost in the tool and charges nothing.
  • Premium picturesAbout166pictures from GPT Image 2.5About 55 from Nano Banana Pro
  • VideoOpens with a single top-up of $10 or moreMade from text, with sound

Each line is an estimate for that use alone. They all draw on one balance, charged by actual usage. What a coding tool costs follows the length of the conversation.

  • The balance never expires
  • No automatic renewal
  • For 35 days after payment: 90 free-model calls every 5 hours
  • While the account has a balance: generated images carry no onomeo mark
  • While the account has a balance: API answers come without the "— via onomeo.com" line
  • The DeepSeek coding line

About how far $5 goes

Estimated from the average length of recent calls, counting a call as at least 250 characters.

  • Gemini 4 Argon1,000replies
  • GPT-6.1 Sol370replies
  • Claude Sonnet 5.5400replies
  • Claude Opus 5.5110replies
  • GPT-6 Luna290replies
  • Grok 4.7340replies
  • DeepSeek Flash1,000replies
  • GPT-6 Astra65replies
  • Claude Fable 5.192replies
  • GLM-5.3130replies
  • Kimi K3400replies

These counts assume short questions and answers. Long inputs and coding tools use more per request.

Billing rules

Free models count calls; big models are charged by usage

  • Claude, GPT and other big models are charged to your balance for the visible text you send and the text that comes back. Each model has its own price, listed on the Pricing page.
  • A model’s own thinking is not charged. A reply that comes back empty is neither counted as a call nor charged.
  • On big models an image is charged as 300 characters, once per conversation in the web chat.
  • On big models, the text read from a file you attach is charged like the rest of the message, each time it goes with a question.
  • Sign in with an email code, Google, GitHub or Discord. No password and no card needed.
  • Up to 12 requests a minute per key.
  • Free models: up to 30 calls in each 5-hour window per account, or 90 for 35 days after a payment. A long message counts as several calls: one for every 50,000 counted characters, and one more for any part left over. Characters are counted across the whole conversation sent, earlier messages included; each Chinese character counts as one, every 4 other characters as one.

Where the models come from The free-route models run on the free tier each provider offers; onomeo puts them behind one key and keeps checking that they answer. Big models such as Claude and GPT are paid for by onomeo, within a shared daily budget.Read the FAQ

Buying

Sign in, then select Top up. Waffo Pancake, our merchant of record, processes the payment, and the balance is added to the account you are signed in with. See the Terms of Use for details.

Frequently asked questions

What is the balance?

The amount you pay becomes your balance, shown in dollars. Claude, GPT and other big models and the DeepSeek coding line are charged to it by usage. Free models do not touch the balance; they are limited by calls. The balance never expires and nothing renews automatically; top up again whenever it runs out.

How much does one reply cost?

It is counted from the visible text sent and received in that call, and each model has its own price, listed above. The web chat shows about how much a message will cost before you send it.

What happened to credits?

The site no longer uses credits. Free models are limited by calls and the big models are charged in dollars; credits given out earlier are no longer in use.

onomeo is in public beta, and feedback is welcome. onomeo is an independent product and is not affiliated with any model provider.