Models
Use them in the browser, or call them through one OpenAI-compatible API key. Check current availability, access requirements and prices before sending.
How these figures are worked out
| # | Model | Availability | Response | Reference price per million output tokens | Left | ||
|---|---|---|---|---|---|---|---|
| 1 | claude-haiku-5.5Anthropic | 100% | —avg. | $0.75Reference price per million output tokensInput $0.15 Cache read $0.015 At 100,001 input tokens or more: Input $0.75 · Output $3.75 · Cache read $0.075 | — | Chat | |
| 2 | gemini-4-argonGoogle | 100% | —avg. | $15.00Reference price per million output tokensInput $3.00 Cache read $0.15 | — | Chat | |
| 3 | gpt-6.1-terraNewOpenAI | 100% | —avg. | $7.50Reference price per million output tokensInput $1.50 Cache read $0.075 At 272,000 input tokens or more: Input $3.00 · Output $11.25 · Cache read $0.15 | — | Chat | |
| 4 | claude-sonnet-5.5Anthropic | 100% | —avg. | $15.00Reference price per million output tokensInput $3.00 Cache read $0.15 | — | Chat | |
| 5 | grok-4.7xAI | 100% | —avg. | $9.00Reference price per million output tokensInput $3.00 Cache read $0.75 | — | Chat | |
| 6 | claude-opus-5.5Anthropic | 100% | —avg. | $30.00Reference price per million output tokensInput $6.00 Cache read $0.30 | — | Chat | |
| — | kimi-k3.1-proNewMoonshot AI | Awaiting first test | —avg. | $15.00Reference price per million output tokensInput $3.00 Cache read $0.30 | — | Chat | |
| — | gpt-6-astraOpenAI | Awaiting first test | —avg. | $75.00Reference price per million output tokensInput $15.00 Cache read $1.50 At 272,001 input tokens or more: Input $30.00 · Output $112.50 · Cache read $3.00 | — | Chat | |
| — | kimi-k3Moonshot AI | Awaiting first test | —avg. | $22.50Reference price per million output tokensInput $4.50 Cache read $0.35 | — | Chat | |
| — | glm-5.3Zhipu AI | Awaiting first test | —avg. | $8.25Reference price per million output tokensInput $2.63 Cache read $0.49 | — | Chat | |
| — | gpt-6-lunaOpenAI | Awaiting first test | —avg. | $0.75Reference price per million output tokensInput $0.15 Cache read $0.015 At 272,001 input tokens or more: Input $0.30 · Output $1.13 · Cache read $0.03 | — | Chat | |
| — | gpt-6.1-solOpenAI | Awaiting first test | —avg. | $15.00Reference price per million output tokensInput $3.00 Cache read $0.15 | — | Chat | |
| — | claude-fable-5.1Anthropic | Awaiting first test | —avg. | $75.00Reference price per million output tokensInput $15.00 Cache read $0.38 | — | Chat | |
| — | mistral-large-4Mistral AI | Awaiting first test | —avg. | $3.13Reference price per million output tokensInput $1.02 Cache read $0.11 | — | Chat | |
| — | qwen3.8-maxQwen | Awaiting first test | —avg. | $9.00Reference price per million output tokensInput $3.00 Cache read $0.38 | — | Chat | |
| — | muse-wonder-1.0Meta | Awaiting first test | —avg. | $30.00Reference price per million output tokensInput $6.00 Cache read $0.30 | — | Chat | |
| 7 | deepseek-flashDeepSeek | 92% | —avg. | $1.76Reference price per million output tokensInput $0.44 Cache read $0.0088 | — | Chat |
These are reference unit prices. Paid text models settle on confirmed billing and actual usage, including input, output and reasoning. Cache reads use the cache rate; supported cache writes have separate prices. The final charge never exceeds this request’s reservation ceiling.
This week's model changes
This week's changes
- New
- None this week
- Removed
- None this week
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.
Pricing
Chat and video are charged by usage; images are charged per picture.
Loading service announcement…
Pay as you go
One payment. What you pay becomes your balance.
- Big modelsUnlocks every modelIncluding GPT-6.1 Terra, Kimi K3.1 Pro, Gemini 4 Argon, Muse Wonder 1.0 and more, charged to the balance by actual usage.A big model in a coding tool is sent the whole conversation again with every call and costs far more than a short reply; before the first large call the site states the estimated cost in the tool and charges nothing.
- Premium picturesAbout333pictures from GPT Image 2.5About 111 from Nano Banana Pro
- VideoAbout405-second clips from MiniMax H3Made 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
- 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
You can also pay with PayPal (through Ko-fi; use the email you sign in with here)
Payments are not refunded. See the Terms of Use.
Billing rules
Paid models are charged by usage; rewards apply to eligible web answers
- These are reference unit prices. Paid text models settle on confirmed billing and actual usage, including input, output and reasoning. Cache reads use the cache rate; supported cache writes have separate prices. The final charge never exceeds this request’s reservation ceiling.
- Output usage includes model reasoning. Requests with no usable delivered content are not charged.
- Images read by text models are included in input tokens, with no additional per-image fee.
- 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.
- Claude, GPT and other big models use your top-up balance; earned rewards can cover selected models in web chat.
- Top up from $5. Your balance never expires, and nothing renews on its own.
- Up to 12 requests a minute per key.
Where the models come from The current catalogue shows available models and prices. Paid calls use your balance, while earned rewards can cover eligible answers in browser chat. Account, rate and shared budget limits still apply.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?
Payments become your balance in dollars. Paid model calls are charged by usage. Earned answers can cover selected models in browser chat; the model picker shows whether a reward applies. Your balance never expires and does not renew automatically.
How much does one reply cost?
These are reference unit prices. Paid text models settle on confirmed billing and actual usage, including input, output and reasoning. Cache reads use the cache rate; supported cache writes have separate prices. The final charge never exceeds this request’s reservation ceiling. The reservation ceiling is checked on send. Actual usage is settled when the request ends; unused reservations are released.
What happened to credits?
Paid usage is billed in dollars. Earned free answers are recorded separately from your balance and can be used on the models marked as eligible in browser chat.
onomeo is in public beta, and feedback is welcome. onomeo is an independent product and is not affiliated with any model provider.