Pay per use
Every request is priced separately and deducted from your wallet, with no mandatory monthly subscription.
See live prices for the GPT (ChatGPT) API and other models: the cost of every million input and output tokens, context length and features of each model. No monthly subscription is needed to use the API; you only pay for what you use from your wallet.
Each request is priced by the number of input tokens (your prompt) and output tokens (the model's answer). Every number on this page is read from the site's active catalog and updates when prices change.
Every request is priced separately and deducted from your wallet, with no mandatory monthly subscription.
The cost of every model is deducted from one wallet, so you do not need a separate account and invoice for each provider.
Tokens, cost, latency and status are recorded for every request. Before sending, you can also check the maximum cost with the cost-estimate endpoint.
The price range of each model family in the active catalog. Open the table below or the model's own page for the exact price of any model.
Prices per million tokens. Select a model name to see its specs, 24-hour performance and a code sample.
openai/gpt-5.6-terra-pro
openai/gpt-5.6-terra
openai/gpt-5.6-sol-pro
openai/gpt-5.6-sol
openai/gpt-5.6-luna-pro
openai/gpt-5.6-luna
openai/gpt-5.5-pro
openai/gpt-5.5
openai/gpt-5.4-pro
openai/gpt-5.4
openai/gpt-5.2-pro
openai/gpt-5.2
openai/gpt-5.1
openai/gpt-5-pro
openai/gpt-5
anthropic/claude-sonnet-5.5
anthropic/claude-opus-5.5
anthropic/claude-sonnet-5
anthropic/claude-opus-5
anthropic/claude-opus-4.8
anthropic/claude-opus-4.7
anthropic/claude-sonnet-4.6
anthropic/claude-opus-4.6
openai/gpt-5.4-mini
anthropic/claude-sonnet-4.5
anthropic/claude-opus-4.5
openai/gpt-5-mini
anthropic/claude-opus-4.1
openai/gpt-5.4-nano
openai/gpt-5-nano
openai/gpt-4o
openai/gpt-4.1
openai/gpt-4.1-mini
~anthropic/claude-sonnet-latest
~anthropic/claude-opus-latest
openai/gpt-4.1-nano
google/gemini-2.5-pro
anthropic/claude-haiku-5.5
openai/o3-pro
openai/o3
google/gemini-3.8-flash
google/gemini-3.7-flash
anthropic/claude-fable-5.2
google/gemini-3.6-flash
google/gemini-3.5-flash
anthropic/claude-haiku-4.5
anthropic/claude-fable-5.1
anthropic/claude-fable-5
openai/gpt-4o-2024-11-20
openai/gpt-4o-2024-08-06
openai/gpt-4o-2024-05-13
~google/gemini-pro-latest
google/gemini-2.5-flash
openai/gpt-4
deepseek/deepseek-v3.2
deepseek/deepseek-v3.1-terminus
deepseek/deepseek-chat-v3.1
x-ai/grok-4.7
x-ai/grok-4.6
x-ai/grok-4.5
openai/gpt-4o-mini-2024-07-18
x-ai/grok-4.3
x-ai/grok-4.20-multi-agent
x-ai/grok-4.20
google/gemini-3.5-flash-lite
~google/gemini-flash-latest
google/gemini-3.1-flash-lite
~anthropic/claude-haiku-latest
deepseek/deepseek-chat
google/gemini-4-neon
google/gemini-4-argon
~anthropic/claude-fable-latest
openai/gpt-6.1-terra-pro
openai/gpt-6.1-terra
openai/gpt-6.1-sol-pro
openai/gpt-6.1-sol
openai/gpt-6-sol-pro
openai/gpt-6-sol
openai/gpt-6-luna-pro
openai/gpt-6-luna
openai/gpt-6-astra-pro
openai/gpt-6-astra
deepseek/deepseek-v4.1-flash
~deepseek/deepseek-v4-flash-latest
openai/gpt-5.3-codex
openai/gpt-5.2-codex
deepseek/deepseek-v4-pro
x-ai/grok-build-0.1
openai/gpt-5.1-codex-max
openai/gpt-5.1-codex
qwen/qwen3.8-flash
qwen/qwen3.8-max-prime
~x-ai/grok-latest
qwen/qwen3.8-omni-flash
qwen/qwen3.8-27b
qwen/qwen3.8-2.4t-a95b
qwen/qwen3.7-plus
qwen/qwen3.7-max
qwen/qwen3.6-plus
qwen/qwen3.6-flash
qwen/qwen3.6-35b-a3b
qwen/qwen3.6-27b
qwen/qwen3.5-plus-02-15
qwen/qwen3.5-flash-02-23
qwen/qwen3.5-9b
qwen/qwen3.5-397b-a17b
qwen/qwen3.5-35b-a3b
qwen/qwen3.5-27b
qwen/qwen3.5-122b-a10b
google/gemini-3.1-pro-preview-customtools
google/gemini-3.1-pro-preview
qwen/qwen3-vl-8b-instruct
qwen/qwen3-vl-30b-a3b-thinking
qwen/qwen3-vl-30b-a3b-instruct
qwen/qwen3-vl-235b-a22b-instruct
qwen/qwen3-next-80b-a3b-instruct
qwen/qwen3-coder-next
qwen/qwen3-coder-flash
qwen/qwen3-coder-30b-a3b-instruct
qwen/qwen3-coder
qwen/qwen3-32b
qwen/qwen3-30b-a3b
qwen/qwen3-14b
deepseek/deepseek-chat-v3-0324
google/gemini-2.5-pro-preview
meta-llama/llama-guard-4-12b
meta-llama/llama-4-scout
meta-llama/llama-4-maverick
qwen/qwen2.5-vl-72b-instruct
moonshotai/kimi-k3.1-pro
qwen/qwen-2.5-coder-32b-instruct
qwen/qwen-2.5-7b-instruct
qwen/qwen-2.5-72b-instruct
openai/gpt-oss-safeguard-20b
openai/gpt-oss-20b
openai/gpt-5.1-codex-mini
moonshotai/kimi-k3
moonshotai/kimi-k2.7-code
moonshotai/kimi-k2.6
meta-llama/llama-3.3-70b-instruct
meta-llama/llama-3.2-3b-instruct
meta-llama/llama-3.2-1b-instruct
moonshotai/kimi-k2.5
meta-llama/llama-3.1-8b-instruct
meta-llama/llama-3.1-70b-instruct
aion-labs/aion-rp-llama-3.1-8b
nousresearch/hermes-3-llama-3.1-70b
nousresearch/hermes-3-llama-3.1-405b
z-ai/glm-5.3-prime
mistralai/mistral-large-4-0
z-ai/glm-5.3-flashx
z-ai/glm-5.3-flash
z-ai/glm-5.3
z-ai/glm-5.2
z-ai/glm-5.1
moonshotai/kimi-k2-thinking
moonshotai/kimi-k2
z-ai/glm-5v-turbo
z-ai/glm-5-turbo
z-ai/glm-5
z-ai/glm-4.7-flash
z-ai/glm-4.7
mistralai/mistral-medium-3-5
deepseek/deepseek-r1-0528
z-ai/glm-4.6v
z-ai/glm-4.6
google/gemini-3-flash-preview
z-ai/glm-4.5v
z-ai/glm-4.5
mistralai/mistral-medium-3.1
mistralai/mistral-medium-3
deepseek/deepseek-v3.2-exp
~deepseek/deepseek-pro-latest
~deepseek/deepseek-flash-latest
qwen/qwen-plus
mistralai/mixtral-8x22b-instruct
~moonshotai/kimi-latest
~openai/gpt-terra-latest
~openai/gpt-sol-latest
~openai/gpt-luna-latest
~openai/gpt-astra-latest
openai/gpt-chat-latest
deepseek/deepseek-v4.1-flash-1017
deepseek/deepseek-v4-pro-0813
deepseek/deepseek-v4-flash-0731
qwen/qwen3.8-max-0902
qwen/qwen3.5-plus-20260420
google/gemini-3.1-flash-lite-preview
mistralai/mistral-large
qwen/qwen3-30b-a3b-instruct-2507
qwen/qwen3-235b-a22b-thinking-2507
qwen/qwen3-235b-a22b-2507
~openai/gpt-mini-latest
mistralai/mistral-small-3.2-24b-instruct
mistralai/mistral-small-3.1-24b-instruct
No models match your search.
Prices are indicative; real billing uses the exact usage of each request.
Enter your monthly usage to see the approximate cost of any model.
This is an estimate; real billing uses the exact usage of each request.
A token is a unit of text processing; a word is usually one or several tokens. Input is the prompt and text you send, output is the model's answer. Generating an answer usually costs more than reading the input, which is why the two are priced separately.
The Persian version shows prices in Toman, while the English and Russian versions show US dollars. Conversion uses the exchange rate set on the site, so the numbers here follow any change of rate or price.
No. The cost of each request is deducted from your wallet balance based on usage.
Yes. Free models are marked "Free" in the table above and can be used after you sign up. Your free usage limit is shown in your panel.
The POST /cost/estimate endpoint takes the same body as your request and returns the most it could cost, without sending anything to the model and without charging your wallet. Details are in the documentation.
Your panel records the model, tokens, cost, duration and status of every request, with charts and filters for reports.
Create an account, top up your wallet and use the models through the API and live chat right away.