x402factory.ai

Create a Solana associated token account (ATA) for a given wallet and SPL mint so it can hold that token. Typical use: prepare a wallet to receive USDC or other SPL tokens before sending funds. Cost: $0.30 USDC. Without payment: checks via RPC whether the ATA already exists; if it does, returns 400 and no payment is needed. For paid calls, if the ATA cannot be created or is found to already exist at execution time, the server attempts to refund the full payment.

Solana music generation endpoint paid via x402. Generates a song from a prompt and returns a hosted mp3 URL (ImageKit). Pricing: 0.02 USDC per second. Allowed duration: 10–500 seconds. This is a fixed-duration tier: '/solana/music/90' charges exactly 1.800000 USDC.

Solana text-to-speech API paid via x402. Converts text input into a hosted audio URL. Dynamic pricing for TTS: the prepaid price is computed per request based on the input and charged upfront via x402. Estimated characters for this request: 11. Prepaid price for this request: 0.006600 USDC.

Solana speech-to-text endpoint using x402 payments. Provide either a YouTube URL/ID or a direct audio file URL; the server downloads the audio, runs speech-to-text, and returns the transcript text. Pricing: 0.01 USDC per started minute of audio, computed from the estimated duration and charged upfront via x402. Default discovery price without a specific URL is 0.60 USDC as an upper-bound quote. For this video the estimated duration is 23 minute(s); prepaid price for this call is 0.230000 USDC.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent NZGVSXRC6HMKB8FWDA on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "Give me the 5 raw output from the most important new topics in this output :". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017011 USDC. Estimated input tokens for pricing: 5026.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent M4BAZ396XPH8QAHE3X on Solana. Model gpt-5-mini, max_input_tokens=1000, max_output_tokens=1000. Preprompt preview (first 150 chars): "You are given a URL that points to an X (Twitter) profile image (PFP). Your task: - Convert the image URL to a 400x400 version. - Do this by replacin". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.003478 USDC. Estimated input tokens for pricing: 1195.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent AW5793DBAYAHSEHJTU on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5300. Preprompt preview (first 150 chars): "Here is a prompt i received from a client, we going to forward it to next step but you need to add the info "create a rap" in before of the prompt, yo". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017932 USDC. Estimated input tokens for pricing: 5079.

Solana coin price mini-endpoint for major tokens only. Returns spot prices and 24h stats for well-known tickers like btc, solana, eth, xmr, ltc and other large-cap coins, never microcaps. Pass an optional ticker to get a single-coin 24h snapshot with price, symbol, changeRate, changePrice, high and low, or omit ticker to receive a compact basket of top tokens in a fixed order. Cost: 0.001 USDC per request.

Create a Solana associated token account (ATA) for a given wallet and SPL mint so it can hold that token. Typical use: prepare a wallet to receive USDC or other SPL tokens before sending funds. Cost: 0.4 USDC per call. The endpoint checks via RPC whether the ATA already exists; if it does, discovery returns an error and no payment is needed. For paid calls, if the ATA cannot be created or is found to already exist at execution time, the server attempts to refund the 0.4 USDC payment.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent 6JAF5PYRGEC8X9XYFC on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "Reply to me with the image url of the most important topic, make sure it's a image url, if most important topic haven't image url use a url from the n". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017028 USDC. Estimated input tokens for pricing: 5069.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent KCBWQQHUC8D4GQB5DT on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "Read the response carefully. If the response already contains an image-generation prompt, reply with ONLY that prompt verbatim. If no prompt is pres". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017118 USDC. Estimated input tokens for pricing: 5295.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent KR92MHBFNW9Z7MST4E on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "You writing a prompt for a image generator to create a thumbnail of a audio news flash that is based on the topics i send you, please always just answ". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017028 USDC. Estimated input tokens for pricing: 5068.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent 6BNTBUF2DASXXWCAD2 on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "You writing a voice over script for a audio newsflash, can you read these topics and create a script for a tts agent, make sure it sounds natural and ". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017048 USDC. Estimated input tokens for pricing: 5119.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent 32X5W88Z9PATZH85T5 on Solana. Model gpt-5-mini, max_input_tokens=1000, max_output_tokens=2000. Preprompt preview (first 150 chars): ".". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.006401 USDC. Estimated input tokens for pricing: 1001.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent 4TC64D7MFFRX5DNRZ9 on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "Give me the 5 raw output from the most important new topics in this output also add the image link to every post :". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017016 USDC. Estimated input tokens for pricing: 5038.

Base X profile mini-endpoint. Fetches a full X profile and the 10 most recent tweets for a given handle, returning the raw profile data plus a trimmed tweet list with key engagement metrics and media. Cost: 0.001 USDC per request.

Paid x402 endpoint for creating social engagement jobs on a specific post.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent J38T6ZGANCNB8SLZJZ on Solana. Model gpt-5-mini, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "can yes extract the atrifact url from this output, only reply with the image url nothing else". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.017013 USDC. Estimated input tokens for pricing: 5031.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent H32KZAUGYY5MPHEX62 on Solana. Model gpt-5.1, max_input_tokens=5000, max_output_tokens=5000. Preprompt preview (first 150 chars): "You are a professional voice-over scriptwriter for short audio newsflashes. Task: Read the provided list of crypto-related topics and generate a conc". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.085632 USDC. Estimated input tokens for pricing: 5316.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent T6G59ANZRFBKRHXTHG on Solana. Model gpt-5-mini, max_input_tokens=12500, max_output_tokens=7500. Preprompt preview (first 150 chars): "Give me the 5 raw output from the most important new topics in this output also add the image link to every post :". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.027516 USDC. Estimated input tokens for pricing: 12538.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent YXPJPFB26CSY6VTN3N on Solana. Model gpt-5.1, max_input_tokens=1000, max_output_tokens=2000. Preprompt preview (first 150 chars): "You are a professional voice-over scriptwriter for short audio newsflashes. Task: Read the provided list of crypto-related topics and generate a conc". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.032632 USDC. Estimated input tokens for pricing: 1316.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. This specific request uses model gpt-5-mini with max_output_tokens=700. Pricing mode: per-token. Prepaid price (x402) for this request: 0.002261 USDC. Estimated input tokens for pricing: 401.

Solana → Base USDC microbridge. This request will accept a payment of 12.350000 USDC on Solana to the bridge wallet and, after a 2.5% commission of approximately 0.308750 USDC, will attempt to deliver around 12.041250 USDC on Base to the specified receiver. If the Base transfer cannot be completed after 2 attempts, the bridge refunds the full original amount on Solana; if the refund also fails after 3 attempts, the bridge is marked as failed and manual support is required.

Solana GPT wrapper API using x402 payments. Default direct call: model gpt-5-mini, max_output_tokens=2000, fixed price 0.01 USDC for up to 1000 input tokens. For all other settings the price is computed per model as (input_tokens * input_price_per_million + max_output_tokens * output_price_per_million) / 1,000,000, with a minimum of 0.001 USDC and always rounded up to 6 decimals. Optional max_input_tokens lets you cap the input tokens used for pricing; if the message is longer than this cap the server returns an error instead of under-pricing. Optional action=message (or omitting action) performs a direct GPT call with the given message. Optional action=create creates a custom agent with the given message as preprompt for 0.001 USDC (no OpenAI call), stores a base_price_usdc using (max_input_tokens_for_agent or 1000) + preprompt + max_output_tokens, and returns a custom_id. Optional action=list lists up to 100 recent custom agents for the paying wallet for 0.001 USDC without calling OpenAI. Custom agents can be called via POST /solana/llm/gpt with custom_id, or POST /solana/llm/gpt/{custom_id}. Each custom agent has a fixed price per call based on its stored preprompt, model, max_output_tokens and max_input_tokens; if the runtime message is longer than max_input_tokens the server returns an error. Custom LLM agent HFNPTD5QQQAMHB6NCF on Solana. Model gpt-5.1, max_input_tokens=27000, max_output_tokens=12000. Preprompt preview (first 150 chars): "You are a professional content summarization agent. Your task is to produce a true summary of a spoken-content transcription (such as a podcast, vide". Pricing mode: agent-per-token. Prepaid price (x402) for this request: 0.235294 USDC. Estimated input tokens for pricing: 27647.