AI & Social

Social intelligence and agentic services, including X persona, news, chat agents, and trend analysis.

Social intelligence and agentic services, including X persona, news, chat agents, and trend analysis. 16 endpoints, each gated by the x402 payment protocol and settled in USDC. Connect the same endpoints over the MCP server for agent-to-agent use.

Claude Fable 5

Claude Fable 5 text generation (Anthropic). Dynamic pricing: estimated input tokens at $0.01/1K + output tier ceiling at $0.05/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports system prompt and image input.

POST /llm/claude-fable-5

Price

$0.05–$0.41 by tier + input

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt for Claude (counts toward input cost at $0.01/1K tokens)
`system_prompt`	`textarea`	No	Optional system prompt (counts toward input cost)
`tier`	`select`	No	Output size tier: small (1024 tokens, ~$0.05), medium (4096, ~$0.20), large (8192, ~$0.41) One of: `small`, `medium`, `large`.
`image`	`string`	No	Optional image URL for vision input (adds a flat 1600-token input charge, ~$0.016)

Response

Returns text (the generated response), model, tier, usage (input/output token counts), and metadata

Example

curl -X POST "https://api.xona-agent.com/llm/claude-fable-5" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "tier": "small",
  "image": "https://example.com/image.jpg"
}'

Claude Opus 4.6

Claude Opus 4.6 text generation (Anthropic). Dynamic pricing: estimated input tokens at $0.005/1K + output tier ceiling at $0.025/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports system prompt and image input.

POST /llm/claude-opus-4-6

Price

$0.03–$0.20 by tier + input

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt for Claude (counts toward input cost at $0.005/1K tokens)
`system_prompt`	`textarea`	No	Optional system prompt (counts toward input cost)
`tier`	`select`	No	Output size tier: small (1024 tokens, ~$0.03), medium (4096, ~$0.10), large (8192, ~$0.20) One of: `small`, `medium`, `large`.
`image`	`string`	No	Optional image URL for vision input (adds a flat 1600-token input charge, ~$0.008)

Response

Returns text (the generated response), model, tier, usage (input/output token counts), and metadata

Example

curl -X POST "https://api.xona-agent.com/llm/claude-opus-4-6" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "tier": "small",
  "image": "https://example.com/image.jpg"
}'

Claude Opus 5

Claude Opus 5 text generation (Anthropic) via OpenRouter. OpenAI-compatible chat completions with a 1M-token context window. Usage-based pricing: input + output tokens at provider cost + 10% (~$5.50 in / $27.50 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, so set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

POST /llm/claude-opus-5

Price

~$5.50 in / $27.50 out per M

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens, lowers the up-front per-call charge
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/claude-opus-5" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

Creative Director

AI-powered creative research and prompt refinement using X and Google. Analyzes trends, and transforms your idea into an optimized generation plan.

POST /image/creative-director

Price

$0.03

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`idea`	`textarea`	Yes	Your creative idea or concept to research and refine
`reference_images`	`string[]`	No	URLs of reference images (optional)

Response

Returns intent analysis, research results from X/Google, and a generation direction plan

Example

curl -X POST "https://api.xona-agent.com/image/creative-director" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "idea": "e.g., A futuristic Solana-themed artwork with neon colors and blockchain elements",
  "reference_images": "https://example.com/image.jpg"
}'

Designer

AI image generation with intelligent style blending. Takes your prompt and style keywords, refines them together, and generates a high-quality image.

POST /image/designer

Price

$0.06

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	Detailed prompt description for the image
`style`	`string[]`	No	Style keywords to blend into the prompt
`aspect_ratio`	`string`	No	Image aspect ratio
`referenceImage`	`string[]`	No	URLs of reference images for style/composition guidance

Response

Returns generated image URL, refined prompt, and generation metadata

Example

curl -X POST "https://api.xona-agent.com/image/designer" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "A vibrant digital illustration depicting futuristic Solana tokens with neon colors...",
  "style": "digital art, futuristic, neon",
  "aspect_ratio": "1:1",
  "referenceImage": "https://example.com/reference.jpg"
}'

Gemini 3.5 Flash

Gemini 3.5 Flash text generation (Google). Dynamic pricing: estimated input tokens at $0.0015/1K + output tier ceiling at $0.009/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports system prompt.

POST /llm/gemini-3.5-flash

Price

$0.01–$0.07 by tier + input

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt for Gemini (counts toward input cost at $0.0015/1K tokens)
`system_prompt`	`textarea`	No	Optional system prompt (counts toward input cost)
`tier`	`select`	No	Output size tier: small (1024 tokens, ~$0.01), medium (4096, ~$0.04), large (8192, ~$0.07) One of: `small`, `medium`, `large`.

Response

Returns text (the generated response), model, tier, usage (input/output token counts), and metadata

Example

curl -X POST "https://api.xona-agent.com/llm/gemini-3.5-flash" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Write assembly to move a file between folders",
  "system_prompt": "You are a helpful assistant.",
  "tier": "small"
}'

GPT-5.2

GPT-5.2 text generation (OpenAI). Dynamic pricing: estimated input tokens at $0.00175/1K + output tier ceiling at $0.014/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports image input and reasoning effort control.

POST /llm/gpt-5.2

Price

$0.01–$0.11 by tier + input

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt for GPT-5.2 (counts toward input cost at $0.00175/1K tokens)
`tier`	`select`	No	Output size tier: small (1024 tokens, ~$0.01), medium (4096, ~$0.06), large (8192, ~$0.11). Reasoning tokens count toward this ceiling. One of: `small`, `medium`, `large`.
`reasoning_effort`	`select`	No	Reasoning depth. Higher effort uses more output tokens (counted in the tier ceiling). One of: `low`, `medium`, `high`.
`image`	`string`	No	Optional image URL for vision input (adds a flat 1600-token input charge, ~$0.003)

Response

Returns text (the generated response), model, tier, usage (input/output token counts), and metadata

Example

curl -X POST "https://api.xona-agent.com/llm/gpt-5.2" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain this paradox through a mathematical proof",
  "tier": "small",
  "reasoning_effort": "medium",
  "image": "https://example.com/image.jpg"
}'

GPT-5.6 Luna

GPT-5.6 Luna text generation (OpenAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$1.10 in / $6.60 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

POST /llm/gpt-5.6-luna

Price

~$1.10 in / $6.60 out per M

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens, lowers the up-front per-call charge
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/gpt-5.6-luna" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

GPT-5.6 Sol

GPT-5.6 Sol text generation (OpenAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$5.50 in / $33 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

POST /llm/gpt-5.6-sol

Price

~$5.50 in / $33 out per M

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens, lowers the up-front per-call charge
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/gpt-5.6-sol" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

GPT-5.6 Terra

GPT-5.6 Terra text generation (OpenAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$2.75 in / $16.50 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

POST /llm/gpt-5.6-terra

Price

~$2.75 in / $16.50 out per M

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens, lowers the up-front per-call charge
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/gpt-5.6-terra" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

Grok 4.5

Grok 4.5 text generation (xAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$2.20 in / $6.60 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

POST /llm/grok-4.5

Price

~$2.20 in / $6.60 out per M

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens, lowers the up-front per-call charge
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/grok-4.5" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

Kimi K3

Kimi K3 text generation (Moonshot) via OpenRouter. OpenAI-compatible chat completions with a 1M-token context window. Usage-based pricing: input + output tokens at provider cost + 10% (~$3.30 in / $16.50 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

POST /llm/kimi-k3

Price

~$3.30 in / $16.50 out per M

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens, lowers the up-front per-call charge
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/kimi-k3" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

NVIDIA NIM

OpenAI-compatible chat completions on frontier models (Claude Fable 5, Gemini 3.5 Flash, GPT-5.2 via Replicate; Nemotron 3 Ultra, Kimi K2.6, DeepSeek V4 Pro, GLM-5.1 via NVIDIA NIM with OpenRouter fallback). Pricing is usage-based: input + output tokens at the provider rate + 10%. On the x402 door the per-call charge is quoted up front as an upper bound (set max_tokens to lower it). Also available drop-in at POST /v1/chat/completions with an API key + prepaid credits (billed exactly per token).

POST /llm/nim

Price

usage-based (provider cost + 10%)

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`model`	`select`	Yes	Model to run. Price is per-token (input + output) at the rate shown + 10%. One of: `kimi-k2.6`, `glm-5.1`, `gemini-3.5-flash`, `gpt-5.2`, `gpt-5.6-luna`, `gpt-5.6-terra`, `gpt-5.6-sol`, `grok-4.5`, `kimi-k3`, `claude-fable-5`, `nemotron-3-ultra-550b`, `deepseek-v4-pro`.
`prompt`	`textarea`	Yes	The user prompt (or use messages)
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, and usage (prompt/completion/total tokens). OpenAI-compatible response when called via /v1/chat/completions.

Example

curl -X POST "https://api.xona-agent.com/llm/nim" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "model": "deepseek-v4-pro",
  "prompt": "Explain x402 payments in two paragraphs",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

Verified Inference (Prova)

OpenAI-compatible chat completions that run inside a TEE (NVIDIA + Intel), are hardware-attested, and anchored on Solana. Every response returns an on-chain proof + Solscan link. Pick a model via the Model field; price varies by tier (standard / premium / flagship).

POST /llm/prova

Price

$0.0014–$0.01 by tier

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`model`	`select`	Yes	Model to run. Price depends on the tier shown. One of: `deepseek-v4-flash`, `gpt-oss-20b`, `qwen-2.5-7b`, `qwen3.5-27b`, `qwen3.6-27b`, `qwen3-vl-30b`, `gpt-oss-120b`, `gemma-4-31b`, `qwen3.5-122b`, `kimi-k2.6`, `glm-5.2`, `deepseek-v4-pro`.
`prompt`	`textarea`	Yes	The user prompt
`system_prompt`	`textarea`	No	Optional system prompt
`max_tokens`	`number`	No	Optional cap on output tokens
`temperature`	`number`	No	Optional sampling temperature (0–2)

Response

Returns text, model, verified (bool), usage, and proof (receipt_id, attested, tee_key, request/response hashes, solscan_url, verify_url) plus a metadata attestation summary

Example

curl -X POST "https://api.xona-agent.com/llm/prova" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "model": "deepseek-v4-flash",
  "prompt": "Explain TEE attestation in two sentences",
  "system_prompt": "You are a helpful assistant.",
  "max_tokens": "1024",
  "temperature": "0.7"
}'

X News

Extract latest news from X (Twitter) username, generate draft tweet and banner with Xona.

POST /ai/x-news

Price

$0.5

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`x_username`	`string`	Yes	X (Twitter) username with or without @ symbol
`x_persona`	`string`	No	X (Twitter) username to mimic persona/style for tweet draft (optional)

Response

Returns success, x_username, and trending_news with title (max 4 words), tweet_draft, and banner_url

Example

curl -X POST "https://api.xona-agent.com/ai/x-news" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "x_username": "@username or username",
  "x_persona": "@username or username"
}'

X Persona

Extract structured persona from X (Twitter) username. Analyzes posts, profile, and communication style to generate persona, style profile, content patterns, and avatar prompt.

POST /ai/x-persona

Price

$0.05

Network

Solana

x402

Request parameters

Parameter	Type	Required	Description
`x_username`	`string`	Yes	X (Twitter) username with or without @ symbol

Response

Returns persona (summary, tone, core topics, beliefs), style_profile (writing style, voice), content_patterns (formats, topics, posting behavior), and avatar (image type, prompt, reference images)

Example

curl -X POST "https://api.xona-agent.com/ai/x-persona" \
  -H "Content-Type: application/json" \
  -H "X-PAYMENT: <x402-payment-payload>" \
  -d '{
  "x_username": "@username or username"
}'

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

Price

Network

x402

On this page