Paid services matching “stream”

Stateful 5-Minute DeFi, DEX & Polymarket Alpha Delta Stream (/v1/alpha-stream) — Stateful 5-minute delta feed for autonomous trading bots: computes real-time shifts in DEX buy/sell ratio, DeFiLlama APY spreads, and Polymarket odds. (https://alpha-stream.agentdiet.dev/v1/alpha-stream)

Stateful 5-Minute DeFi, DEX & Polymarket Alpha Delta Stream (/v1/alpha-stream) — Stateful 5-minute delta feed for autonomous trading bots: computes real-time shifts in DEX buy/sell ratio, DeFiLlama APY spreads, and Polymarket odds.

A stream pass ($0.50 per pass, not per call): up to 60 minutes of Server-Sent Events at /v1/sol/bursts/stream?token=…, pushing Solana pump.fun and Robinhood Chain buyer bursts, pump.fun graduations and new Telegram calls (public chats named, callers hashed) as they fire. The worker appends events every few seconds; heartbeat every 15 s, up to 2 connections per pass. Answers 503 stream_disabled (no

Macro-Odds Real-Time Polymarket Prediction Market Stream: Streams live prediction market implied probabilities, volume, and orderbook depth.

Autonomous agent execution (multi-step reasoning + tools). Engines: cheap agents/oss-20b or premium agents/gpt-6-sol; stream=true streams SSE step events. Ceiling = engine base + max_steps x step + code_exec calls ($0.002 each, max 3 per task) (charged_ceiling_usd).

Linkrra Synap: Google Gemma 4 26B A4B Instruct (model "gemma-4-26b-a4b-it") - fast general model, long context. OpenAI-compatible chat completions for this one model, 128K context, served only on dedicated GPUs we operate, 4-bit AWQ. Pay per call in USDC on Base via x402 - no account, no API key. From $0.001 per call, usage-priced per token above that (GET /v1/models). Streaming supported. Product

Change stream for PDUFA dates a company put in an SEC filing: every set, extension and resolution of every tracked catalyst, with the outcome (approval or CRL), the filing quote and its EDGAR source, as a since-cursor feed. Use when you mirror those disclosed dates and need changes as they land, not a snapshot. Accuracy and coverage are free at GET /v1/accuracy. Flat price per request.

DeepSeek V4 Flash Chat API (deepseek/deepseek-chat): LLM inference via OpenAI-compatible chat completions, pay per call in USDC on Base with x402. No API key, no account. Suited for AI agents and scripts that need DeepSeek V4 Flash Chat on demand. When listed, this request cost 30% less than the same request on BlockRun. Streaming and function calling supported. Exact price in the 402 quote before

OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.

High-speed single-pass state machine microservice that deterministically repairs cut-off and truncated JSON streams from LLMs (e.g., max_tokens cut-offs or live SSE chunks). Automatically closes unterminated strings, completes partial literals (tru/fals/nul) and numbers, resolves dangling keys/colons, strips markdown fences, and balances nested containers in LIFO stack order with optional progress

Turn newline-delimited JSON exports into one JSON array for downstream processing. Parse supplied NDJSON or JSON Lines text with LF or CRLF endings. A final newline is required; empty-line skipping is optional. Rejects malformed JSON and duplicate keys. Bounded text input, not file reading or streaming.

Mid-tier OpenAI-compatible chat completion. Qwen3 235B (instruct/thinking/VL/next), DeepSeek V3.2, GLM 5.2, venice-uncensored 1.2, GLM 4.6/4.7, Kimi K2.5, MiniMax M3 Preview, Nemotron 3 Ultra 550B, DeepSeek V4.1 Flash, Gemma 4 26B. Supports tools/tool_choice and stream:true SSE.

Twitter (X) video & image downloader — pass a public tweet / X post URL, get direct CDN media links: .mp4 video URLs with thumbnails plus every image in the post, ready to stream, embed, re-host, or download. No scraping or browser automation.

Decode a MessagePack or CBOR byte stream (supplied as a base64/base64url/hex string) back into a JSON value. A malformed envelope, malformed bytes, or a value that is not JSON-representable is rejected before payment.

Follow subscription: a token for the live event stream for 24 hours

OpenAI-compatible chat completions for hundreds of open and closed models (DeepSeek, Kimi, GLM, Qwen, Llama, Claude, GPT, Gemini) through one endpoint, each call routed to the cheapest healthy provider for that model. Pay per call in USDC on Base with no API key or account: the 402 quotes this prompt plus max_tokens (up to 4,096). Streaming and tool calls supported. Model ids and prices: https://a

Retrieves a previously stored object by its key (?key=...) and streams it back with its original Content-Type. Flat $0.01 per call, regardless of size.

Resolve a token symbol, name or address to DEX pools on Solana, Base or Ethereum: pool, token, dex, price, liquidity, market cap and 24h volume, best liquidity first. Use it to turn a ticker into a tradeable pool address before calling pool, ohlcv, trades or holders.

Ask a live crypto, stock, or macro analyst desk any market question — social sentiment, dominant narrative, Polymarket & Kalshi prediction-market odds, sentiment-vs-price divergence, whale positioning and funding context — answered fresh in 10-180s. ?q= free-form and/or ?asset=BTC. A live specialist desk at generic-AI-research prices. No charge if the desk fails to answer. Descriptive research, no

FuelScout cheapest-fuel query (station-level where open data exists, regional averages otherwise)

Unified Bitcoin transaction analysis: fee verdict, mempool state, RBF bump plan, and Core v31 template check.

BorderScout crossing query (crossings ranked by all-in time: drive + wait, per lane type)

RecallScout recall lookup (active US recalls across FDA, NHTSA and CPSC with normalised severity)

Tip $1.00 USDC for level 100 supporter chat

Processed transactions that touch specified accounts or programs before finalization.