Perplexity launches multi-model API: switches to GPT when Claude declines to respond, solves 3 more of 63 programming problems
10 minutes ago
Beating AI Newsflash: Perplexity has released its Orchestrator API, integrating over 45 models including GPT, Claude, Gemini, Grok, GLM, Kimi, and DeepSeek into a single interface. Developers only need one set of API keys to call models from different providers and settle fees uniformly. The API features two layers of automatic scheduling. The first layer ensures service stability: for instance, if Anthropic’s Claude API experiences errors, rate limits, or timeouts, the system automatically switches to the same Claude model via AWS Bedrock, eliminating the need for manual developer intervention. The second layer automatically selects models based on task requirements. Developers can define rules in natural language, such as assigning simple code edits to low-cost GLM-5.3 Flash, complex troubleshooting to Claude Opus 5.5, and cross-module design to GPT-6.1 Sol. The system reads the ongoing conversation and uses a dedicated decision model to determine the appropriate model. Even when switching models mid-process, it retains access to the full prior conversation history. If the original model is switched back later, it can reuse its cached outputs to reduce redundant computation. Perplexity also tested a special use case: when Claude rejects a task due to safety restrictions, the system switches to GPT to continue processing. The team has established switching rules for cybersecurity, biology, and post-refusal requests. In Terminal-Bench 4.1’s 63 programming problems, Claude Fable 5.2 completed 38 tasks on its own, and 41 tasks with the routing feature, though the estimated cost per task also rose.
Palantir Director Alexander Sells $2.69 Million Worth of Shares, Cashing Out Approximately $2.69 Million
10 minutes ago
Bullish reports Q3 net profit of $576 million, board approves up to $300 million in stock repurchases.
10 minutes ago
Speculation on Jensen Huang's next move: A Semafor reporter predicts he may raise $50 billion to launch a new venture, with zero chance of him returning to NVIDIA.
10 minutes ago
Wells Fargo cuts NVIDIA Corporation's target price from $300 to $250.
10 minutes ago
TD Cowen retains its buy rating on SharpLink and $13 price target, while lowering its ETH price forecast.
10 minutes ago
Cognition launches Devin Bots: one person manages 20 AI agents, processing 1,900 pull requests (PRs) weekly.
10 minutes ago
Hot feeds
A trader profits $448K by monitoring #Binance's new listings!
2024.12.13 17:37:29
Last week, funds have flowed into #Bitcoin, #Ethereum, and #Hyperliquid.
2024.12.16 14:48:36
A $PEPE whale that had been dormant for 600 days transferred all 2.1T $PEPE($52M) to a new address.
2024.12.14 10:35:27
NFT project Ptah has launched, with its trading volume exceeding $900,000 in just half a day; its minting mechanism mandates the use of a Binance Agent ID.
2026.10.23 10:16:30
When Elon Musk tweeted about Moltbook, the meme coin MOLT experienced a short-term 30% price surge, hitting a new all-time high of $114 million.
2026.01.31 18:37:29
A smart #AI coin trader made $17.6M on $GOAT, $ai16z, $Fartcoin,$arc.
2025.01.05 16:05:18
MoreHot Articles

How did I turn $1,000 into $30,000 with smart money?
2024.12.09

10 promising AI Agent cryptos
2024.12.05

The 30-Year-Old Entrepreneur Behind Virtual, a Multi-Million Dollar AI Agent Society
2025.01.22

10 smart traders specializing in MEMEcoin trading on Solana
2024.12.09

A trader lost $73.9K trading memecoins in just 3 minutes — a lesson for us all!
2024.12.13

What is $SPORE? Let us take you through the on-chain records to show you how it works.
2024.12.25

