Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

@RequestyAI
requesty.ai > models > deepinfra > deepseek-v4.1-flash

DeepInfra Inc. deepseek-v4.1-flash API Pricing & Cost: Context Window & Benchmarks

10+ hour, 19+ min ago   (463+ words) Which id to call These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay against these rates, not…...

Requesty
requesty.ai > blog > litellm-default-key-exposure-ai-gateway-tier-one-security

One in ten exposed LiteLLM gateways still answers to sk-1234: your AI gateway is a tier one security asset now

3+ day, 5+ hour ago   (897+ words) On 10 September, The Hacker News summarised a Wiz Research report in one line that reached 2.3 million followers: one example LiteLLM admin key was accepted by nearly 1 in 10 gateways. Researchers found 294 of 3,074 internet facing instances accepted sk-1234, the placeholder in the…...

@RequestyAI
requesty.ai > model > deepseek > deepseek-v4-flash-vision-exp

deepseek-v4-flash-vision-exp: Compare 1 Provider, API Pricing & Performance

4+ day, 23+ hour ago   (276+ words) Which id to call 1 endpoint / 1 region Provider prices, per 1M tokens. Pay as you go adds 5%, or 0% on your own keys. A column is blank where no qualifying sample exists, and every row links to that provider's endpoint page. This model…...

@RequestyAI
requesty.ai > models > compare > google--gemini-3.5-flash > moonshot--kimi-k2.6

gemini-3.5-flash vs kimi-k2.6: Benchmarks, Pricing & Context Window

6+ day, 18+ hour ago   (85+ words) Requesty Side-by-side comparison of gemini-3.5-flash and kimi-k2.6: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. gemini-3.5-flash outperforms kimi-k2.6 on 4 of 7 shared benchmarks. Scores sourced from official model cards, Artificial Analysis, and public leaderboards....

@RequestyAI
requesty.ai > models > fireworks > glm-5.3-flash

Fireworks AI glm-5.3-flash API Pricing & Cost: Context Window & Benchmarks

6+ day, 16+ hour ago   (470+ words) Which id to call These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay against these rates, not…...

@RequestyAI
requesty.ai > models > vertex > gemini-3.8-flash

Google LLC (Vertex AI) gemini-3.8-flash API Pricing & Cost: Context Window & Benchmarks

1+ week, 3+ day ago   (380+ words) Google LLC (Vertex AI)/🇺🇸 US/chat50% off Which id to call This exact deployment on Google LLC (Vertex AI), with no routing and no failover. Send it as the model field. These are the upstream provider rates. Pay as you go…...

@RequestyAI
requesty.ai > models > fireworks > glm-5.3

Fireworks AI glm-5.3 API Pricing & Cost: Context Window & Benchmarks

1+ week, 6+ day ago   (415+ words) Which id to call These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay against these rates, not…...

Requesty
requesty.ai > blog > open-weight-frontier-august-2026-glm-qwen-hy4

Five open weight releases in nine days: GLM-5.3-Flash, Qwen3.8-Flash, Hy4 and the collapse of the capability premium

2+ week, 2+ day ago   (846+ words) Model launch chatter in our social listening corpus went from 506 mentions in the week of 15 to 21 August to 978 in the week of 22 to 28 August. That is 1.93x, and it is not a scraping artifact. Five labs shipped open weight models with…...

@RequestyAI
requesty.ai > models > fireworks > nemotron-lightning-3.5-30b-a3b

Fireworks AI nemotron-lightning-3.5-30b-a3b API Pricing & Cost: Context Window & Benchmarks

3+ week, 1+ day ago   (344+ words) Fireworks AI/🇺🇸 US/chat10% off Which id to call These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay…...

@RequestyAI
requesty.ai > models > fireworks > qwen3.8-max

Fireworks AI qwen3.8-max API Pricing & Cost: Context Window & Benchmarks

3+ week, 1+ day ago   (405+ words) Fireworks AI/🇺🇸 US/chat10% off Which id to call These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay…...