Requesty @RequestyAI

The AI gateway. One API for 600+ models, routed intelligently. Built for teams shipping AI to production. requesty.ai Joined September 2023

Tweets

234
Followers

815
Following

97
Likes

156

Requesty @RequestyAI

14 hours ago

Claude Code. Cursor. Codex. curl. All on your API keys. Do you know which ones? New in Requesty: see every agent on every key, catch leaked keys, kill them in one click. → app.requesty.ai/api-keys?view=…

2 1 3 110 0

View Details

Requesty @RequestyAI

a day ago

Congrats to our friends at @MiniMax_AI for their new release! Live on requesty.ai

0 0 1 96 0

View Details

Requesty @RequestyAI

2 days ago

Keys leak. Make a leaked key useless off your network. New on Requesty: Allowed IPs. List the IPv4 addresses and CIDR ranges that may call Requesty for your org. Anything else is rejected, on every endpoint, and every change lands in the audit trail.

0 1 3 151 1

View Details

Requesty @RequestyAI

3 days ago

New @deepseek_ai v4.1 51% discounted on Requesty! $0.098 / 1M tokens $0.294 / 1M tokens $0.003 cached / 1M tokens

0 1 2 137 0

View Details

Requesty @RequestyAI

5 days ago

A Jev decision through Requesty, median over the last 30 days: Model: 241 ms Requesty: 2.3 ms That 2.3 ms is key auth, spend limits, approved-model and compliance checks, and rate limits. Under 1% of the request. typesafe/jev-latest

0 0 2 145 0

View Details

Requesty @RequestyAI

5 days ago

Meta's Muse Spark Open is live on Requesty. Open weights, 816B total / 42B active parameters, 1M context. Meta built it for coding and long-horizon agentic work, and calls it the most capable US open-weight model to date. model: muse-spark-open

AI at Meta @AIatMeta

5 days ago

Today we’re releasing Muse Spark Open, the most capable US open-weight model to date. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning. Key Model Specs: → 816B total / 42B active parameters → 1M token

474 1K 12K 1.2M 2K

0 0 5 260 0

View Details

Requesty @RequestyAI

6 days ago

Small one, but you kept asking for it. Top up by card in USD, GBP, EUR, JPY or CNY, or iDEAL in EUR. It lands in your USD balance at the rate shown in checkout. Auto top-up charges your card in its own currency too.

0 0 1 94 0

View Details

Requesty @RequestyAI

6 days ago

Jev 1.14 now live on requesty.ai !

0 0 1 297 0

View Details

Requesty @RequestyAI

7 days ago

Morning spikes pushed NotarBot past provider quotas, and 429s stalled live calls. Rotating regions split the prompt cache. Now: one stable endpoint, higher-limit deployments, cross-provider failover. Cache hits on nearly every turn. requesty.ai/customers/nota…

0 0 0 86 0

View Details

Requesty @RequestyAI

a week ago

Gemini 4 Argon from @GoogleDeepMind is live on Requesty. Google's new frontier model for coding, enterprise knowledge work and cyber defense. 1M context, up to 1M output tokens, with vision, tools and caching. Served globally and from the EU.

Google DeepMind @GoogleDeepMind

a week ago

Gemini 4 Argon is now globally available. Built to solve your hardest problems from start to finish, the model brings frontier capabilities across coding, enterprise workflows, and cyber defense.

395 674 6K 2.5M 2K

0 0 1 134 0

View Details

Requesty @RequestyAI

a week ago

The fastest provider for a model changes all day. Requesty's latency routing sends each new session to the fastest one, ranked on time to first token and throughput, corrected for errors. Sessions stay pinned so your cache stays warm. docs.requesty.ai/features/laten…

0 0 1 117 0

View Details

Melious AI GmbH @MeliousAI

a week ago

We are happy to announce that we are now partnering with @RequestyAI 🚀 One shared conviction. European inference should be a routing decision, not a migration project. Requesty routes 225B+ tokens a day through 600+ model endpoints. As of today, you'll be able to route GLM-5.3, GLM-5.3 Flash, DeepSeek V4.1 Flash and DeepSeek V4 Flash through the same endpoint and SDK your team already builds on, from $0.12 per 1M tokens. Through Requesty's unified API and Melious' European infrastructure, teams can access high-performance inference while keeping their workloads in Europe. No new integration. Just a European option. This is what building a sovereign AI ecosystem looks like, one partner at a time. #SovereignAI #EuropeanAI #OpenWeightModels #MeliousAI #Requesty

0 3 3 578 1

View Details

Requesty @RequestyAI

a week ago

Meta's Muse Wonder is live on Requesty. Built for long-running agentic work: memory across sessions, persistence through blockers, check-ins before important actions. $4 in / $20 out per 1M tokens, $0.20 cache reads, 1M context. model: muse-wonder-1.0

1 0 4 268 0

View Details

Requesty @RequestyAI

a week ago

Haiku 5.5 vs Haiku 4.5, same customers, same window: 2.9x faster output 3.8x longer answers 3.1x more context per request 44% of calls end in a tool call (14% on 4.5) 21% of output is thinking (3% on 4.5) And 48% cheaper per request.

0 0 0 59 0

View Details

Requesty @RequestyAI

a week ago

Claude 5.5 is a speed upgrade, not just a quality one. p50 output speed on streaming Claude traffic through Requesty, Oct 8 to 11: Haiku 5.5: 3.3x Haiku 4.5 Sonnet 5.5: 2.3x Sonnet 5 5 days after launch, Haiku 5.5 already carries 94% of Haiku tokens.

1 0 0 83 0

View Details

Requesty @RequestyAI

a week ago

Haiku 5.5 is the fastest Claude switch we've measured on Requesty. It took 51% of all Haiku tokens in its first 46 hours. Same window after launch: > Opus 4.8: 32% of Opus tokens > Opus 5.5: 19% > Sonnet 5.5: 17% > Opus 4.7: 7%

3 0 6 451 1

View Details

Requesty @RequestyAI

2 weeks ago

Open-source models on Requesty. January → September 2026: Tokens: 5% → 53% Requests: 12% → 42% Spend: 0.4% → 14%

0 1 4 134 0

View Details

Requesty @RequestyAI

2 weeks ago

"Where did our prompts go, and who kept them?" Requesty's new Compliance page answers that for every request: where the model was hosted, whether it retains or trains on data, and what scanning caught. One click exports it as an evidence report. app.requesty.ai/compliance

0 0 0 84 0

View Details

Requesty @RequestyAI

2 weeks ago

Claude Haiku 5.5 is live on Requesty. The fastest model in the Claude 5.5 family, built for high-volume, speed-sensitive workloads. $0.10 / $0.50 per MTok (≤100k input), $0.50 / $2.50 above First Haiku with effort levels Still on Haiku 4.5? Time to upgrade.

Claude @claudeai

2 weeks ago

Introducing Claude Haiku 5.5: the cheapest, fastest, and most capable small model we’ve ever released. On average, it costs around 75% less to run than Claude Haiku 4.5.

2K 3K 45K 6.7M 5K

0 0 2 278 0

View Details

Requesty @RequestyAI

2 weeks ago

ZoomInfo evaluated over 7 AI gateways, then routed Claude Code, Copilot and its agents through Requesty. "Requesty's enterprise readiness and configurability is what set it apart." - Arkady Landes, Senior Cloud DevOps Manager, ZoomInfo requesty.ai/customers/zoom…