Add corrections, implementation notes, pricing changes, or usage caveats for other readers.
Last updated
Jul 21, 2026
Knowledge cutoff
2026-03
Input modalities
Output modalities
Capabilities
1,048,576 tokens
Recent tweets and retweets from Requesty
Gemini 3.7 flash now available on Requesty!
Both global and EU endpoint with 50% off!
requesty.ai/models/vertex/ge…
Link
Google LLC (Vertex AI) gemini-3.7-flash API Pricing & Cost: Context Window & Benchmarks | Requesty
gemini-3.7-flash API pricing: $0.75/1M input,…
API key management just got a lot better in Requesty 🔑
Filter keys by owner, expiry, spend, usage, logging, labels & service accounts, then enforce budgets, expiry, logging and model access.
Plus: per-key analytics for $, tokens, requests & model usage.
Video
DeepSeek Pro v4-0813 from @deepseek_ai is now available on Requesty!
requesty.ai/models/deepseek/…
Link
DeepSeek deepseek-v4-pro-0813 API Pricing & Cost: Context Window & Benchmarks | Requesty
deepseek-v4-pro-0813 API pricing: $0.43/1M input, $0.87/1M output, 1M context.…
Grok 4.6 from @SpaceXAI is now live on Requesty!
It lands close to other frontier models across the board, at a fraction of the price. Just $2/M input tokens and $6/M output tokens.
Available now: requesty.ai/models/xai/grok-…
We shipped a new Overview page in Requesty 🚀
See exactly how AI is being used across your organisation.
Drill into usage by:
→ Models
→ Apps
→ Groups
→ Users
→ API keys
And understand the spend, requests + tokens behind each.
Video
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.