proomt

Search

Search posts, papers, and topics

All posts

VercelKevin Dawkins1 min readrelease notesintro

DeepSeek V4 Flash is 90% off through Novita on AI Gateway

Read on vercel.com

Summary

Vercel AI Gateway offers DeepSeek v4 Flash at a 90% discount through Novita for Pro customers until Aug 11. Use the `order:['novita']` option to route requests and fall back to other providers if needed.

  • Set `model` to `deepseek/deepseek-v4-flash` (or the versioned name) and add `order: ['novita']` in providerOptions to get the discounted rate.
  • The 90% discount applies to Vercel Pro customers only and expires on August 11.
  • If Novita cannot serve the request, the gateway automatically falls back to other providers at standard pricing.
  • After the discount period, the model remains available at regular rates with no markup.

Cost‑conscious developers using Vercel’s AI Gateway can test the DeepSeek model cheaply before the discount ends.

3/10

Related reading

  1. GLM 5.3 FlashX now available on AI Gateway

    Vercel AI Gateway now offers the GLM‑5.3‑FlashX model, a fast (~200 tps) multimodal coding LLM. The post includes a TypeScript streaming example, notes the model’s fit for coding agents and interactive tools, and lists AI Gateway features (unified API, usage tracking, retries/failover, custom reporting, key budgets, routing rules) with no platform fee.

    Vercelvercel.com1 minrelease

  2. DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

    DeepSeek‑V4.1‑Flash is a 552B‑parameter multimodal Mixture‑of‑Experts LLM that supports up to 1 M‑token contexts while slashing KV‑cache memory to 890 bytes/token (≈¼ of its predecessor) via cross‑layer reuse (CSA2) and FP4 quantisation, plus a SWA‑Bounded Replay scheme that cuts persistent cache to 1/8. The Causal Encoder‑Decoder design halves prefill compute (8B vs 16B active parameters) and th…

    Hugging Face Daily Papersarxiv.org3 minpaperHN12710

  3. Qwen 3.8 Max now available on Vercel AI Gateway

    Vercel AI Gateway now offers Qwen 3.8 Max, a 2.4 T‑parameter multimodal LLM with up to 1 M token context. It can be invoked via the standard `streamText` API or through Vercel’s coding agents, with no extra platform fees and full control over usage and security.

    Vercelvercel.com1 minrelease

  4. Open-weight models take 56% of token volume, Astra doubles Fable 5.1 spend

    Vercel’s September AI Gateway Production Index shows open‑weight models processing 56% of token volume (up from 7% in Dec 2025) while accounting for only 14% of spend. Token price fell 23.2% month‑over‑month. Anthropic’s Opus 5 captured 22.5% of spend, overtaking Fable 5 which dropped to 4.9%. OpenAI’s new GPT‑6 Astra grabbed ~7.7% of total gateway spend in its first 12 days, more than double Ant…

    Vercelvercel.com6 minHN2

  5. GPT-Live 1 now available on AI Gateway

    Vercel AI Gateway now offers OpenAI’s GPT‑Live 1, a full‑duplex voice model that can listen and speak simultaneously. The SDK lets you start a voice session and optionally delegate work to any text model, with code examples for both patterns.

    Vercelvercel.com1 minrelease

  6. TypeSafe AI's Jev now available on AI Gateway

    Vercel AI Gateway now offers Jev, a probabilistic decision model that returns typed choices, scores, and booleans instead of raw text. TypeSafe AI reports it runs up to 193× faster and 445× cheaper than standard LLMs, exposed via the experimental evaluate API in AI SDK 7.

    Vercelvercel.com2 minrelease