Telexed

telexed ~ home★4 and up · hourly · UTC+09LIVE

TELEXED// solo-operator signal radar · Issue 829

AI news through a solo-operator lens — only what changes your day3 of 829

FILTER[All][Agents & tools][Models & API][Generative media][Infra & SaaS][ASO & growth][Indie business][Idea signals][Other][★6+ high-signal]

vercel_blog ✕clear filters

Thu, May 281 dispatches

#0829
#0829Models & API vercel_blog2 days ago
`Claude Opus 4.8` lands on `Vercel AI Gateway`
80radar
Vercel AI GatewayLLM gateway — unified calls, cost tracking, and failover
Long-running coding and knowledge tasks can now route through one Vercel API. Useful if you already want retries, cost tracking, and failover without wiring providers yourself.
- Use anthropic/claude-opus-4.8 in the AI SDK; model switching stays inside the existing Gateway path.
- Positioned for long-horizon agent work: multi-step refactors and complex coding tasks need less mid-task correction.
- Gateway adds usage and cost tracking, retries, failover, and latency/cost-based provider sorting. Less infra glue around LLM calls.
- Pricing mirrors provider rates with no Vercel markup or platform inference fee, including BYOK requests.
Source: vercel.com/changelog/opus-4-8-on-ai-gatewayRead original →
FIG-8291:1
80radar
FIG-8291:1

Wed, May 201 dispatches

#0828
#0828Models & API vercel_bloglast week
`Grok Build 0.1` lands on `Vercel AI Gateway`
60radar
Grok Build 0.1Agentic coding model — powers the Grok Build CLI
A beta agentic coding model is now callable through the AI SDK. Useful for quick experiments, but early access and fixed reasoning keep it from being a default choice.
- Set the model to xai/grok-build-0.1 in the AI SDK; integration cost is low if the app already uses AI Gateway.
- Reasoning effort is not configurable, and there is no non-reasoning mode. Latency and cost controls are limited for production agents.
- AI Gateway adds usage tracking, cost reporting, retries, failover, BYOK, and provider routing around the model call.
Source: vercel.com/changelog/grok-build-0-1-now-available-on-verRead original →
FIG-8281:1
60radar
FIG-8281:1

Tue, May 191 dispatches

#0827
#0827Models & API vercel_blog2 weeks ago
`Gemini 3.5 Flash` lands on `Vercel AI Gateway`
80radar
Vercel AI GatewayLLM API gateway — routing, cost tracking, and failover
Better coding, reasoning, and agent loops are now available through one gateway call. Good fit when uptime, cost tracking, and failover matter more than direct provider integration.
- Use google/gemini-3.5-flash in the AI SDK; migration is mostly a model string change for existing Gateway users.
- Default thinking level is medium, aiming for faster and cheaper generation without fully dropping reasoning quality.
- temperature, topP, topK, and thinking_budget are unsupported, so apps relying on sampling controls need compatibility checks.
- AI Gateway adds usage tracking, cost reporting, retries, failover, BYOK, and provider routing on top of the model call.
Source: vercel.com/changelog/gemini-3-5-flash-on-ai-gatewayRead original →
FIG-8271:1
80radar
FIG-8271:1