Context-window floors on anyrouter/auto, free, byok, and the other virtual ids
Append [1m] or [500k] to any first-party virtual id to keep only members with at least that context window. Not a new listing. The same preset, with a token floor.
Open AnyRouter Auto- AnyRouter Autoanyrouter/auto[1m] / [500k]
- AnyRouter Freeanyrouter/free[1m] / [500k]
- AnyRouter BYOKanyrouter/byok[1m] / [500k]
- AnyRouter Codinganyrouter/coding
- AnyRouter Agentanyrouter/agent
- AnyRouter Hermesanyrouter/hermes
- AnyRouter Coworkanyrouter/cowork
- AnyRouter Latestanyrouter/latest
First-party virtual ids now accept a context-window suffix. [anyrouter/auto[1m]](https://anyrouter.dev/model/anyrouter/auto) and [anyrouter/auto[500k]](https://anyrouter.dev/model/anyrouter/auto) are the same preset as anyrouter/auto, with provider.min_context set to 1,000,000 or 500,000 tokens. The same spelling works on anyrouter/free, anyrouter/byok, anyrouter/coding, anyrouter/agent, anyrouter/hermes, anyrouter/cowork, and anyrouter/latest. There is no extra catalog row for the suffix.
Claude Code strips [1m] before the gateway, so anyr claude peels the floor into CLAUDE_CODE_EXTRA_BODY. A bare anyrouter/auto without the floor can still pick a high-usage member. Model pages list the shortcuts and can preview the ≥500k / ≥1M member list.
- App code: Vercel AI SDK or OpenAI SDK.
- Coding agent:
anyr claude/anyr opencode/anyr codex(playbook). - No code: playground.
Try it in the Vercel AI SDK. createAnyRouter() reads ANYROUTER_API_KEY:
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"
const anyrouter = createAnyRouter()
const { text } = await generateText({
model: anyrouter("anyrouter/auto[1m]"),
prompt: "Summarize this diff in three bullets.",
})
console.log(text)Already on the OpenAI SDK? OpenAI SDK playbook:
import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://anyrouter.dev/api/v1",
apiKey: process.env.ANYROUTER_API_KEY,
})
const res = await client.chat.completions.create({
model: "anyrouter/auto[1m]",
messages: [{ role: "user", content: "Hello" }],
})
console.log(res.choices[0]?.message.content)curl https://anyrouter.dev/api/v1/chat/completions \
-H "Authorization: Bearer $ANYROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"anyrouter/auto[1m]","messages":[{"role":"user","content":"Hello"}]}'Or launch a coding agent through the anyr CLI:
curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr claude --model "anyrouter/auto[1m]"curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr opencode --model "anyrouter/free[1m]"curl -fsSL https://anyr.dev/cli.sh | bash
anyr login
anyr codex --model "anyrouter/auto[500k]"More: AI SDK · OpenAI SDK · coding agents · Claude Code.
No terminal? Open the playground and send a first message.
Try in playgroundRelated posts
- How our CI/CD changed when coding agents took overEngineeringNovember 3, 2026 · Coding agents now write and ship most AnyRouter changes. After five months on GitHub Actions, we changed our CI/CD design four times in one month. We moved from GitHub Actions to local CI on one machine, then to review-gated PRs, then to a few fat PRs, and now to commits straight on main. This post walks through each stage with the numbers we measured, the bugs we found on the way, and the rules we give our agents today.
- CLI update: a separate key for each coding agentProductNovember 2, 2026 · The anyr CLI can now give Claude Code, Codex, OpenCode and the other coding agents it launches their own API key or their own account, with plain commands. Each agent gets its own spend, limits and revocation.
- Where every -latest alias points todayProductOctober 10, 2026 · AnyRouter has 19 family aliases like google/gemini-flash-latest and z-ai/glm-latest. Here is the model each one resolves to on October 10, 2026, and the seven you can call on live routes right now.
- Latest aliases: name a family, always get a live modelProductSeptember 30, 2026 · Models get retired or go down. A -latest alias calls the newest model in a family that is available right now, skips dead ones, and bills the model that answered.
Looking for the full catalog?Muốn xem toàn bộ danh mục?想看完整目录? Browse all modelsXem tất cả model浏览全部模型.