Model releases

Scira's Amos 1 joins the Decisions family: four open-weight decision models, from a 0.5B CPU encoder to a 27B decoder, free on AnyRouter.

9 models from 5 providers joined the catalog the week of 2026-10-12.

Four new chat models: Mistral's new frontier model, Fireworks' short-trace reasoning model on Kimi K3, IBM's mid-size Granite 4.2 reasoner, and PrismML's ternary 27B. All BYOK.

HAL-X's THX-01 joins the Decisions family: a 322M multilingual decision model with calibrated probabilities, free on AnyRouter.

OpenCode Zen no longer lists fledge-alpha-free (verify:upstreams MISSING and a second /zen/v1/models fetch, 2026-10-11). The platform hop was already commented out (#4419), so the BYOK hop was its only upstream; disabled rather than pruned.

Microsoft-Decision-1, Solar Decide Flash, PPLX Decider v1.1, Drex v1.5 and SubQ Snap Preview join the Decisions family: send state and typed questions, get probabilities back, not chat text.

Subquadratic's long-context chat model, built on its sparse attention architecture for very large inputs. Early access, BYOK via SubQ.

Anthropic's fastest, cheapest Claude 5.x model: 1M context, vision, tools, adaptive thinking always on. $0.10 / $0.50 per 1M list. BYOK.

A stealth reasoning model for coding and long-context work, 256k context, via Vercel AI Gateway BYOK.

9 models from 6 providers joined the catalog the week of 2026-10-05.

Mistral's Apache 2.0 hybrid model, which folds its instruct, reasoning and coding lines into one. 256k context, image input, $0.15 / $0.60 per 1M. BYOK.

Google's Gemma 3n E2B, run on a phone you pair yourself and relayed to AnyRouter. $0 in and out — your hardware does the work.

inclusionAI's Ling 3.1 Flash joins the catalog: a hybrid reasoning mixture-of-experts model with 25B active of 560B total parameters, a 262,144-token context window, and tool calling, available through BYOK.

Apodex 1.1 Mini, a free reasoning-first model for research and forecasting, and Laya, a free System One evaluation model from Convai Innovations.

Google's Gemma 3 4B IT joins the catalog: a 4B open-weight instruct model with text and image input, a 131,072-token context window, and multilingual coverage across 140+ languages, available through BYOK.

Gateway time on anyrouter/free dropped at the slow end, from about 5 seconds to 1.6 seconds. If the first upstream stays silent, anyrouter/free and anyrouter/auto start a second one and keep whichever sends a token first.

Unbiased's newer composite model joins the catalog: 1,048,576-token context, text and image input, tool calling, and a 131,072-token maximum output at $0.80 / $3.20 per million input / output tokens. BYOK-only via OpenRouter.

Fledge Alpha joins the catalog as a free stealth preview: a 1,048,576-token context window, text and image input, tool calling, and reasoning effort on low / high / max — $0 / $0 through OpenCode Zen.

Perplexity's multimodal decision model joins the Decisions family: send state — text or images — and typed questions, get back a probability distribution over a fixed set of answers, not generated chat text.

Strands Labs' open-weight decision model joins the Decisions family: run `strands-decider serve` on your own hardware and route POST /api/v1/decisions to it through AnyRouter BYOK.

Cloudflare has not published per-token pricing for this hosted SKU, so it cannot be billed accurately. It is listed for reference and will return once a published rate is available.

Inception's decision model joins the Decisions family: send state and typed questions, get back a choice, a score or a yes/no answer with a calibrated probability — no generated tokens, no per-token price.

OpenAI's GPT-6.1 Sol joins the catalog BYOK-only through OpenAI — 1.05M-token context, 128K max output, image input, and adjustable reasoning at $2 / $10 per million input / output tokens.

Send google/gemini-flash-latest, anthropic/claude-sonnet-latest and 17 other -latest ids. AnyRouter calls the newest model in that family that is available right now, skips retired ones, and bills the model that answered.

Liquid AI's first decision model joins the Decisions family: send state and typed questions, get calibrated probabilities back with zero generated tokens. Free on Liquid's API with your own Liquid key.

Four Xiaomi MiMo models: V2.6 Pro and V2.6 Flash (1M context, full-modality reasoning) plus V2 Pro and V2 Flash. BYOK via AIHubMix.

Upstage's Solar Decide joins the Decisions family: send state and typed questions, get structured answers instead of chat text, with a 524,288-token context window at $0.05 per million input tokens.

The only upstream no longer publishes inclusionai/ling-2.6-1t (live /models 2026-09-30); the Ling-3.0 family replaces it. (#3687) Plus 2 more.

Anthropic's Claude Sonnet 5.5 joins the catalog — the direct upgrade to Claude Sonnet 5, at the same $2 / $10 per million input / output tokens, with adaptive thinking on by default, 1M-token context, 128K max output, and vision input.

deepseek/deepseek-v4.1-flash gains a DeepInfra BYOK route at $0.20 / $0.60 per million input / output tokens. Novita retires deepseek/deepseek-v4-flash at 16:00 UTC on Oct 9, 2026 — both Novita hops now carry the date and point at V4.1 Flash.

StepFun's next-generation flagship base model joins the catalog BYOK-only on AIHubMix — 1M-token context, 64K max output, text/image/video input, and adjustable reasoning at $1.08 / $3.0888 per million input / output tokens.

Six new BYOK listings: Sakana Fugu Max, Upstage Solar Mini 4, Tencent's Hy-MT2 translation model, Respan's Span-01 Lite classifier, Gemini Embedding 2 and Qwen3 Embedding 4B.

Two more GLM 5.3 tiers from Z.ai: Prime, the top reasoning tier ($2.80 / $8.80 list), and FlashX, the high-speed cut ($0.37 / $1.25 list). Both 1M context, BYOK.

Two BAAI multilingual embedding models and Mistral's current 24B instruction model join the catalog, both on a new BYOK provider: OVHcloud AI Endpoints.

Kev 4B is a small open-weight decision model — a LoRA adapter and pointer head on Qwen3.5-4B-Base. It answers typed questions about a state with calibrated probabilities instead of generated text, on the same native `/v1/decisions` contract as the rest of the family.

Fastino GLiNER2.5-Decide joins TypeSafe Jev and the anyrouter/decision preset, while the new `anyr decision` command gives the whole Decisions family a native terminal client instead of a chat-agent launcher.

Meituan's LongCat-2.5-Preview — a ~1.6T-parameter MoE with ~48B active, 1M-token context, image understanding, and a thinking toggle — joins the catalog over the official LongCat API, BYOK.

Space Bunny Alpha — an anonymous frontier-class stealth preview with blazing-fast inference, strong coding performance, and native multimodal input — joins the catalog as a free model. It always reasons with adjustable effort over a 1M-token context window, served $0 via OpenRouter, Nous, and OpenCode Zen platform hops.

Five verified text-output models join the catalog through AIHubMix and other BYOK routes: Qwen3 235B A22B Instruct 2507, Mercury 2.5, L3.1 Euryale 70B, GPT-6 Sol, and GPT-6 Luna. Published provider prices and context windows are recorded per upstream; AnyRouter does not add platform markup to BYOK traffic.

Previously verified platform routes return 404 for stealth/union-alpha. Hidden from the catalog; configured BYOK fallbacks remain available for users who saved keys.

Anthropic's Claude Opus 5.5 — the successor to Claude Opus 5 for long-running agentic coding and knowledge work — joins the catalog. It delivers Fable 5.1-level performance at 40% lower cost ($4 / $20 per million input / output tokens), with adaptive thinking always on, 1M-token context, vision input, and tool use.

ByteDance Seed's reasoning model for coding, math and multilingual work, 262k context. BYOK via AIHubMix.

xAI's Grok 4.7 joins the catalog — 500K context, adjustable reasoning, vision in, and six BYOK upstream routes.

Two free 35B research and agent models from InternScience and InternLM, plus Qwen3.8 Omni Flash with text, image, audio and video input at 1M context. BYOK via AIHubMix.

NVIDIA's hosted NIM API returns 404 for this catalog id. The model is downloadable self-host NIM only. The live NVIDIA embedding SKU is nvidia/nemotron-3-embed-1b.

Stealth preview Union Alpha joins the catalog free — multimodal research, coding, and agentic workflows at $0.

Agnes AI's Agnes 3.0 Flash (512K, vision in, text out) and NVIDIA Nemotron Parse 2.0 (document images in, structured markdown out) join the catalog.

Existing listings pick up an aihubmix-byok hop. Same catalog ids — not new SKUs. Platform aihubmix stays off (#3031).

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.

The Poolside platform key returns HTTP 429 usage limit exceeded. Listings stay: poolside/laguna-s-2.1, poolside/laguna-xs-2.1, poolside/laguna-m.1, poolside/laguna-xs.2 — not new SKUs. Platform poolside is off; hops parked. poolside-byok stays live.

inclusionAI Ling-3.0-flash-VL, Sante, and Fin join the catalog, plus Nex-N2.5 Mini/Pro. OpenRouter :free is the wire and an alias — Nemotron 3 Ultra and Inkling Small pick up hue hops so we can burn remaining free quota.

DeepSeek V4.1 Flash joins the catalog as deepseek/deepseek-v4.1-flash, with official DeepSeek API and OpenRouter BYOK hops. Peak list $0.30 / $1.20 per 1M tokens.

FPT backend disabled 2026-09-07 (#3146/#2871) — HTTP 401; this model's only platform upstream was fpt. Plus 1 more.

The FPT Cloud platform key returns HTTP 401 Access denied, and the SambaNova platform account requires a payment method (HTTP 402). BYOK SambaNova stays live; FPT Cloud now has a BYOK sibling (fpt-byok). NVIDIA NIM hops that 404 for models NVIDIA does not serve were dropped per listing, not the whole nvidia backend.

Experiential Cloud promotional hops for Claude Fable 5.1 and a new GPT-6 Astra listing (BYOK live; hosted platform hop pending #2842 recert).

Cloudflare AI Gateway Unified Billing is exhausted (#3121), so the platform cloudflare backend is disabled. Keep the verified unbiased/pareto model as a disabled catalog tombstone until the backend is funded and re-enabled.

Meta's Muse Spark 1.3 joins the catalog over AIHubMix BYOK — a multimodal reasoning model for agentic tasks with a 1M-token context window.

Google Gemini 3.8 Flash and Inception Labs Mercury 2.5 Preview join the catalog. Claude Fable 5.1 and Qwen3.8 Max pick up AIHubMix hops on their existing ids.

This model has been removed. Requests that still use stealth/ox-alpha or stealth/ox-alpha[1m] are routed to anyrouter/auto.

Anthropic Claude Fable 5.1 joins the catalog as one listing, routed through Anthropic BYOK and Cloudflare Workers AI, with OpenRouter BYOK as a fallback.

Tencent Hunyuan Hy4 Preview joins the catalog as tencent/hy4-preview, routed through AIHubMix BYOK at the aggregator's published list rates.

Alibaba Qwen3.8 Flash via AIHubMix BYOK. List $0.1126 / $0.38 per 1M.

Every remaining platform host returns 404 for this catalog id. NVIDIA's current Nano omni/VL successor is nvidia/nemotron-3-nano-omni-30b-a3b-reasoning. Plus 1 more.

Hosted probes for this catalog id fail with a bad request. The model is unlisted rather than advertised as a live hosted chat model.

The remaining platform host is out of credit, and the other platform route is already disabled. Remaining routes require a user-owned key, so the model is unlisted rather than advertised as a live hosted chat model. Plus 4 more.

Eight models from the post-closeout sweep: Z.AI GLM-5.3 (coding preview), DeepSeek vision + 0731-fast, Microsoft MAI-Thinking-1, OpenAI GPT-5.6 Sol Disc, and Agnes 2.5 Flash/Pro/Alpha via AIHubMix.

The Ox Alpha preview is GLM-5.3-Flash: native multimodal, 1M context, MIT-licensed 320B-A18B. Same AnyRouter routes, catalog id z-ai/glm-5.3-flash.

Free community endpoint for Qwen3.8-Flash-Next — open by default, from Empero research lab. Catalog id qwen/qwen3.8-flash-next.

AIHubMix joins the platform free pool: MiniMax M2.7, Kimi K3, Gemini 3.x Flash, Nemotron 3, GPT-OSS 20B, and more, all routed at $0.

The only platform host (hoian) is balance-quarantined and no longer serves this catalog id reliably. Unlisted until a live hosted path returns. Plus 1 more.

Ox Alpha joins the catalog free — a stealth reasoning model for coding, agentic work, and long-horizon engineering.

Qwen3.6-27B, Qwen3.8-27B, Gemma 3 27B IT, and Meta Llama 3.3 70B Instruct join the catalog as paid chat models.

Half off through 1 Sep. Same ids, same API — just a friendlier bill.

The platform Workers AI host no longer serves this catalog id (model_unavailable). Remaining routes require a user-owned key, so the model is unlisted rather than advertised as a live hosted chat model. Plus 11 more.

Cloudflare Workers AI retired this SKU on 2026-05-30; live smoke 2026-08-14/18 returns model_unavailable (no_route). It was this model's only upstream, so it was disabled rather than the route pruned.

GitHub Models was fully retired on 2026-07-30. The inference API and BYOK endpoints return HTTP 410, so the github and github-byok backends are off.

DeepSeek V4 Pro (0813) joins the catalog, hosted on Cloudflare Workers AI with a 1M-token context window.

Cloudflare has not published per-token pricing for this partner-hosted SKU (rate visible only in the CF dashboard once provisioned); shipping it live on the metered `cloudflare` backend without a real rate would bill $0. Plus 3 more.

Google Gemini 3.7 Flash joins the catalog, plus Qwen3.8 2.4T A95B, Muse Spark 1.2, Inkling Small, Solar Pro 4, Seed 2.1 Turbo, Seed 2.0 Code, Claude Opus 5 Fast, and Dots3-Note Preview.

CF Workers AI LoRA host 404 / model_unavailable on every smoke probe (2026-08-14). Canonical Gemma instruct SKUs remain (gemma-3 / gemma-4). Sibling gemma-2b-it-lora already disabled. Plus 4 more.

SiliconFlow no longer lists this id; its catalogue carries gemma-4-12B-it, gemma-4-26B-A4B-it and gemma-4-31B-it instead. Plus 6 more.

NVIDIA NIM additions (Nemotron 3.5 Lightning 30B, Meta Muse Glimmer 30B, DeepSeek-V4-Flash 0731), ByteDance Seedance 2.5 on Workers AI, and free Requesty route for Ling-3.0-tiny.

Expanded free platform routes across NVIDIA Nemotron free models, GPT-OSS-20B free, Ling-3.0-tiny on Novita, and new Liquid LFM 2.5 2.6B free. CommandCode free/promo routes for Laguna S 2.1 and MiMo V2.5 Pro.

xAI Grok 4.6 joins the catalog via xAI BYOK and OpenRouter BYOK. 500K context, $2/$6 list on xAI.

The catalogue is text/embedding-output only; video models stay on disk for future re-enable (same posture as seedance-2.0-mini). Unpriced CF video would also fail metered-catalog-billing. Plus 2 more.

Google's EmbeddingGemma 300M open embedding model and inclusionAI's Ling-3.0-tiny free MoE chat model join the catalog.

Sakana AI's Japanese-specialized LLM (built on Kimi K2.6) joins the catalog via BYOK.

1 model from 1 provider joined the catalog the week of 2026-08-03.

NVIDIA's Nemotron 3.5 Nano joins the catalog via Blackbox AI BYOK.

Eight new models discovered from upstream providers and added to the catalog — NVIDIA's free Nemotron Nano 12B V2 VL and 9B V2 via OpenRouter, Z-AI's GLM-4.5 and GLM-4.6 (with vision variant), MiniMax M2, and Alibaba's Qwen3.5-9B and Qwen3.5-27B.

Alibaba's Qwen3.7 Flash — a vision-language reasoning model for multimodal agents, visual coding, search, and computer interaction — joins the catalog via OpenRouter BYOK.

The catalogue was narrowed to models whose output is text or embeddings; this model's output is an image, so it was taken out of service. Related: #1551 (these SKUs bill $0 on a metered backend). Plus 15 more.

Anthropic's Claude Opus 5 — the flagship model for demanding reasoning, coding, and long-horizon agentic work — joins the catalog, BYOK-only like its Claude siblings.

inclusionAI's Ling-3.0-flash — a 124B-parameter Mixture-of-Experts model (~5.1B active) tuned for token-efficient, production-scale agentic inference — joins the catalog, served free with a user-owned API key (BYOK).

The Cloudflare AI Gateway unified-billing balance and the Blackbox platform budget both ran out. BYOK siblings stay live; platform traffic fails over or stops.

Google's Gemini 3.6 Flash and Gemini 3.5 Flash Lite join the catalog as partner-hosted SKUs on Cloudflare Workers AI, with OpenRouter BYOK fallback.

Poolside's latest coding agent model Laguna S 2.1 (118B total, 8B active parameters, 1M context, 70.2% Terminal-Bench 2.1, 40.4% DeepSWE) joins the catalog — open-weight under OpenMDW-1.1.

1 model from 1 provider joined the catalog the week of 2026-07-20.

Thinking Machines Lab's first open-weights foundation model Inkling (975B MoE, 41B active, 1M context, multimodal input with switchable reasoning) and NVIDIA's Nemotron-3-Embed-1B multilingual embedding model (2048 dims, 34 languages) join the catalog via NVIDIA NIM.

Moonshot AI's Kimi K3 is now available on AnyRouter — an open-source model with a 1M-token context window and native visual understanding (text, image, and video). Built for long-horizon software engineering and deep reasoning where code meets visual and spatial thinking, with thinking mode always on.

The platform OpenAI key has no quota (429 insufficient_quota) and DeepInfra has no payment method (402). BYOK users are unaffected.

3 models from 2 providers joined the catalog the week of 2026-07-13.

The public `openrouter` backend is off. Platform traffic uses the masked hue route; user keys stay on openrouter-byok.

Two frontier additions: xAI's Grok 4.5 joins the catalog and Poolside ships a refreshed Laguna XS 2.1 coding model.

A batch of open-weight models now has a free-tier upstream — Qwen3 across sizes, Gemma 4 27B, and Tencent Hy3.

9 models from 6 providers joined the catalog the week of 2026-07-06.

Anthropic's Claude Sonnet 5 is available through BYOK — bring your Anthropic key and route it behind the gateway.

The OpenAI Codex family lands — GPT-5.3 / 5.2 Codex and 5.1 Codex Max — alongside Z.ai's GLM-5 and Qwen3.7 Max.

The LongCat provider joins the catalog with LongCat-2.0, available via BYOK.

4 models from 3 providers joined the catalog the week of 2026-06-29.

Three new upstreams broaden coverage — Cerebras GPT-OSS, Venice's MiniMax M2.7, and Wafer's aggregated MiniMax M3 and GLM-5.2.

8 models from 3 providers joined the catalog the week of 2026-06-22.

3 models from 2 providers joined the catalog the week of 2026-06-15.

14 models from 8 providers joined the catalog the week of 2026-06-08.

10 models from 9 providers joined the catalog the week of 2026-06-01.

6 models from 2 providers joined the catalog the week of 2026-05-25.

12 models from 7 providers joined the catalog the week of 2026-05-18.

24 models from 3 providers joined the catalog the week of 2026-05-11.

1 model from 1 provider joined the catalog the week of 2026-03-30.

1 model from 1 provider joined the catalog the week of 2026-03-02.

1 model from 1 provider joined the catalog the week of 2025-04-07.

1 model from 1 provider joined the catalog the week of 2025-03-31.

1 model from 1 provider joined the catalog the week of 2025-03-10.

1 model from 1 provider joined the catalog the week of 2025-02-10.

1 model from 1 provider joined the catalog the week of 2024-11-11.

2 models from 1 provider joined the catalog the week of 2024-07-22.

Its BYOK aggregator upstream no longer lists this model id (verify:upstreams MISSING 2026-07-16), and that was its only upstream. See #1283. Plus 12 more.