# Aion-2.0, Aion-3.0, Aion-RP 1.0 (8B) and 54 more added

> 57 models from 19 providers joined the catalog the week of 2026-11-02.

- Date: 2026-11-02
- HTML: https://anyrouter.dev/blog/releases/2026-11-02-catalog

## Models

- `aion-labs/aion-2.0` (Aion-2.0) — 131K context · $0.889 / $1.78 per 1M
- `aion-labs/aion-3.0` (Aion-3.0) — 131K context · $3.33 / $6.67 per 1M
- `aion-labs/aion-rp-llama-3.1-8b` (Aion-RP 1.0 (8B)) — 33K context · $0.889 / $1.78 per 1M
- `amazon/nova-2-lite-v1` (Nova 2 Lite) — 1M context · $0.567 / $4.72 per 1M
- `amazon/nova-lite-v1` (Nova Lite 1.0) — 300K context · $0.066 / $0.264 per 1M
- `amazon/nova-pro-v1` (Nova Pro 1.0) — 300K context · $0.888 / $3.55 per 1M
- `bytedance-seed/seed-1.6` (Seed 1.6) — 262K context · $0.361 / $2.89 per 1M
- `cohere/command-r-plus-08-2024` (Command R+ (08-2024)) — 128K context · $3.17 / $15.83 per 1M
- `cohere/embed-5-fast` (Embed 5 Fast) — 128K context · $0.08 per 1M tokens
- `cohere/embed-5-pro` (Embed 5 Pro) — 128K context · $0.12 per 1M tokens
- `deepseek/deepseek-chat` (DeepSeek V3) — 164K context · $0.122 / $0.518 per 1M
- `deepseek/deepseek-chat-v3.1` (DeepSeek V3.1) — 164K context · $0.222 / $0.778 per 1M
- `deepseek/deepseek-v3.1-terminus` (DeepSeek V3.1 Terminus) — 164K context · $0.278 / $0.778 per 1M
- `inception/mercury-2` (Mercury 2) — 128K context · $0.181 / $0.542 per 1M
- `inclusionai/ling-3.2-flash` (Ling-3.2-flash) — 1M context · $0 / $0 per 1M
- `meta/llama-4-maverick` (Llama 4 Maverick) — 524K context · $0.178 / $0.567 per 1M
- `microsoft/phi-4` (Phi 4) — 16K context · $0.078 / $0.156 per 1M
- `minimax/minimax-m1` (MiniMax M1) — 1M context · $0.347 / $2.2 per 1M
- `mistralai/codestral-2508` (Codestral 2508) — 256K context · $0.333 / $1 per 1M
- `mistralai/ministral-14b-2512` (Ministral 3 14B 2512) — 262K context · $0.222 / $0.222 per 1M
- `mistralai/ministral-3b-2512` (Ministral 3 3B 2512) — 131K context · $0.111 / $0.111 per 1M
- `mistralai/ministral-8b-2512` (Ministral 3 8B 2512) — 262K context · $0.167 / $0.167 per 1M
- `mistralai/mistral-large` (Mistral Large) — 128K context · $2.23 / $6.67 per 1M
- `mistralai/mistral-medium-3` (Mistral Medium 3) — 131K context · $0.444 / $2.22 per 1M
- `mistralai/mistral-medium-3.1` (Mistral Medium 3.1) — 131K context · $0.444 / $2.22 per 1M
- `mistralai/mistral-nemo` (Mistral Nemo) — 131K context · $0.032 / $0.033 per 1M
- `mistralai/mistral-saba` (Saba) — 33K context · $0.221 / $0.661 per 1M
- `mistralai/mistral-small-24b-instruct-2501` (Mistral Small 3) — 33K context · $0.056 / $0.089 per 1M
- `moonshotai/kimi-k2-thinking` (Kimi K2 Thinking) — 262K context · $0.339 / $1.44 per 1M
- `morph/morph-v3-fast` (Morph V3 Fast) — 262K context · $0.578 / $0.867 per 1M
- `morph/morph-v3-large` (Morph V3 Large) — 262K context · $0.85 / $1.79 per 1M
- `openai/gpt-5-pro` (GPT-5 Pro) — 400K context · $15 / $120 per 1M
- `openai/gpt-5.2-pro` (GPT-5.2 Pro) — 400K context · $21 / $168 per 1M
- `openai/gpt-6-cyber` (GPT-6 Cyber) — 1.1M context · $20 / $100 per 1M
- `openai/o3` (o3) — 200K context · $2 / $8 per 1M
- `openai/o3-pro` (o3-pro) — 200K context · $20 / $80 per 1M
- `openai/text-embedding-3-large` (text-embedding-3-large) — 8K context · $0.13 per 1M tokens
- `openai/text-embedding-3-small` (text-embedding-3-small) — 8K context · $0.02 per 1M tokens
- `perplexity/sonar` (Sonar) — 127K context · $0.487 / $4.88 per 1M
- `perplexity/sonar-pro` (Sonar Pro) — 200K context · $3.56 / $17.81 per 1M
- `qwen/qwen-2.5-7b-instruct` (Qwen2.5 7B Instruct) — 33K context · $0.048 / $0.119 per 1M
- `qwen/qwen2.5-vl-72b-instruct` (Qwen2.5 VL 72B Instruct) — 128K context · $0.835 / $0.835 per 1M
- `qwen/qwen3-235b-a22b-thinking-2507` (Qwen3 235B A22B Thinking 2507) — 128K context · $0.357 / $0.595 per 1M
- `qwen/qwen3-30b-a3b-instruct-2507` (Qwen3 30B A3B Instruct 2507) — 262K context · $0.222 / $0.556 per 1M
- `qwen/qwen3-coder` (Qwen3 Coder 480B A35B) — 262K context · $0.144 / $0.556 per 1M
- `qwen/qwen3-coder-next` (Qwen3 Coder Next) — 262K context · $0.143 / $0.95 per 1M
- `qwen/qwen3-next-80b-a3b-instruct` (Qwen3 Next 80B A3B Instruct) — 262K context · $0.108 / $0.867 per 1M
- `qwen/qwen3-vl-235b-a22b-instruct` (Qwen3 VL 235B A22B Instruct) — 262K context · $0.222 / $0.978 per 1M
- `qwen/qwen3-vl-30b-a3b-instruct` (Qwen3 VL 30B A3B Instruct) — 262K context · $0.142 / $0.567 per 1M
- `qwen/qwen3.5-122b-a10b` (Qwen3.5-122B-A10B) — 262K context · $0.3 / $2.4 per 1M
- `qwen/qwen3.5-35b-a3b` (Qwen3.5-35B-A3B) — 262K context · $0.225 / $1.8 per 1M
- `stealth/frantic-ferret` (Frantic Ferret) — 1M context · $0 / $0 per 1M
- `unbiased/pareto-26.9` (Pareto 26.9) — 262K context · $2.5 / $7.5 per 1M
- `z-ai/glm-4.5-air` (GLM 4.5 Air) — 131K context · $0.122 / $0.672 per 1M
- `z-ai/glm-4.5v` (GLM 4.5V) — 66K context · $0.567 / $1.7 per 1M
- `z-ai/glm-5.3-flashx-legal` (GLM-5.3-FlashX-Legal) — 1M context · $0.37 / $1.25 per 1M
- `z-ai/glm-5v-turbo` (GLM 5V Turbo) — 203K context · $1.2 / $4 per 1M

## Notes

Two models joined the catalog on 3 and 4 November without a launch note of their own. Both run on your own provider key (BYOK).

| Model | Context | Price per 1M (in / out) | Route |
| --- | --- | --- | --- |
| [`z-ai/glm-5.3-flashx-legal`](https://anyrouter.dev/model/z-ai/glm-5.3-flashx-legal) | 1M | $0.37 / $1.25 (list) | BYOK |
| [`unbiased/pareto-26.9`](https://anyrouter.dev/model/unbiased/pareto-26.9) | 262K | $2.50 / $7.50 (list) | BYOK |

**GLM-5.3-FlashX-Legal** is Z.ai's legal model, built on GLM-5.3-FlashX with legal-domain training. It targets legal research, contract review and drafting. It takes text, image and video input and has a 1M-token context, so a full contract bundle fits in one request. The list rate is $0.37 / $1.25 per 1M.

**Pareto 26.9** is the September 2026 release of Unbiased's blended model. Each request goes to a mix of frontier and open models, and their outputs are blended into one answer. It now has its own pinned id. [Pareto 26.10](https://anyrouter.dev/model/unbiased/pareto-26.10) replaced it and is cheaper ($0.80 / $3.20 per 1M against $2.50 / $7.50), so use 26.9 only when you need to reproduce earlier results.

On a BYOK route AnyRouter charges $0. The provider bills your own account at the list rate above. Add a key under [Dashboard → BYOK](https://anyrouter.dev/dashboard/byok).

Call any of them with the catalog id. In the [Vercel AI SDK](https://anyrouter.dev/use-cases/ai-sdk), `createAnyRouter()` reads `ANYROUTER_API_KEY`:

```ts
import { createAnyRouter } from "@anyr/ai-sdk-provider"
import { generateText } from "ai"

const anyrouter = createAnyRouter()

const { text } = await generateText({
  model: anyrouter("z-ai/glm-5.3-flashx-legal"),
  prompt: "List the risky clauses in this contract.",
})
console.log(text)
```

_generateText with the catalog id._

### curl

```bash
curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"z-ai/glm-5.3-flashx-legal","messages":[{"role":"user","content":"Hello"}]}'
```

### Claude Code

```bash
curl -fsSL https://anyrouter.dev/cli.sh | bash
anyr login
anyr claude --model "z-ai/glm-5.3-flashx-legal"
```

Also new this week, each with its own note: [LongCat-2.5](https://anyrouter.dev/blog/releases/2026-11-02-longcat-2-5), [Aion 3.5](https://anyrouter.dev/blog/releases/2026-11-02-aion-3-5), [Aion 3.0 Mini](https://anyrouter.dev/blog/releases/2026-11-02-aion-3-0-mini), [Hy-MT2 1.8B](https://anyrouter.dev/blog/releases/2026-11-02-hy-mt2-1-8b), [Granite 4.2 30B](https://anyrouter.dev/blog/releases/2026-11-03-granite-4-2-30b) and [Llamport](https://anyrouter.dev/blog/releases/2026-11-03-llamport).

More: [OpenAI SDK](https://anyrouter.dev/use-cases/openai-sdk) · [coding agents](https://anyrouter.dev/use-cases/coding-agents).

No terminal? Open the playground and send a first message.

[Try in playground](https://anyrouter.dev/playground?model=z-ai/glm-5.3-flashx-legal)
