> ## Documentation Index
> Fetch the complete documentation index at: https://docs.layerx1.com/llms.txt
> Use this file to discover all available pages before exploring further.

# The model catalog.

> Every model in the catalog, with its tier, context window, capabilities, and per-million-token list pricing. Request one by name with the model field.

Request a model by name with the `model` field. Every paid plan includes the whole
catalog; the Free plan includes the open-model lineup. Prices are USD per one million
tokens — the public list rates your plan's included usage is measured at. Model names
link to the full page for that model: description, strengths, and capabilities.

## Live and preview

The **Availability** column is the one to read before you pin an id in production.

* **Live** — the gateway holds a routed placement for this exact model. It is what
  [`GET /v1/models`](/api/models-endpoint) returns, and its published context window,
  capabilities and rates are that model's own.
* **Preview** — the id is accepted and answered, but no dedicated placement is routed for
  it yet, so the request is served by a capability-comparable model from the serving pool.
  Its row below is the card we will bill against and the shape we are working toward; it is
  **not** a guarantee that the named model itself is what responds today. A conversation
  stays on one pick, so behaviour is stable within a session.

Pin **Live** ids for anything whose exact behaviour you depend on — evals, structured
extraction, a golden-path agent step. Treat **Preview** ids as a forward-compatible name to
develop against, and re-check this page before you depend on one.

<Note>
  This page is a snapshot, and it is the broader of the two lists. Call `GET /v1/models`
  to read the catalog programmatically — it returns the routed models only, each entry
  self-describing down to its capabilities, limits and pricing. The gateway is always
  authoritative over this page.
</Note>

## Frontier

The largest frontier models, reachable by name through the same endpoint.

| Model                                                             | Context | Input /Mtok | Output /Mtok | Capabilities             | Availability |
| ----------------------------------------------------------------- | ------- | ----------- | ------------ | ------------------------ | ------------ |
| [`lx1-fable-5`](https://layerx1.com/models/lx1-fable-5)           | 1M      | \$10        | \$50         | Tools, Reasoning, Vision | Live         |
| [`lx1-gemini-3-pro`](https://layerx1.com/models/lx1-gemini-3-pro) | 1M      | \$2         | \$12         | Tools, Reasoning, Vision | Preview      |
| [`lx1-gpt-5.4`](https://layerx1.com/models/lx1-gpt-5.4)           | 400K    | \$1.25      | \$10         | Tools, Reasoning, Vision | Preview      |
| [`lx1-gpt-5.5`](https://layerx1.com/models/lx1-gpt-5.5)           | 400K    | \$2.5       | \$15         | Tools, Reasoning, Vision | Preview      |
| [`lx1-inkling`](https://layerx1.com/models/lx1-inkling)           | 1M      | \$1         | \$4.05       | Tools, Reasoning, Vision | Preview      |
| [`lx1-kimi-k3`](https://layerx1.com/models/lx1-kimi-k3)           | 1M      | \$3         | \$15         | Tools, Reasoning, Vision | Preview      |
| [`lx1-opus-4.7`](https://layerx1.com/models/lx1-opus-4.7)         | 1M      | \$5         | \$25         | Tools, Reasoning, Vision | Preview      |
| [`lx1-opus-5`](https://layerx1.com/models/lx1-opus-5)             | 1M      | \$5         | \$25         | Tools, Reasoning, Vision | Live         |
| [`lx1-qwen3.7-max`](https://layerx1.com/models/lx1-qwen3.7-max)   | 1M      | \$2.5       | \$7.5        | Tools, Reasoning         | Preview      |

* `lx1-fable-5` — The narrative flagship — deepest creative and long-form reasoning. Max plan only.
* `lx1-gemini-3-pro` — Frontier scale — a 1M-token window and strong multimodal reasoning.
* `lx1-gpt-5.4` — The prior GPT-5 flagship — most of 5.5's strength for less.
* `lx1-gpt-5.5` — Frontier generalist — broad, sharp, and steady on long tool chains.
* `lx1-inkling` — Thinking Machines' frontier debut — text, images, and audio in one model.
* `lx1-kimi-k3` — Moonshot's flagship — deep reasoning, vision, and a 1M-token window.
* `lx1-opus-4.7` — Prior Opus flagship — frontier reasoning, pinned in place.
* `lx1-opus-5` — The frontier ceiling — deepest reasoning and vision for the hardest problems. Pro and Max plans.
* `lx1-qwen3.7-max` — The current Qwen flagship — frontier scale with a 1M-token window.

## Premium

The ceiling — for the steps where nothing else will do.

| Model                                                         | Context | Input /Mtok | Output /Mtok | Capabilities             | Availability |
| ------------------------------------------------------------- | ------- | ----------- | ------------ | ------------------------ | ------------ |
| [`lx1-grok-4.3`](https://layerx1.com/models/lx1-grok-4.3)     | 1M      | \$1.25      | \$2.5        | Tools, Reasoning         | Live         |
| [`lx1-haiku-4.5`](https://layerx1.com/models/lx1-haiku-4.5)   | 200K    | \$1         | \$5          | Tools, Reasoning, Vision | Preview      |
| [`lx1-sonnet-4.6`](https://layerx1.com/models/lx1-sonnet-4.6) | 200K    | \$3         | \$15         | Tools, Reasoning, Vision | Live         |
| [`lx1-sonnet-5`](https://layerx1.com/models/lx1-sonnet-5)     | 1M      | \$3         | \$15         | Tools, Reasoning, Vision | Live         |

* `lx1-grok-4.3` — Deep reasoning over a very large window, at the low end of premium.
* `lx1-haiku-4.5` — The fast Claude — premium-family quality at a fraction of the latency.
* `lx1-sonnet-4.6` — The premium ceiling — top reasoning and vision for the hardest work.
* `lx1-sonnet-5` — The newest Sonnet — near-frontier quality for everyday premium work, on every paid plan.

## Coding

Heavy, high-stakes coding. The main line of a serious session.

| Model                                                                     | Context | Input /Mtok | Output /Mtok | Capabilities     | Availability |
| ------------------------------------------------------------------------- | ------- | ----------- | ------------ | ---------------- | ------------ |
| [`lx1-deepseek-v4-pro`](https://layerx1.com/models/lx1-deepseek-v4-pro)   | 1M      | \$1.32      | \$3.96       | Tools, Reasoning | Live         |
| [`lx1-glm-5`](https://layerx1.com/models/lx1-glm-5)                       | 200K    | \$1         | \$3.2        | Tools, Reasoning | Live         |
| [`lx1-glm-5.2`](https://layerx1.com/models/lx1-glm-5.2)                   | 131K    | \$1.4       | \$4.4        | Tools, Reasoning | Live         |
| [`lx1-kimi-k2.7-code`](https://layerx1.com/models/lx1-kimi-k2.7-code)     | 131K    | \$0.95      | \$4          | Tools, Reasoning | Live         |
| [`lx1-longcat-2`](https://layerx1.com/models/lx1-longcat-2)               | 1M      | \$0.75      | \$2.95       | Tools, Reasoning | Live         |
| [`lx1-qwen3-coder-480b`](https://layerx1.com/models/lx1-qwen3-coder-480b) | 131K    | \$0.45      | \$1.8        | Tools            | Live         |
| [`lx1-qwen3-max`](https://layerx1.com/models/lx1-qwen3-max)               | 262K    | \$1.2       | \$6          | Tools, Reasoning | Preview      |

* `lx1-deepseek-v4-pro` — Agentic coding flagship — thinks out loud, and holds a million tokens while it does.
* `lx1-glm-5` — Fast, reliable coding flagship for everyday heavy work.
* `lx1-glm-5.2` — Highest-quality GLM. Flagship tuned for quality over raw speed — higher, variable latency.
* `lx1-kimi-k2.7-code` — Coding-specialist flagship. Quality-first; higher, variable latency.
* `lx1-longcat-2` — Meituan's flagship MoE — a 1M-token window with an unusually deep cached-input discount.
* `lx1-qwen3-coder-480b` — Heavy coding flagship — large MoE built for complex code.
* `lx1-qwen3-max` — The prior Qwen flagship — a heavyweight that codes exceptionally well.

## Reasoning

Models that think before they answer — analysis, planning, hard problems.

| Model                                                                     | Context | Input /Mtok | Output /Mtok | Capabilities             | Availability |
| ------------------------------------------------------------------------- | ------- | ----------- | ------------ | ------------------------ | ------------ |
| [`lx1-deepseek-v3.2`](https://layerx1.com/models/lx1-deepseek-v3.2)       | 131K    | \$0.57      | \$1.71       | Tools, Reasoning         | Live         |
| [`lx1-ernie-x1`](https://layerx1.com/models/lx1-ernie-x1)                 | 128K    | \$0.28      | \$1.1        | Tools, Reasoning         | Preview      |
| [`lx1-hunyuan-t1`](https://layerx1.com/models/lx1-hunyuan-t1)             | 200K    | \$0.14      | \$0.55       | Tools, Reasoning         | Preview      |
| [`lx1-kimi-k2-thinking`](https://layerx1.com/models/lx1-kimi-k2-thinking) | 262K    | \$0.6       | \$2.5        | Tools, Reasoning         | Live         |
| [`lx1-minimax-m2.5`](https://layerx1.com/models/lx1-minimax-m2.5)         | 197K    | \$0.3       | \$1.2        | Tools, Reasoning         | Live         |
| [`lx1-nemotron-3-ultra`](https://layerx1.com/models/lx1-nemotron-3-ultra) | 202K    | \$0.6       | \$2.4        | Tools, Reasoning         | Preview      |
| [`lx1-qwen3-235b`](https://layerx1.com/models/lx1-qwen3-235b)             | 262K    | \$0.22      | \$0.88       | Tools, Reasoning         | Live         |
| [`lx1-qwen3.5-397b`](https://layerx1.com/models/lx1-qwen3.5-397b)         | 262K    | \$0.6       | \$3.6        | Tools, Reasoning         | Preview      |
| [`lx1-qwen3.8-max`](https://layerx1.com/models/lx1-qwen3.8-max)           | 992K    | \$2         | \$6          | Tools, Reasoning, Vision | Live         |
| [`lx1-step-3`](https://layerx1.com/models/lx1-step-3)                     | 256K    | \$0.57      | \$1.42       | Tools, Reasoning, Vision | Preview      |

* `lx1-deepseek-v3.2` — Strong reasoning. Best on open-ended analysis, not strict tool loops.
* `lx1-ernie-x1` — Baidu's reasoning specialist — deep deliberation at a low price.
* `lx1-hunyuan-t1` — Tencent's reasoning model — strong long-form thinking, very cheap.
* `lx1-kimi-k2-thinking` — Extended reasoning; budget output tokens for its hidden chain-of-thought.
* `lx1-minimax-m2.5` — Cheap reasoning with a large context window.
* `lx1-nemotron-3-ultra` — The top Nemotron — 550B of deliberate reasoning at a mid-tier price.
* `lx1-qwen3-235b` — Big reasoning model at a cheap-tier price — standout value.
* `lx1-qwen3.5-397b` — Qwen's biggest open-weight reasoner — flagship thinking, mid-tier price.
* `lx1-qwen3.8-max` — Flagship reasoning with images and a near-million-token window.
* `lx1-step-3` — StepFun's multimodal reasoner — thinks, sees, and calls tools.

## General purpose

Capable generalists priced to carry an agent's daily traffic.

| Model                                                                               | Context | Input /Mtok | Output /Mtok | Capabilities             | Availability |
| ----------------------------------------------------------------------------------- | ------- | ----------- | ------------ | ------------------------ | ------------ |
| [`lx1-deepseek-v4-flash`](https://layerx1.com/models/lx1-deepseek-v4-flash)         | 1M      | \$0.44      | \$1.32       | Tools, Reasoning         | Live         |
| [`lx1-ernie-5.1`](https://layerx1.com/models/lx1-ernie-5.1)                         | 128K    | \$0.59      | \$2.65       | Tools, Vision            | Preview      |
| [`lx1-gemini-3-flash`](https://layerx1.com/models/lx1-gemini-3-flash)               | 1M      | \$0.5       | \$3          | Tools, Reasoning, Vision | Preview      |
| [`lx1-gemma-4-31b`](https://layerx1.com/models/lx1-gemma-4-31b)                     | 256K    | \$0.14      | \$0.4        | Tools, Reasoning         | Live         |
| [`lx1-glm-4.7`](https://layerx1.com/models/lx1-glm-4.7)                             | 200K    | \$0.6       | \$2.2        | Tools, Reasoning         | Preview      |
| [`lx1-gpt-oss-120b`](https://layerx1.com/models/lx1-gpt-oss-120b)                   | 128K    | \$0.35      | \$0.75       | Tools, Reasoning         | Live         |
| [`lx1-hunyuan-hy3`](https://layerx1.com/models/lx1-hunyuan-hy3)                     | 262K    | \$0.14      | \$0.58       | Tools, Reasoning         | Preview      |
| [`lx1-hunyuan-turbos`](https://layerx1.com/models/lx1-hunyuan-turbos)               | 200K    | \$0.11      | \$0.28       | Tools                    | Preview      |
| [`lx1-kimi-k2.6`](https://layerx1.com/models/lx1-kimi-k2.6)                         | 262K    | \$0.95      | \$4          | Tools, Reasoning, Vision | Preview      |
| [`lx1-llama-3.3-70b`](https://layerx1.com/models/lx1-llama-3.3-70b)                 | 131K    | \$0.9       | \$0.9        | Tools                    | Preview      |
| [`lx1-minimax-m3`](https://layerx1.com/models/lx1-minimax-m3)                       | 1M      | \$0.3       | \$1.2        | Tools, Reasoning, Vision | Preview      |
| [`lx1-mistral-large-3-675b`](https://layerx1.com/models/lx1-mistral-large-3-675b)   | 262K    | \$0.5       | \$1.5        | Tools                    | Live         |
| [`lx1-nemotron-3-120b`](https://layerx1.com/models/lx1-nemotron-3-120b)             | 256K    | \$0.5       | \$1.5        | Tools, Reasoning         | Live         |
| [`lx1-nemotron-super-3-120b`](https://layerx1.com/models/lx1-nemotron-super-3-120b) | 262K    | \$0.15      | \$0.65       | Tools, Reasoning         | Live         |
| [`lx1-qwen3-next-80b`](https://layerx1.com/models/lx1-qwen3-next-80b)               | 262K    | \$0.14      | \$1.2        | Tools                    | Live         |
| [`lx1-qwen3-vl-235b`](https://layerx1.com/models/lx1-qwen3-vl-235b)                 | 262K    | \$0.4       | \$1.6        | Tools, Vision            | Preview      |
| [`lx1-qwen3.7-plus`](https://layerx1.com/models/lx1-qwen3.7-plus)                   | 1M      | \$0.4       | \$1.6        | Tools, Reasoning         | Preview      |
| [`lx1-qwen3.8-27b`](https://layerx1.com/models/lx1-qwen3.8-27b)                     | 262K    | \$0.45      | \$3.2        | Tools, Reasoning, Vision | Live         |

* `lx1-deepseek-v4-flash` — Default. The fast half of the V4 line — a million-token window at everyday prices.
* `lx1-ernie-5.1` — Baidu's flagship generalist — broad knowledge with vision.
* `lx1-gemini-3-flash` — Google's fast frontier model — 1M context, multimodal, cheap.
* `lx1-gemma-4-31b` — Google's open workhorse — reasoning and a 256K window near the price floor.
* `lx1-glm-4.7` — The GLM workhorse — flagship instincts at an everyday price.
* `lx1-gpt-oss-120b` — Strong general-purpose agent model with fast responses. Reachable by name.
* `lx1-hunyuan-hy3` — Tencent's newest generalist — reasoning and tools near the price floor.
* `lx1-hunyuan-turbos` — Tencent's fast generalist — quick answers at a rock-bottom price.
* `lx1-kimi-k2.6` — Kimi's vision generalist — thinks when asked, sees what you show it.
* `lx1-llama-3.3-70b` — Meta's dependable open workhorse — a known quantity everywhere.
* `lx1-minimax-m3` — MiniMax's frontier agent model — 1M context and vision at a workhorse price.
* `lx1-mistral-large-3-675b` — Large general-purpose model, fast and capable.
* `lx1-nemotron-3-120b` — Hybrid MoE, strong on multi-agent, 256K context.
* `lx1-nemotron-super-3-120b` — Strong all-round workhorse with a very large context.
* `lx1-qwen3-next-80b` — Efficient workhorse — big context at a low price.
* `lx1-qwen3-vl-235b` — Affordable eyes — a 235B vision model at workhorse money.
* `lx1-qwen3.7-plus` — Qwen's balanced mid-tier — a 1M-token window at an everyday price.
* `lx1-qwen3.8-27b` — The compact Qwen 3.8 — vision, tools, and reasoning in a 27B dense model.

## Everyday coding

Everyday coding hands for routine changes and fast loops.

| Model                                                                     | Context | Input /Mtok | Output /Mtok | Capabilities     | Availability |
| ------------------------------------------------------------------------- | ------- | ----------- | ------------ | ---------------- | ------------ |
| [`lx1-devstral-2-123b`](https://layerx1.com/models/lx1-devstral-2-123b)   | 262K    | \$0.4       | \$2          | Tools            | Live         |
| [`lx1-kat-coder-pro`](https://layerx1.com/models/lx1-kat-coder-pro)       | 256K    | \$0.3       | \$1.2        | Tools            | Preview      |
| [`lx1-kimi-k2.5`](https://layerx1.com/models/lx1-kimi-k2.5)               | 262K    | \$0.6       | \$3          | Tools            | Live         |
| [`lx1-minimax-m2.7`](https://layerx1.com/models/lx1-minimax-m2.7)         | 205K    | \$0.3       | \$1.2        | Tools, Reasoning | Preview      |
| [`lx1-qwen3-coder-30b`](https://layerx1.com/models/lx1-qwen3-coder-30b)   | 262K    | \$0.15      | \$0.6        | Tools            | Live         |
| [`lx1-qwen3-coder-next`](https://layerx1.com/models/lx1-qwen3-coder-next) | 262K    | \$0.5       | \$1.2        | Tools            | Live         |

* `lx1-devstral-2-123b` — Coding-specialist tuned for software tasks.
* `lx1-kat-coder-pro` — Kuaishou's coding specialist — direct edits, no reasoning overhead.
* `lx1-kimi-k2.5` — Fast coding-general model.
* `lx1-minimax-m2.7` — MiniMax's coding workhorse — agentic edits at a budget rate.
* `lx1-qwen3-coder-30b` — Cheap coding offload for routine changes.
* `lx1-qwen3-coder-next` — Balanced coding model with a large context.

## Long context

Huge context at small-model prices — for the jobs that eat tokens.

| Model                                                               | Context | Input /Mtok | Output /Mtok | Capabilities             | Availability |
| ------------------------------------------------------------------- | ------- | ----------- | ------------ | ------------------------ | ------------ |
| [`lx1-gemma-4-26b`](https://layerx1.com/models/lx1-gemma-4-26b)     | 256K    | \$0.1       | \$0.3        | Tools, Reasoning         | Live         |
| [`lx1-mimo-v2.5`](https://layerx1.com/models/lx1-mimo-v2.5)         | 1M      | \$0.168     | \$0.336      | Tools, Reasoning, Vision | Preview      |
| [`lx1-qwen3.5-flash`](https://layerx1.com/models/lx1-qwen3.5-flash) | 1M      | \$0.1       | \$0.4        | Tools, Reasoning         | Preview      |

* `lx1-gemma-4-26b` — 256K context for the price of a small model.
* `lx1-mimo-v2.5` — Xiaomi's efficiency play — 1M context and vision for pocket change.
* `lx1-qwen3.5-flash` — A million tokens of context at one flat, tiny price.

## Fast

Quick turns, glue steps, dispatch — at all-day-volume prices.

| Model                                                                           | Context | Input /Mtok | Output /Mtok | Capabilities             | Availability |
| ------------------------------------------------------------------------------- | ------- | ----------- | ------------ | ------------------------ | ------------ |
| [`lx1-glm-4.7-flash`](https://layerx1.com/models/lx1-glm-4.7-flash)             | 131K    | \$0.0605    | \$0.4        | Tools, Reasoning         | Live         |
| [`lx1-gpt-oss-20b`](https://layerx1.com/models/lx1-gpt-oss-20b)                 | 128K    | \$0.2       | \$0.3        | Tools, Reasoning         | Live         |
| [`lx1-nemotron-nano-3-30b`](https://layerx1.com/models/lx1-nemotron-nano-3-30b) | 262K    | \$0.06      | \$0.24       | Tools, Reasoning         | Live         |
| [`lx1-qwen-turbo`](https://layerx1.com/models/lx1-qwen-turbo)                   | 98K     | \$0.05      | \$0.2        | Tools                    | Live         |
| [`lx1-step-3.7-flash`](https://layerx1.com/models/lx1-step-3.7-flash)           | 262K    | \$0.2       | \$1.15       | Tools, Reasoning, Vision | Preview      |

* `lx1-glm-4.7-flash` — Near the price floor — GLM-family quality in the budget tier.
* `lx1-gpt-oss-20b` — Smallest and fastest tier.
* `lx1-nemotron-nano-3-30b` — Cheapest tool + reasoning capable model.
* `lx1-qwen-turbo` — The catalog's cheapest chat tokens — quick, direct answers at volume.
* `lx1-step-3.7-flash` — StepFun's quick multimodal — sees, thinks, and answers fast for very little.

## Embeddings

Turn text into vectors — for semantic search, RAG, clustering, and dedupe.

| Model                                                                     | Max input | Input /Mtok | Dimensions | Capabilities | Availability |
| ------------------------------------------------------------------------- | --------- | ----------- | ---------- | ------------ | ------------ |
| [`lx1-bge-base-en`](https://layerx1.com/models/lx1-bge-base-en)           | 1K        | \$0.07      | 768        | Embeddings   | Live         |
| [`lx1-bge-large-en`](https://layerx1.com/models/lx1-bge-large-en)         | 1K        | \$0.21      | 1,024      | Embeddings   | Live         |
| [`lx1-bge-m3`](https://layerx1.com/models/lx1-bge-m3)                     | 8K        | \$0.02      | 1,024      | Embeddings   | Live         |
| [`lx1-bge-small-en`](https://layerx1.com/models/lx1-bge-small-en)         | 1K        | \$0.03      | 384        | Embeddings   | Live         |
| [`lx1-embed-gemma-300m`](https://layerx1.com/models/lx1-embed-gemma-300m) | 2K        | \$0.02      | 768        | Embeddings   | Live         |
| [`lx1-plamo-embed-1b`](https://layerx1.com/models/lx1-plamo-embed-1b)     | 4K        | \$0.02      | 2,048      | Embeddings   | Live         |
| [`lx1-qwen3-embed-0.6b`](https://layerx1.com/models/lx1-qwen3-embed-0.6b) | 8K        | \$0.02      | 1,024      | Embeddings   | Live         |

* `lx1-bge-base-en` — The long-standing default English embedding.
* `lx1-bge-large-en` — The most accurate English embedding in the catalog.
* `lx1-bge-m3` — BAAI's versatile embedding — multilingual, multi-granularity.
* `lx1-bge-small-en` — 384 dimensions — the smallest index and the fastest search.
* `lx1-embed-gemma-300m` — Compact Gemma-family embedding with a 2K input window.
* `lx1-plamo-embed-1b` — Japanese-specialist embedding — the widest vector in the catalog.
* `lx1-qwen3-embed-0.6b` — Multilingual retrieval with an 8K input window.