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

# Models

> Every model available on ByteSpike, organized by family. Each model page lists its public price and protocol, and a runnable quickstart.

This is the **model-first** index for ByteSpike. Pick the model you want; the per-model page tells you what it costs, what protocol it speaks, and how to make your first call.

## Claude family

Anthropic's reasoning-and-vision lineup, available via both the Anthropic Messages protocol and the OpenAI Chat Completions API. Cache control, tool use, and thinking blocks pass through transparently.

| Model               | Tier     | Context | Price  | Page                           |
| ------------------- | -------- | ------- | ------ | ------------------------------ |
| `claude-opus-4-8`   | flagship | 200K    | $5/$25 | [→](/models/claude-opus-4-8)   |
| `claude-opus-4-7`   | large    | 200K    | $5/$25 | [→](/models/claude-opus-4-7)   |
| `claude-opus-4-6`   | large    | 200K    | $5/$25 | legacy                         |
| `claude-sonnet-4-6` | mid      | 200K    | $3/$15 | [→](/models/claude-sonnet-4-6) |
| `claude-haiku-4-5`  | small    | 200K    | $1/$5  | [→](/models/claude-haiku-4-5)  |

## GPT family

OpenAI's GPT lineup — Chat Completions for ubiquitous SDK code, Responses for Codex-style clients. Reasoning, structured outputs, web search, and vision all pass through.

| Model          | Tier      | Context | Price       | Page                      |
| -------------- | --------- | ------- | ----------- | ------------------------- |
| `gpt-5-5`      | flagship  | 128K    | $5/$30      | [→](/models/gpt-5-5)      |
| `gpt-5-4`      | mid       | 128K    | $2.50/$15   | [→](/models/gpt-5-4)      |
| `gpt-5-4-mini` | small-mid | 128K    | $0.75/$4.50 | [→](/models/gpt-5-4-mini) |

## Gemini family

Google's Gemini lineup, exposed through the OpenAI Chat Completions API. `gemini-3-5-flash` is the fast, multimodal mid-tier with a 1M-token context window. Additional Gemini Flash, Flash-Lite, and Pro tiers are live in the [catalog](https://bytespike.ai/models).

| Model              | Tier | Context | Price    | Page                          |
| ------------------ | ---- | ------- | -------- | ----------------------------- |
| `gemini-3-5-flash` | mid  | 1M      | $1.50/$9 | [→](/models/gemini-3-5-flash) |

## DeepSeek family

The DeepSeek lineup via DeepSeek's own HTTP API. V4 is dual-protocol (Chat Completions + Anthropic Messages). Vision **not** exposed on the HTTP API today.

| Model               | Tier      | Context | Price        | Page                           |
| ------------------- | --------- | ------- | ------------ | ------------------------------ |
| `deepseek-v4-flash` | small-mid | 64K     | $0.14/$0.28  | [→](/models/deepseek-v4-flash) |
| `deepseek-v4-pro`   | flagship  | 64K     | $0.435/$0.87 | [→](/models/deepseek-v4-pro)   |

## 字节跳动 / 豆包 (Doubao) family

ByteDance's Doubao lineup — strong on Chinese-language tasks, vision-capable. Served over the OpenAI Chat Completions API.

| Model                 | Tier     | Page                             |
| --------------------- | -------- | -------------------------------- |
| `doubao-seed-2.0-pro` | flagship | [→](/models/doubao-seed-2-0-pro) |

## Zhipu / 智谱 (GLM) family

Zhipu's GLM lineup — Chinese-LLM general chat with vision support. Served over the OpenAI Chat Completions API.

| Model     | Tier     | Page               |
| --------- | -------- | ------------------ |
| `glm-5-1` | flagship | [→](/models/glm-5) |

## Moonshot / Kimi family

Moonshot's Kimi lineup — long-context Chinese-LLM. Served over the OpenAI Chat Completions API.

| Model       | Tier     | Context | Page                   |
| ----------- | -------- | ------- | ---------------------- |
| `kimi-k2-6` | flagship | 128K    | [→](/models/kimi-k2-6) |

## MiniMax family

MiniMax's lineup — competitive Chinese-LLM general chat. Served over the OpenAI Chat Completions API.

| Model          | Tier     | Context | Page                      |
| -------------- | -------- | ------- | ------------------------- |
| `minimax-m2-7` | flagship | 128K    | [→](/models/minimax-m2-7) |

## Image and video

Image and video models live under their own protocol surfaces (`/v1/images/generations` for image, `/v1/tasks/submit` for async video). Per-model pages with current per-call rates live in [/api-reference/image](/api-reference/image) and [/api-reference/video](/api-reference/video) today; they'll migrate into `/models/` in a follow-up.

## DOSIA recommended paths

If you're calling ByteSpike from DOSIA, two protocol surfaces matter — and each one has a recommended primary model plus cheaper fallbacks.

| DOSIA mode                                     | Protocol                | Primary                                          | Cost-optimized fallback                        | Region-of-China primary                                                   |
| ---------------------------------------------- | ----------------------- | ------------------------------------------------ | ---------------------------------------------- | ------------------------------------------------------------------------- |
| **Agent** (tool use, thinking, cache\_control) | Anthropic Messages      | [`claude-sonnet-4-6`](/models/claude-sonnet-4-6) | [`claude-haiku-4-5`](/models/claude-haiku-4-5) | [`deepseek-v4-pro`](/models/deepseek-v4-pro) (anthropic-compat)           |
| **Chat** (general Q\&A, drafting)              | OpenAI Chat Completions | [`gpt-5-4`](/models/gpt-5-4)                     | [`gpt-5-4-mini`](/models/gpt-5-4-mini)         | [`deepseek-v4-flash`](/models/deepseek-v4-flash) or `doubao-seed-2.0-pro` |

For DOSIA Cloud Enterprise admins building permission templates:

* **Global edition** preset → unlock `claude-sonnet-4-6`, `claude-opus-4-8`, `gpt-5-4`, `gpt-5-4-mini`, `gpt-5-5`, `gemini-3-5-flash`. Default to Anthropic for Agent, OpenAI for Chat.
* **China edition** preset → unlock `deepseek-v4-pro`, `deepseek-v4-flash`, `doubao-seed-2.0-pro`, `glm-5-1`, `kimi-k2-6`, `minimax-m2-7`. Default to `deepseek-v4-pro` for Agent (anthropic-compat), `doubao-seed-2.0-pro` for Chat.

Both presets are admin-defined in the [DOSIA Cloud Console](https://console.bytespike.ai); members never have to pick a model unless they want to override.

## How to read a model page

Each page is the same shape:

1. **Quickstart** — a runnable request against the model via its primary protocol.
2. **Capabilities** — what the model itself supports (vision, tools, reasoning, JSON mode, streaming).
3. **When to use** — opinionated guidance.
4. **Next** — links to related models.

Same shape across families so you can scan side-by-side.

## Next

* [Endpoint types](/concepts/endpoints) — the eight request shapes ByteSpike accepts
* [Pricing](/pricing) — the per-model public rate card