AICraft — host details and model catalog for the known-good-hosts docs

Following up on #6289 as you asked — here are the details for AICraft.

**Host**

| | |
|---|---|
| Base URL | `https://aicraftapi.com/v1` |
| Wire | OpenAI-compatible (`/v1/chat/completions`) |
| API key page | https://aicraftapi.com/dashboard.html |
| Model catalog | `GET https://aicraftapi.com/v1/models` (requires a bearer key) |

**Config**

```toml
provider = "aicraft"

[providers.aicraft]
kind = "openai-compatible"
base_url = "https://aicraftapi.com/v1"
api_key = "sk-..."
model = "claude-4.6-sonnet"
```

**Model names**

`GET /v1/models` is the authority — it currently returns 123 ids. Rather than have you hand-maintain a table that drifts, I'd point the docs lookup at the endpoint. But since you asked, here is the full current catalog verbatim:

Full catalog — 123 model ids (as returned by GET /v1/models, 2026-09-17)

```
MiniMax-M1
anthropic/claude-4.7-opus
anthropic/claude-4.8-opus
anthropic/claude-fable-5
anthropic/claude-fable-5.1
anthropic/claude-opus-5
anthropic/claude-sonnet-5
bytedance/doubao-seed-2-1-pro
bytedance/doubao-seed-2-1-turbo
bytedance/doubao-seedance-2-0-260128
bytedance/doubao-seedance-2-0-fast-260128
bytedance/doubao-seedance-2-0-mini-260615
bytedance/doubao-seedance-2-5-260628
byteplus/dreamina-seedance-2-0-260128
byteplus/dreamina-seedance-2-0-fast-260128
byteplus/dreamina-seedance-2-0-mini-260615
claude-4.5-haiku
claude-4.5-opus
claude-4.5-sonnet
claude-4.6-opus
claude-4.6-sonnet
deepseek-v3
deepseek/deepseek-v3.2-251201
deepseek/deepseek-v4-flash
deepseek/deepseek-v4-flash-20260731
deepseek/deepseek-v4-flash-vision-exp
deepseek/deepseek-v4-pro
deepseek/deepseek-v4-pro-0813
deepseek/deepseek-v4.1-flash
doubao-seed-2.0-code
doubao-seed-2.0-lite
doubao-seed-2.0-mini
doubao-seed-2.0-pro
gemini-2.5-flash
gemini-2.5-flash-image
gemini-2.5-flash-lite
gemini-2.5-pro
gemini-3.0-flash-preview
gemini-3.1-pro-preview
google/gemini-3-pro-image
google/gemini-3.1-flash-image
google/gemini-3.1-flash-lite
google/gemini-3.1-flash-lite-image
google/gemini-3.5-flash
google/gemini-3.5-flash-lite
google/gemini-3.6-flash
google/gemini-3.7-flash
google/gemini-3.8-flash
gpt-oss-120b
kling-v1
kling-v1-5
kling-v2
kling-v2-1
kling-v2-5-turbo
kling-v2-6
kling-v2-new
kling-v3
kling-v3-omni
kling-video-o1
kling-video/kling-3.0-turbo
minimax/minimax-h3
minimax/minimax-h3-max
minimax/minimax-m2.5
minimax/minimax-m2.5-highspeed
minimax/minimax-m2.7
minimax/minimax-m3
moonshotai/kimi-k2.6
moonshotai/kimi-k2.7-code
moonshotai/kimi-k3
openai/gpt-5
openai/gpt-5-mini
openai/gpt-5-nano
openai/gpt-5.2
openai/gpt-5.2-codex
openai/gpt-5.3-codex
openai/gpt-5.4
openai/gpt-5.4-mini
openai/gpt-5.4-nano
openai/gpt-5.5
openai/gpt-5.6-luna
openai/gpt-5.6-sol
openai/gpt-5.6-terra
openai/gpt-6-astra
openai/gpt-image-2
openai/gpt-image-2.5-flare
openai/gpt-image-2.5-sunburst
qwen/qwen3.5-plus
qwen/qwen3.6-27b
qwen/qwen3.6-plus
qwen/qwen3.7-flash
qwen/qwen3.7-max
qwen/qwen3.7-plus
qwen/qwen3.8-flash-next
qwen/qwen3.8-max
qwen3-next-80b-a3b-thinking
qwen3.5-397b-a17b
stepfun/step-3.7-flash
tencent/hy4-preview
veo-3.1-fast-generate-001
veo-3.1-generate-001
vidu/viduq3
viduq1
viduq2
viduq2-pro
viduq2-turbo
viduq3-pro
viduq3-turbo
x-ai/grok-4.1-fast
x-ai/grok-4.1-fast-non-reasoning
x-ai/grok-4.1-fast-reasoning
x-ai/grok-4.2-fast-non-reasoning
x-ai/grok-4.2-fast-reasoning
x-ai/grok-4.2-non-reasoning
x-ai/grok-4.2-reasoning
x-ai/grok-4.3
x-ai/grok-4.5
x-ai/grok-4.6
x-ai/grok-code-fast-1
z-ai/glm-5
z-ai/glm-5.1
z-ai/glm-5.2
z-ai/glm-5.3
z-ai/glm-5.3-flash
```

Start by following issue #6289 and locating the existing known-good-hosts documentation. Add AICraft's base URL, OpenAI-compatible wire format, API-key page, TOML configuration, and guidance to use GET /v1/models as the model catalog authority. Done means the host details and model lookup instructions are documented without requiring a manually maintained model table.

Written by the indexing model from the issue text.