Every model, one key.
Flagship models servable through RawLine — every one jailbreak-ready behind a single
OpenAI-compatible key. Search, filter by provider, or pull the live list with prices straight from
GET /v1/models.
| Model | Provider | Best for | Jailbreak |
|---|---|---|---|
| Claude Opus 5.5 | Anthropic | Strongest reasoning and coding | preset-ready |
| Claude Sonnet 5.5 | Anthropic | Flagship all-rounder | preset-ready |
| GPT-6 Astra | OpenAI | Frontier generalist, agentic tasks | preset-ready |
| GPT-6.1 Sol | OpenAI | Latest GPT generation | preset-ready |
| Qwen3.8 Max | Qwen / Alibaba | Top open-weight flagship | preset-ready |
| Muse Spark 1.3 | Meta | Open-weight alternative | preset-ready |
| Claude Haiku 5.5 | Anthropic | Fast and cheap, 1M context | preset-ready |
| Step-5 Preview | StepFun | 1M context preview | preset-ready |
Nothing matches. Try another query, or pull the live list from GET /v1/models.
Only servable models are listed. Unpriced models answer 402 price_not_set — never served free.
Picking one
Hardest problems
Claude Opus 5.5 for reasoning-heavy work, GPT-6.1 Sol for the newest GPT generation.
Daily driver
Claude Sonnet 5.5 for a flagship all-rounder, GPT-6 Astra for agentic pipelines.
Volume work
Claude Haiku 5.5 — fast, cheap, 1M context. Qwen3.8 Max for open-weight.
Long context
Step-5 Preview and Claude Haiku 5.5 both hold 1M tokens of context.
Live list and prices
This page is a static snapshot. The authoritative list — context length, max output, supported parameters and per-token pricing in USD — comes from the API:
curl https://app.rawline.dev/v1/models \
-H "Authorization: Bearer rlk_YOUR_KEY"A model whose providers all lack credentials is omitted from the response. See the API reference for the full field list and error codes.