Ottili models
Every model. One catalog.
OpenAI-compatible models on one API — including Ottili Auto, the adaptive router that picks Vale or Cairn per request. Model cards below follow the same shape used for provider readiness reviews (OpenRouter-style): pricing, context, capabilities and health.
Ottili Vale 1.2
ottili/vale-1.2Efficient tier for everyday developer and business work — fast and cost-effective.
Input
$0.20/1M
Output
$0.40/1M
Context
1000K
Max output
384K
Best for
- Small code fixes
- UI changes
- Quick debugging
- Structured / JSON output
- Docs generation
- Lightweight automation
curl https://ai.ottili.one/api/v1/chat/completions \
-d '{"model":"ottili/vale-1.2",...}'Ottili Cairn 1.2
ottili/cairn-1.2Premium price-performance tier for serious software and analysis work.
Input
$0.65/1M
Output
$1.30/1M
Context
1000K
Max output
384K
Best for
- Large repo analysis
- Architecture planning
- Multi-step coding
- Complex debugging
- Production readiness review
- Security review
curl https://ai.ottili.one/api/v1/chat/completions \
-d '{"model":"ottili/cairn-1.2",...}'Ottili Auto
ottili/autoAdaptive router that picks Vale or Cairn per request — Vale for everyday work, Cairn for serious engineering.
Input
$0.43/1M
Output
$0.85/1M
Context
1000K
Max output
384K
Best for
- Hands-off model selection
- Mixed simple + complex workloads
- Everyday fixes routed to Vale
- Heavy tasks routed to Cairn
- Agentic / multi-step routed to Cairn
- Reasoning tasks routed to Cairn
curl https://ai.ottili.one/api/v1/chat/completions \
-d '{"model":"ottili/auto",...}'Ottili Spire 1.2
ottili/spire-1.2Reserved flagship of the Ottili AI Platform — not yet available.
Input
$0.00/1M
Output
$0.00/1M
Context
1000K
Max output
384K
Best for
- Coming soon
- Reserved for the Ottili flagship model
- Pricing published at launch
- Not yet purchasable
curl https://ai.ottili.one/api/v1/chat/completions \
-d '{"model":"ottili/spire-1.2",...}'Side by side
Compare
| Spec | Ottili Vale 1.2 | Ottili Cairn 1.2 | Ottili Auto | Ottili Spire 1.2 |
|---|---|---|---|---|
| Model ID | ottili/vale-1.2 | ottili/cairn-1.2 | ottili/auto | ottili/spire-1.2 |
| Context window | 1000K tokens | 1000K tokens | 1000K tokens | 1000K tokens |
| Max output tokens | 384K tokens | 384K tokens | 384K tokens | 384K tokens |
| Input price | $0.20 / 1M tokens | $0.65 / 1M tokens | $0.43 / 1M tokens | $0.00 / 1M tokens |
| Output price | $0.40 / 1M tokens | $1.30 / 1M tokens | $0.85 / 1M tokens | $0.00 / 1M tokens |
| Streaming | Yes (SSE) | Yes (SSE) | Yes (SSE) | Yes (SSE) |
| Tool calling / JSON mode | Yes | Yes | Yes | Yes |
| Auth | API key (otk_live_ / otk_test_) | API key (otk_live_ / otk_test_) | API key (otk_live_ / otk_test_) | API key (otk_live_ / otk_test_) |
| Compatibility | OpenAI-compatible /v1/chat/completions | OpenAI-compatible /v1/chat/completions | OpenAI-compatible /v1/chat/completions | OpenAI-compatible /v1/chat/completions |
Less infrastructure.
More intelligence.
Integrate Ottili AI Platform with a few lines of code and run production workloads through one unified, OpenAI-compatible interface.