Skip to main content
Corti Models exposes four variants that combine two dimensions — model tier and reasoning mode — so you can balance capability, speed, and cost for each use case.
With reasoningInstant (no reasoning)
Frontiercorti-s1corti-s1-instant
Efficientcorti-s1-minicorti-s1-mini-instant
Corti also offers access to OpenAI GPT models on request, at the same price as OpenAI, so you can mix and match models from a single provider.

​
Model tiers

corti-s1 family

Corti’s frontier-tier model. Choose it for complex reasoning, difficult coding tasks, and multi-step problems where quality is the priority.

corti-s1-mini family

An efficient-tier model that retains strong capability at roughly half the price. Well-suited to high-volume or latency-sensitive workloads.

​
Reasoning vs. instant

Standard models produce a chain-of-thought reasoning trace before the final answer. The trace is visible in the reasoning field of chat-completion responses and as structured type: "reasoning" output items in the Responses API. The -instant variants skip this step and return only the answer, making them faster and cheaper per token when you don’t need the reasoning trace.
Choose a reasoning model for complex multi-step problems, debugging, or when you need transparency into the model’s thinking. Choose an -instant variant for straightforward generation, classification, or high-throughput workloads where speed and cost matter more than an auditable thought process.

​
Pricing

Prices are per million tokens.
ModelInputCached inputOutput
corti-s1$2.00$0.20$8.00
corti-s1-instant$2.00$0.20$8.00
corti-s1-mini$1.00$0.10$4.00
corti-s1-mini-instant$1.00$0.10$4.00
Cached input applies when the same prompt prefix is reused across requests. Corti caches those tokens and charges them at a 90% discount, so long conversations and repeated system prompts cost significantly less.

​
Choosing a model

Use corti-s1 for your hardest tasks — complex coding, multi-step analysis, and problems where you want the model’s chain-of-thought alongside the answer.
Use corti-s1-instant when you want the same model’s output quality but don’t need the reasoning trace. Responses arrive faster and consume fewer tokens.
Use corti-s1-mini for moderate tasks that still benefit from reasoning — summarisation, classification, and code generation — at half the price of the frontier-tier model.
Use corti-s1-mini-instant for high-volume, straightforward work — extraction, formatting, simple Q&A — where cost per request is the primary concern.

​
Next steps

Quickstart

Make your first API call with any OpenAI SDK.

API Reference

Explore the Chat Completions and Responses endpoints.