Upgraded codex model optimized for software engineering and agentic coding workflows with steerable reasoning.
OffRail routes requests to the best providers that are able to handle your prompt size and parameters.
Upgraded codex model optimized for software engineering and agentic coding workflows with steerable reasoning. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for GPT-5.2 Codex on OffRail starts at $1.75 per million input tokens and $14.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
GPT-5.2 Codex supports a context window of up to 400,000 tokens on its largest provider deployment.
GPT-5.2 Codex is served by Azure through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
GPT-5.2 Codex supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
GPT-5.2 Codex was released on January 14, 2026.
GPT-5.6 Sol
1,050,000 context$5.00 in / $30.00 out per 1M
GPT-5.6 Terra
1,050,000 context$2.00 in / $12.00 out per 1M
GPT-5.6 Luna
1,050,000 context$0.20 in / $1.20 out per 1M
GPT Realtime 2.1
128,000 context$4.00 in / $24.00 out per 1M
GPT Realtime 2.1 Mini
128,000 context$0.60 in / $2.40 out per 1M
GPT-5.5
1,050,000 context$5.00 in / $30.00 out per 1M