GPT-5.1 Codex
As of Oct 4, 2026, the cheapest GPT-5.1 Codex API price is $1.07 per 1M input tokens (OpenCode Zen) and $8.5 per 1M output tokens (OpenCode Zen). GPT-5.1 Codex is offered by 19 providers in the gpt-codex family, reasoning enabled.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked.
| OpenCode Zen | Cheapest$1.07 | Cheapest$8.5 | $0.107 | — | 400k |
| Poe | $1.1 | $9 | $0.11 | — | 400k |
| Jiekou.AI | $1.125 | $9 | — | — | 400k |
| Abacus | $1.25 | $10 | $0.125 | — | 400k |
| AIHubMix | $1.25 | $10 | $0.125 | — | 400k |
| Azure | $1.25 | $10 | $0.125 | — | 400k |
| Azure Cognitive Services | $1.25 | $10 | $0.125 | — | 400k |
| Eden AI | $1.25 | $10 | $0.125 | — | 272k |
| Helicone | $1.25 | $10 | $0.125 | — | 400k |
| Impossibl | $1.25 | $10 | $0.125 | — | 400k |
| Kilo Gateway | $1.25 | $10 | $0.13 | — | 400k |
| DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | — | 400k |
| LLM Gateway | $1.25 | $10 | — | — | 400k |
| NanoGPT | $1.25 | $10 | $0.125 | — | 400k |
| OpenRouter | $1.25 | $10 | $0.13 | — | 400k |
| OrcaRouter | $1.25 | $10 | $0.125 | — | 400k |
| Vercel AI Gateway | $1.25 | $10 | $0.13 | — | 400k |
| Vivgrid | $1.25 | $10 | $0.125 | — | 400k |
| ZenMux | $1.25 | $10 | $0.12 | — | 400k |
GPT-5.1 Codex pricing FAQ
What is the cheapest GPT-5.1 Codex API?
As of Oct 4, 2026, OpenCode Zen has the lowest GPT-5.1 Codex output price at $8.5 per 1M tokens, and OpenCode Zen has the lowest input price at $1.07 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer GPT-5.1 Codex?
19 providers list GPT-5.1 Codex on Sovyron; 19 of them sell it at a metered per-token price.
Is GPT-5.1 Codex free?
No provider in the Sovyron catalog lists a free tier for GPT-5.1 Codex.
What is the context window of GPT-5.1 Codex?
GPT-5.1 Codex supports a 400k-token context window and up to 272k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not.
Estimated
—