Coding-optimized GPT model for repository edits, reviews, and agentic software work
GPT-5-Codex by openai is offered by 10 providers on this page. Its reference price is $1.25 per 1M input tokens and $10.00 per 1M output tokens. The lowest paid channel is OpenCode Zen at $1.07 / $8.50 per 1M, about 1.2× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 24.9 on the Intelligence Index. Against its lowest blended price of $2.93 per 1M, that is roughly 9 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 400,000 tokens, with an output limit of 128,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-09-30.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| OpenCode Zen | Gateway | $1.07 | $8.50 | $0.11 | — | 400,000 | 128,000 | |
| Poe | Gateway | $1.10 | $9.00 | — | — | 400,000 | 128,000 | |
| Jiekou.AI | Gateway | $1.13 | $9.00 | — | — | 400,000 | 128,000 | |
| Abacus | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| Azure | Cloud | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| Azure Cognitive Services | Cloud | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| ZenMux | Gateway | $1.25 | $10.00 | $0.12 | — | 400,000 | 64,000 | |
| Impossibl | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| Vercel AI Gateway | Cloud | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| Helicone | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 / 10 providers expose no reasoning control (reasoning_options: []).
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 38.9 | index | Source ↗ |
| SciCode | — | 40.9 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 37.9 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.