Neither wins outright: OpenAI: GPT-5 Codex is the pick when you need to fit long inputs in one request, Pareto 26.9 when you want the newer model.
| Spec | OpenAI: GPT-5 Codex | Pareto 26.9 |
|---|---|---|
| Provider | OpenAI | Unbiased |
| Input price (per 1M tokens) | $1.25 | $2.50 |
| Output price (per 1M tokens) | $10.00 | $7.50 |
| Blended price (3:1 input/output) | $3.44 | $3.75 |
| Cheaper than … of all models we track | 19% | 17% |
| Context window | 400K tokens (~600 pages) | 262K tokens (~393 pages) |
| Larger context than … of all models | 63% | 48% |
| Max output per response | 128K tokens (~96,000 words) | 131K tokens (~98,300 words) |
| Input types | text, image | text, image |
| Output types | text | text |
| Free variant | No | No |
| Listed since | 2025-09-23 | 2026-10-13 |
Monthly cost at list price for five common workloads. Token counts per unit are stated so you can scale them to your own traffic. A workload that does not fit a model's context window is marked rather than priced.
| Workload (per month) | OpenAI: GPT-5 Codex | Pareto 26.9 | Difference |
|---|---|---|---|
| Customer-support chatbot 50,000 conversations — each a 6-turn conversation (1,500 in / 400 out tokens) | $294 | $338 | OpenAI: GPT-5 Codex saves $43.75 |
| RAG search over documents 20,000 questions — each a question answered from ~8 retrieved passages (6,000 in / 500 out tokens) | $250 | $375 | OpenAI: GPT-5 Codex saves $125 |
| Coding / tool-using agent 2,000 tasks — each a multi-step task with tool calls and file context (60,000 in / 6,000 out tokens) | $270 | $390 | OpenAI: GPT-5 Codex saves $120 |
| Batch summarisation 10,000 documents — each a 6,000-word report summarised to a page (8,000 in / 600 out tokens) | $160 | $245 | OpenAI: GPT-5 Codex saves $85.00 |
| Long-document analysis 500 documents — each a 150-page contract or codebase read in one pass (100,000 in / 2,000 out tokens) | $72.50 | $133 | OpenAI: GPT-5 Codex saves $60.00 |
| Capability | OpenAI: GPT-5 Codex | Pareto 26.9 | What it lets you do |
|---|---|---|---|
| Tool / function calling | ✓ Yes | ✓ Yes | call your APIs and run agent loops |
| Structured output (JSON schema) | ✓ Yes | ✓ Yes | return JSON that validates against your schema |
| Reasoning / thinking mode | ✓ Yes | — | spend extra tokens thinking before answering hard problems |
| Image input | ✓ Yes | ✓ Yes | read screenshots, charts and scanned pages |
| Audio input | — | — | take speech or audio directly |
| File / PDF input | — | — | accept documents without your own parsing step |
| Image output | — | — | generate images, not just text |
| Built-in web search | — | — | answer from live web results |
| Seed (reproducible sampling) | ✓ Yes | — | repeat a generation for tests and evals |
| Log-probabilities | — | — | read token confidence for classification and scoring |
From each model's published parameters and input/output types. “—” means not advertised, not proven absent.
Neither wins outright: OpenAI: GPT-5 Codex is the pick when you need to fit long inputs in one request, Pareto 26.9 when you want the newer model. In short: OpenAI: GPT-5 Codex when you need to fit long inputs in one request, you need reasoning / thinking mode, you need seed (reproducible sampling); Pareto 26.9 when you want the newer model.
OpenAI: GPT-5 Codex is cheaper: $3.44 vs $3.75 per 1M tokens at a typical 3:1 input/output mix, 8% less. For 50,000 support conversations a month that is $294 against $338.
OpenAI: GPT-5 Codex costs $1.25 per 1M input tokens and $10.00 per 1M output tokens; Pareto 26.9 costs $2.50 input and $7.50 output. Output tokens are billed separately, so long answers shift the gap.
OpenAI: GPT-5 Codex: 400K tokens, about 600 pages, against 262K (about 393 pages) for Pareto 26.9.
Tool calling — OpenAI: GPT-5 Codex: yes, Pareto 26.9: yes. JSON-schema structured output — OpenAI: GPT-5 Codex: yes, Pareto 26.9: yes.
Yes, both accept image input.
No free variant is listed for either; both are pay-per-token.
OpenAI: GPT-5 Codex can write up to 128K tokens (about 96,000 words) per response; Pareto 26.9 up to 131K (about 98,300 words).
OpenAI: GPT-5 Codex was listed on 2025-09-23; Pareto 26.9 on 2026-10-13.
GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks. The model supports building projects from scratch, feature development, debugging, large-scale refactoring, and code review. Compared to GPT-5, Codex is more steerable, adheres closely to developer instructions, and produces cleaner, higher-quality code outputs. Reasoning effort can be adjusted with the `reasoning.effort` parameter. Read the [docs here](https://openrouter.ai/docs/use-cases/reasoning-tokens#reasoning-effort-level) Codex integrates into developer environments including the CLI, IDE extensions, GitHub, and cloud tasks. It adapts reasoning effort dynamically—providing fast responses for small tasks while sustaining extended multi-hour runs for large projects. The model is trained to perform structured code reviews, catching critical flaws by reasoning over dependencies and validating behavior against tests. It also supports multimodal inputs such as images or screenshots for UI development and integrates tool use for search, dependency installation, and environment setup. Codex is intended specifically for agentic coding applications.
Full OpenAI: GPT-5 Codex specs →Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
Full Pareto 26.9 specs →