openai
OpenAI: GPT-4
openai/gpt-4
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter's catalog describes openai/gpt-4 as OpenAI's flagship large-scale language model with broad general knowledge and advanced reasoning. These capabilities are source-reported rather than independently verified in this pack. The description calls it multimodal, although the catalog fields list text-only input and output. Listed controls include tools, response formatting, sampling, seed, stop, and logprobs. The catalog gives a September 2021 knowledge cutoff and contains a coding benchmark entry, while agentic and general-intelligence benchmark fields are empty. An independent model card was not available in the supplied sources.[1]
Strengths
Limitations
- All evidence comes from the OpenRouter catalog; no independent model card was supplied.[1]
- Structured catalog fields list text-only modalities, so other modality support should not be inferred from the description's multimodal label.[1]
- The September 2021 knowledge cutoff is stated, while reasoning, agentic, and general-intelligence benchmark fields are unpopulated.[1]
Where to use it
- Consider it for text-only assistant, drafting, summarization, or question-answering workloads after validating them directly.[1]
- It may suit applications needing catalog-declared tool controls or configurable response formatting.[1]
- Treat coding suitability as a hypothesis to test, since the supplied benchmark evidence is limited to one catalog entry.[1]
Sources
- [1] OpenRouter catalog · OpenAI: GPT-4Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
Specifications
- Model ID
- openai/gpt-4
- Creator
- openai
- Added to OpenRouter
- 28.05.2023
- Context length
- 8,191
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $30 / out $60
- Knowledge cutoff
- 30.09.2021
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | No measurement | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 13.1 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Azure | 8,191 | $30 | $60 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.