Omni-era GPT for multimodal chat, practical coding, and general assistants
GPT-4o by openai is offered by 25 providers on this page. Public prices are shown for 24 of them. Its official list price is $2.50 per 1M input tokens and $10.00 per 1M output tokens. The lowest paid channel is Cloudflare AI Gateway at $1.25 / $5.00 per 1M, about 2.5× below the list price.
Artificial Analysis rates it 9 on the Intelligence Index. Against its lowest blended price of $2.19 per 1M, that is roughly 4 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 128,000 tokens, with an output limit of 16,384 tokens. It supports 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 2023-09.
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 |
|---|---|---|---|---|---|---|---|---|
| Cloudflare AI Gateway | Cloud | $1.25 | $5.00 | $0.63 | — | 128,000 | 16,384 | |
| Ofox | Gateway | $2.00 | $8.00 | $1.00 | — | 128,000 | 16,384 | |
| NanoGPT | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| Kilo Gateway | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| Abacus | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| 302.AI | Gateway | $2.50 | $10.00 | — | — | 128,000 | 16,384 | |
| OpenRouter | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| Azure | Cloud | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | deprecated |
| Azure Cognitive Services | Cloud | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | deprecated |
| Impossibl | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| OpenAIOfficial | First-party | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
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.
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | Vercel AI Gateway | $4.25 | $17.00 | $2.13 | — |
| fast | OpenAI | $4.25 | $17.00 | $2.13 | — |
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 23.1 | percent correct | 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.