← Model list
GPT-4o (2024-08-06)
openai·openai/gpt-4o-2024-08-06·GA·Closed·gpt series
GPT model for general reasoning, writing, coding, and tool-assisted tasks
At a glance
Official price$2.50 / $10.00 per 1M
Cache read $1.25 · OpenAI
Lowest paid$2.50 / $10.00
OrcaRouter Gateway · 1× spread
Context128,000
Output limit16,384
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF
Knowledge cutoff2023-09
Released / updated2024-08-06 / 2024-08-06
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 7 providers7 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| OrcaRouter | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| NanoGPT | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| OpenRouter | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| OpenAIOfficial | First-party | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| Merge Gateway | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| Eden AI | Gateway | $2.50 | $10.00 | $1.25 | — | 128,000 | 16,384 | |
| Kilo Gateway | Gateway | $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.
Your usage cost
1OrcaRouter$850.00
2NanoGPT$850.00
3OpenRouter$850.00
4OpenAI · Official$850.00
5Merge Gateway$850.00
6Eden AI$850.00
Switch to OrcaRouter to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 23.1 | percent correct | Source ↗ |
| Artificial Analysis Coding Index | — | 16.6 | index | Source ↗ |
| SciCode | — | 33.1 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 8.3 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Related models
RouteLLMsame series$3.00 / $15.00GPT-Realtime-2.1same series$4.00 / $24.00NanoGPT Helpsame series$0 / $0Qwen3 Maxcheaper alternative$0.861 / $3.44Qwen3 235B-A22B Instruct 2507cheaper alternative$1.03 / $3.08Qwen3-Next 80B-A3B Instructcheaper alternative$0.144 / $0.574Qwen3-Coder 30B-A3B Instructcheaper alternative$0.216 / $0.861
Price historyone sample accumulated per data sync
Input listOutput listMin blended