GPT-4o
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. $2.50 per million input tokens, $10 per million output tokens. 128,000 token context window, maximum output of 16,384 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.
- Input / output price
- $2.50 / $10.00 per 1M
- Context
- 128K tokens
- Released
- May 13, 2024
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure Foundry azure_foundry/gpt-4o | $2.50/M | $10.00/M |
Azure OpenAI azure_openai/gpt-4o | $2.50/M | $10.00/M |
Inference.net inference_net/gpt-4o | $2.50/M | $10.00/M |
OpenAI openai/gpt-4o | $2.50/M | $10.00/M |
OpenRouterRetired openrouter/gpt-4o | $2.50/M | $10.00/M |
Is a provider down? Azure OpenAI status, ChatGPT status, OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $2.50 per 1M
- Average output
- $10.00 per 1M
- Average cache read
- $1.25 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better31tokens/sacross providers
Time to first token
Lower is better0.8sacross providers
Response latency
Lower is better0.9sacross providers
Benchmarks
The Respan Index plus 16 published scores from 7 sources, each linked to where it was published.
16.0/ 100
Respan Index#156 of 176
- 156GPT-4o16.0
- 155NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP416.1
- 157Amazon Nova 2 Lite15.8
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedEpoch AI | 31% | Epoch AI | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 25.1% | Håvard Tveit Ihle | Oct 5, 2026 |
| GSO Opt@1GSO | 0% | GSO | May 30, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 49.2% | Epoch AI | Oct 5, 2026 |
| GPQA DiamondOpenAI | 46% | OpenAI | Apr 14, 2025 |
| Chess PuzzlesEpoch AI | 9% | Epoch AI | Nov 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MATH Level 5Epoch AI | 53.3% | Epoch AI | Oct 5, 2026 |
| AIME 2024OpenAI | 13.1% | OpenAI | Apr 14, 2025 |
| AIME 2025MathArena | 11.7% | MathArena | Sep 17, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 6.4% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 0.4% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLUOpenAI | 85.7% | OpenAI | Apr 14, 2025 |
| SimpleQA VerifiedEpoch AI | 26% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1346 Elo · #155 of 191 | LMArena | Oct 8, 2026 |
| LMArena VisionLMArena | 1162 Elo · #81 of 91 | LMArena | Oct 9, 2026 |
How GPT compares: Claude vs GPT, Gemini vs GPT, DeepSeek vs GPT
Compare GPT-4o: GPT-4o vs GPT-6.2 Astra, GPT-4o vs GPT-6 Astra, GPT-4o vs GPT-6.1 Sol, GPT-4o vs GPT-6.1 Terra, GPT-4o vs GPT-6.2 Sol, GPT-4o vs GPT-6 Sol
Apps
Use GPT-4o in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
GPT-4o FAQ
Short answers, built from the data on this page.
GPT-4o is a model from OpenAI, released on May 13, 2024. GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. $2.50 per million input tokens, $10 per million output tokens. 128,000 token context window, maximum output of 16,384 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analysis.
On the Respan gateway, GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens on every provider, after gateway discounts.
GPT-4o is available through 5 providers: Azure Foundry, Azure OpenAI, Inference.net, OpenAI, and OpenRouter.
GPT-4o accepts up to 128K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "openai/gpt-4o". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
GPT-4o scores 16.0 out of 100 on the Respan Index v1.1, ranking #156 of 176 models. By category: Coding 2.0, Agents 11.1, Reasoning 17.3, Knowledge & language 25.7, and Human preference 38.6. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
GPT-4o has 16 published benchmark scores, including SWE-bench Verified 31%, BALROG 32.3%, and GPQA Diamond 49.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.