Skip to main content

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
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "openai/gpt-4o".

Read docs

Providers

5 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Azure Foundryazure_foundry/gpt-4o
$2.50/M$10.00/M
Azure OpenAIazure_openai/gpt-4o
$2.50/M$10.00/M
Inference.netinference_net/gpt-4o
$2.50/M$10.00/M
OpenAIopenai/gpt-4o
$2.50/M$10.00/M
OpenRouterRetiredopenrouter/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.

$2.50/MAzure Foundry, Azure OpenAI, Inference.net, OpenAI, and OpenRouter

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 better

31tokens/sacross providers

Faster than 57% of the other 596 models on the gateway

Time to first token

Lower is better

0.8sacross providers

Faster than 79% of the other 153 models on the gateway

Response latency

Lower is better

0.9sacross providers

Faster than 64% of the other 768 models on the gateway

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

176 ranked models. The shaded band is this model's 95% interval, 12.8 to 22.0. NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 and Amazon Nova 2 Lite fall inside it, so the gap is within the margin of error.
GPT-4o by category: Coding 2.0, Agents 11.1, Reasoning 17.3, Knowledge & language 25.7, Human preference 38.6
  1. 156GPT-4o16.0
  2. 155NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP416.1
  3. 157Amazon Nova 2 Lite15.8

Published scores

BenchmarkScore
SWE-bench VerifiedEpoch AI31%
WeirdMLHåvard Tveit Ihle25.1%
GSO Opt@1GSO0%

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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.