The AI arena is free today

Open Superagent
API Provider44 active models1 organization

OpenAI: API pricing, speed & models

OpenAI hosts 44 active AI models, with input pricing from $0.10 per 1M tokens, with median throughput of 233 characters/sec, and P95 time to first token of 3.92s, with 100% success rate over 7 days. Compare OpenAI's API speed, pricing, and reliability against other inference providers.

Image generationVideoFirst-party only
Median throughput233 c/s
Median TTFT1.39s
P95 TTFT3.92s
Success rate (7d)100%
From$0.10 /M tok

Catalog

Type
Price
97 models
Model
GPT-6 Rosalindcache pricing
GPT-6 Rosalindcache pricing
GPT-6 Astra Lawcache pricing
GPT-6 Astra Lawcache pricing
GPT-6.1 Terracache pricing
GPT-6.1 Terracache pricing
GPT-Rosalindcache pricing
GPT-Rosalindcache pricing
GPT-6.1 Solcache pricing
GPT-6.1 Solcache pricing
GPT-6 Lunacache pricing
GPT-6 Lunacache pricing
GPT-6 Solcache pricing
GPT-6 Solcache pricing
GPT-6 Astracache pricing
GPT-6 Astracache pricing
GPT-5.6 Cybercache pricing
GPT-5.6 Cybercache pricing
GPT-5.6 Lunacache pricing
GPT-5.6 Lunacache pricing
GPT-5.6 Terracache pricing
GPT-5.6 Terracache pricing
GPT-5.6 Solcache pricing
GPT-5.6 Solcache pricing
GPT-5.5cache pricing
GPT-5.5cache pricing
GPT-5.450 QPS
GPT-5.450 QPS
GPT-5.2100 QPS
GPT-5.2100 QPS
GPT-5.1100 QPS
GPT-5.1100 QPS
GPT-5 mini200 QPS
GPT-5 mini200 QPS
GPT-4o132 QPS
GPT-4o132 QPS
GPT-4o100 QPS
GPT-4o100 QPS
GPT-4.1100 QPS
GPT-4.1100 QPS
At a glance

OpenAIpricing, performance & catalog

The citable facts about OpenAI's 44 models — sourced from provider APIs and refreshed continuously.

Lowest price
GPT-6 Luna at $0.100 per 1M input tokens
Highest median throughput
GPT-4.1 mini at 421 chars/s
Lowest median TTFT
GPT-5.4 nano at 1.34s
Largest context
GPT-6.1 Terra at 1.1M tokens
Catalog
44 active models from 1 organization

FAQ

Common questions about OpenAI.

What is OpenAI?

OpenAI is an API provider that hosts large language models. Active models: 44; From (input): $0.10 / 1M tok; Median throughput: 233 c/s; Median TTFT: 1.39s; Success rate (7d): 100%.

How many models does OpenAI offer?

OpenAI currently serves 44 active models out of 69 historical offerings on LLM Stats.

What is OpenAI's API pricing?

OpenAI input pricing starts from $0.10 per 1M tokens, with the most expensive offering at $15 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

How fast is OpenAI?

OpenAI delivers a median throughput of 233 characters per second and P95 time to first token of 3.92s across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is OpenAI reliable?

OpenAI has a 100% success rate across 54 API calls in the last 7 days, with a 0% error rate.

Does OpenAI support function calling?

Yes. 66 of 44 models on OpenAI support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does OpenAI support JSON mode and structured output?

Yes. 58 of 44 models on OpenAI support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Does OpenAI offer batch inference?

Yes. 58 of 44 models on OpenAI support batch inference for cheaper, asynchronous workloads.

Does OpenAI support fine-tuning?

Yes. 10 of 44 models on OpenAI support fine-tuning. The Capabilities tab lists which specific models accept fine-tuning jobs.

Does OpenAI support multimodal models?

Yes. OpenAI's catalog includes 44 vision-capable, 20 image generation, 4 audio, and 4 video models. See the Models and Capabilities tabs for the full per-model breakdown.

Whose models does OpenAI host?

OpenAI hosts models from OpenAI. See the Models tab for the full catalog grouped by creator.

How do I start using OpenAI?

Sign up at https://openai.com to get an API key, then call OpenAI's API directly from your application. Most clients work out of the box by pointing the OpenAI SDK at OpenAI's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.