GPT-4.5: API Pricing, Context Window & Benchmarks
GPT-4.5 is a language model from OpenAI, released in February 2025, with multimodal input.
GPT-4.5 is OpenAI's most advanced model, offering improved reasoning, coding, and creative capabilities with faster performance and longer context handling than GPT-4. It features enhanced instruction following, reduced hallucinations, and
GPT-4.5 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for GPT-4.5 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How GPT-4.5 holds up as conversations get longer.
Quality Tracker
GPT-4.5 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
GPT-4.5 pricing
Providers
GPT-4.5 starts at $75.00 per million input tokens and $150 per million output tokens via OpenAI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
| $75.00 | — | $150 | 128.0K/4.1K | 20.00 | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
GPT-4.5 context window
Input and output token limits for GPT-4.5, plus how it ranks on long-context understanding.
GPT-4.5 API
Available from the model provider
GPT-4.5 has an official provider API. It is not currently routed through the LLM Stats gateway.
Read the official API documentationGPT-4.5 latency
GPT-4.5 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
GPT-4.5 examples
Recent arena outputs from GPT-4.5, picked from the highest-ranked matchups.
GPT-4.5 license
GPT-4.5 is a proprietary model available under its provider's product and API terms.
- License
- Proprietary
- Hosted access
Proprietary license - usage restrictions apply
GPT-4.5 resources
Official sources for GPT-4.5: api documentation, official playground, official launch post, source repository.
GPT-4.5 vs other models
The most-compared alternatives to GPT-4.5 are Llama 3.1 405B Instruct, Qwen3 VL 32B Thinking, Sarvam-105B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-4.5
Models ranked just above and below GPT-4.5 by LLM Stats score.
FAQ
Common questions about GPT-4.5.