Yes—Nvidia officially announced those U.S. desktop launch prices, but they were announced on January 6, 2025, not as a permanent promise of today’s retail pricing. The GeForce RTX 5090 launched at a $1,999 starting MSRP, the RTX 5080 at $999, and the RTX 5070 Ti at $749. Nvidia also launched an RTX 5070 at $549. “Starting at” means an entry price for a Founders Edition or base partner card, not a guarantee that every model would sell for that amount.
Official RTX 50-series desktop prices
Nvidia announced the prices at CES on January 6, 2025. The RTX 5090 and RTX 5080 were scheduled for January 30, 2025; the RTX 5070 Ti and RTX 5070 were listed as starting in February 2025. These are U.S.-dollar launch MSRPs, generally before sales tax, and do not establish current global or retailer pricing. Nvidia’s announcement and its RTX 5090/5080 launch notice provide the official dates and prices.
| Desktop GPU | U.S. launch MSRP | Announced availability | VRAM |
|---|---|---|---|
| GeForce RTX 5090 | $1,999 | January 30, 2025 | 32GB GDDR7 |
| GeForce RTX 5080 | $999 | January 30, 2025 | 16GB GDDR7 |
| GeForce RTX 5070 Ti | $749 | Starting February 2025 | 16GB GDDR7 |
| GeForce RTX 5070 | $549 | Starting February 2025 | 12GB GDDR7 |
For a historical launch comparison, Tom’s Hardware reported that the RTX 5080 inherited the RTX 4080 Super’s $999 launch price. That positioning alone does not prove better value; performance, memory capacity, power use and availability determine value. Tom’s Hardware, January 7, 2025.
What “starting at” means in practice
Nvidia’s wording applies to an entry configuration, not every board on the market. Founders Edition cards and the least expensive add-in-board models may target the base price, while factory-overclocked, liquid-cooled, white, compact or heavily customized versions commonly cost more. Nvidia identified partners including ASUS, Colorful, GIGABYTE, MSI, PNY and ZOTAC, alongside limited Founders Edition availability. Nvidia’s launch details.
Recommended Free Tools
#1 Best Overall
- AI Performance: 772 AI TOPS
- OC mode: 2580 MHz Default mode: 2550 MHz(Boost clock)
- Powered by the NVIDIA Blackwell architecture and DLSS 4
- SFF-Ready Enthusiast GeForce Card
- Axial-tech fans feature a smaller fan hub that facilitates longer blades and a barrier ring that increases downward air pressure
- A partner RTX 5090 above $1,999 is not automatically contradicting Nvidia’s announcement.
- U.S. advertised prices usually exclude state and local sales tax.
- Currency conversion does not account for regional tax, duties, distribution costs or local pricing policy.
- Shortages, demand and reseller activity can push prices far above MSRP.
Before buying, compare the exact board model, cooler, dimensions, power connector, warranty and retailer return policy—not just the GPU name.
Hardware differences that explain the price gaps
| Specification | RTX 5090 | RTX 5080 | RTX 5070 Ti |
|---|---|---|---|
| Architecture / GPU | Blackwell / GB202 | Blackwell / GB203 | Blackwell / GB203 |
| CUDA cores | 21,760 | 10,752 | 8,960 |
| VRAM | 32GB GDDR7 | 16GB GDDR7 | 16GB GDDR7 |
| Memory bus | 512-bit | 256-bit | 256-bit |
| Memory bandwidth | 1,792GB/s | 960GB/s | 896GB/s |
| Total board power | 575W | 360W | 300W |
| Launch MSRP | $1,999 | $999 | $749 |
Specifications are from Nvidia’s announcement and Blackwell architecture documentation.
Rank #2
- [3352 AI TOPS, 5th Gen Tensor Cores, AI Content Creation] Built for AI-assisted photo and video workflows including upscaling, denoise, background removal, masking, and generative AI creation for faster creator productivity.
- [32GB GDDR7 VRAM, Local LLM Inference, Larger Models] Run local LLM inference and on-device AI tools with massive VRAM headroom for larger models, longer context, and heavier multitasking across AI and creator apps.
- [28 Gbps, 512-bit, 21760 CUDA Cores] High-throughput next-gen memory and core resources for demanding creator projects, complex timelines, large assets, and GPU-accelerated ML experimentation and inference pipelines.
- [Quad-Fan Force, Vapor Chamber, Phase-Change Thermal Pad] Designed for sustained performance under heavy loads with quad-fan cooling, a patented vapor chamber, and a phase-change GPU thermal pad to help lower temps and reduce hotspots.
- [DP 2.1b x3, HDMI 2.1b x2, Bundle GPU Holder] Multi-display ready with up to 4 displays and up to 7680 x 4320 max digital resolution, plus an included GPU Holder to help reduce GPU sag and improve long-term build stability.
RTX 5090: the no-compromise option
The 5090’s 32GB frame buffer, 512-bit bus and 1,792GB/s bandwidth target high-refresh 4K gaming, demanding ray tracing, local generative-AI work, 3D rendering and other professional workloads. Nvidia advertised up to twice the RTX 4090’s performance when Blackwell features and DLSS 4 are used; that is not a universal native-rendering guarantee. Its 575W board power can require a higher-capacity modern power supply, stronger case airflow, adequate cooling and careful connector routing.
RTX 5080: high-end 4K at half the launch price
With 10,752 CUDA cores, 16GB of GDDR7 and 960GB/s bandwidth, the 5080 is aimed at high-settings 4K gaming and ray tracing without the 5090’s cost and power demand. Nvidia claimed up to twice the RTX 4080’s performance with Blackwell and DLSS 4. The 16GB capacity may constrain some future games, large texture packs, professional scenes and AI workloads.
Do these 3 things before closing this tab:
1Fix the driver behind crashes, sound loss and screen glitches2Clear out junk files and repair common Windows errors3Scan for outdated or missing drivers - takes under a minuteRank #3
- Powered by the NVIDIA Blackwell architecture and DLSS 4. System Requirements: Minimum 850W PSU with 16-pin 12V-2x6 (12VHPWR) connector required. Verify before purchasing.
- Military-grade components deliver rock-solid power and longer lifespan for ultimate durability. Compatibility: 348mm (13.7") length, 3.6 slots, 4.3 lbs. Confirm case clearance and slot spacing. GPU bracket included.
- Protective PCB coating helps protect against short circuits caused by moisture, dust, or debris
- 3.6-slot design with massive fin array optimized for airflow from three Axial-tech fans
- Phase-change GPU thermal pad helps ensure optimal thermal performance and longevity, outlasting traditional thermal paste for graphics cards under heavy loads
RTX 5070 Ti: the practical middle ground
The 5070 Ti combines 8,960 CUDA cores, 16GB GDDR7, 896GB/s bandwidth and 300W board power. It is positioned for high-refresh 1440p and more affordable 4K gaming. Its 16GB capacity matches the 5080, but its lower compute resources and bandwidth mean it is not equivalent to a 5080.
The omitted RTX 5070
The $549 RTX 5070 completes the initial desktop stack and is relevant when comparing budgets. It carries 12GB of GDDR7, so the $200 step to the 16GB 5070 Ti buys both additional memory and substantially more GPU resources. Nvidia’s official announcement lists the $549 starting price. Nvidia source.
Rank #4
- Equipped with GeForce RTX 5090 chipset
- Integrated with 32GB of 512-bit GDDR7 memory interface
- WATERFORCE All-in-One Cooling System
- RGB Lighting
- Protective metal back plate
How DLSS 4 changes “twice as fast” claims
DLSS 4 adds Multi Frame Generation for RTX 50-series cards. Nvidia says supported games can generate up to three additional frames for each traditionally rendered frame and describes potential multiplication of up to 8× in supported scenarios. Nvidia’s explanation.
- Generated frames are not equivalent to independently rendered frames.
- Results depend on game support, base frame rate, resolution, image quality and display refresh rate.
- Generated frames can improve perceived smoothness but do not remove a CPU bottleneck or automatically reduce input latency.
- Compare native rasterization, hardware ray tracing, DLSS Super Resolution, Frame Generation and Multi Frame Generation separately.
Therefore, Nvidia’s “up to” and “twice as fast” figures should be read as technology-enabled claims under specified conditions, not unconditional increases in native FPS.
What’s actually slowing this PC down?
Pick the symptom - the matching free tool is one click away.
Best Value
- Powered by the NVIDIA Blackwell architecture and DLSS 4
- Powered by GeForce RTX 5080
- Integrated with 16GB GDDR7 256bit memory interface
- PCIe 5.0
- WINDFORCE cooling system
Desktop and laptop RTX 50 GPUs are different products
The prices above apply only to desktop graphics cards. Laptop RTX 5090, 5080 and 5070 Ti GPUs have different power limits, memory configurations and performance, even though they share names. Nvidia said those laptops would begin appearing in March 2025, with RTX 5070 laptops following in April. A laptop marketed with an “RTX 5090” should not be priced or evaluated as a desktop RTX 5090 equivalent.
MSRP versus what buyers actually paid
Launch MSRP is a reference point, not a live deal. An August 2026 Tom’s Hardware market snapshot reported examples around $4,381 for an RTX 5090, $1,289 for an RTX 5080, $989 for an RTX 5070 Ti and $629 for an RTX 5070. Those are dated market observations, not current guaranteed prices. Tom’s Hardware, August 2026.
For a current check, use Nvidia’s RTX 5090 product finder, RTX 5080 product finder and RTX 5070 Ti product finder, then verify the retailer’s total after tax and shipping.
Which card fits your budget and workload?
Choose the RTX 5090 when
- Maximum 4K performance, heavy ray tracing, local AI or professional rendering matters more than price.
- 32GB of VRAM is useful to your workload.
- Your power supply, case, cooling and cabling can handle a 575W board.
Choose the RTX 5080 when
- You want high-end 4K performance without the 5090’s price and power requirements.
- 16GB of VRAM is sufficient.
- You can buy near the $999 launch MSRP rather than a large markup.
Choose the RTX 5070 Ti when
- Your target is high-refresh 1440p or more affordable 4K.
- You want 16GB of VRAM on a lower budget.
- Your system is not suited to a 575W flagship.
Check these costs before committing
- Compare current street price with the historical MSRP.
- Separate native and DLSS-assisted performance in reviews.
- Check VRAM, power-supply capacity, included cables, card length and thickness.
- Confirm case airflow, CPU balance, monitor resolution and refresh rate.
- Review cooler noise, warranty and return period.
- Compare current-generation alternatives and previous-generation clearance cards.
- Consider a prebuilt if you also need a PSU, case, cooling, operating system and assembly.
The Bottom Line
Nvidia’s $1,999 RTX 5090, $999 RTX 5080 and $749 RTX 5070 Ti prices were genuine U.S. desktop launch MSRPs announced in January 2025. They were starting prices, not permanent retail guarantees. The right purchase depends on today’s actual listing, your resolution and workload, VRAM needs, and the power and cooling upgrades the card may require.
Quick Recap
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
