Tesla T4 rental price: from $0.35/hr today
The cheapest on-demand Tesla T4 today is $0.35 an hour at Google Cloud, US Central (Iowa), checked 22 October 2026.
- Spot $0.21 Google Cloud, interruptible
- Serverless $0.59 Modal, per second
- 6 offers
- 5 providers
- Cheapest unchanged since 20 July
- Source cloud.google.com
Tesla T4 offers: 6 configurations from 5 providers
More filters: provider, memory, node size, stock, place, sort, price unit
“Machines in” filters the 2 of 6 offers whose provider says where the machine is; the others are under “Place not stated”.
Baseten, Cerebrium and Modal put GPUs in North America on their own pages, but none of their offers here says so.
- Rent →
Google Cloud1 configuration$0.35on-demandNot reportedOn-demand $0.35Spot & community $0.21US Central (Iowa)
Configuration Billing $/GPU-hour Node Stock · checked Tesla T4US Central (Iowa) spot / interruptible $0.21 node size not published checked 22 October 2026 · source Tesla T4US Central (Iowa) on-demand $0.35 node size not published checked 22 October 2026 · source Google Cloud Tesla T4 pricing · Google Cloud: every GPU, fees and billing
- Rent →
Modal1 configuration$0.59serverlessNot reportedServerless $0.59
Configuration Billing $/GPU-hour Node Stock · checked Tesla T4 serverless $0.59 node size not published checked 22 October 2026 · source - Rent →
Cerebrium1 configuration$0.59serverlessNot reportedServerless $0.59
Configuration Billing $/GPU-hour Node Stock · checked Tesla T4 serverless $0.59 node size not published checked 22 October 2026 · source Cerebrium Tesla T4 pricing · Cerebrium: every GPU, fees and billing
- Rent →
Baseten1 configuration$0.63serverlessNot reportedServerless $0.63
Configuration Billing $/GPU-hour Node Stock · checked Tesla T4 serverless $0.63 node size not published checked 22 October 2026 · source Baseten Tesla T4 pricing · Baseten: every GPU, fees and billing
- Rent →
Replicate1 configuration$0.81serverlessNot reportedServerless $0.81
Configuration Billing $/GPU-hour Node Stock · checked Tesla T4 serverless $0.81 node size not published checked 22 October 2026 · source Replicate Tesla T4 pricing · Replicate: every GPU, fees and billing
1 providers with on-demand offers, cheapest first. Tap a provider for its configurations.
| GPU / provider | Billing | $/GPU-hour | Node · total per hour | Rent |
|---|---|---|---|---|
| Tesla T4 · Google Cloud16 GB | on-demand | $0.35 | – | Rent →checked 22 OctDetails
|
| Tesla T4 · Google Cloud16 GB | spot / interruptible | $0.21 | – | Rent →checked 22 OctDetails
|
| Tesla T4 · Modal16 GB | serverless | $0.59$0.000164/sec | – | Rent →checked 22 OctDetails
|
| Tesla T4 · Cerebrium16 GB | serverless | $0.59$0.000164/sec | – | Rent → |
| Tesla T4 · Baseten16 GB | serverless | $0.63$0.000175/sec | – | Rent → |
| Tesla T4 · Replicate16 GB | serverless | $0.81$0.000225/sec | – | Rent → |
Try another provider or reduce the minimum memory.
Tables rank by price, lowest first. Commercial relationships never affect ordering. How we collect and rank prices.
Same GPU, provider, billing and price on several hosts or listings: one row, with the count. – means the provider does not state it.
Monthly view assumes 730 hours of continuous use. Daily view assumes 24 hours.
Cite this data
GPU Rental Prices, "Tesla T4 rental price: from $0.35/GPU-hour", prices checked 22 October 2026, https://gpurentalprices.com/t4
Quote it with a link to this page. Downloads of the whole dataset are on Data & API.
On-demand and secure-cloud rates are capacity the provider runs, with no reservation. Spot and community capacity can be interrupted. A marketplace host is one independent owner's server listed on a marketplace. Prices are per GPU per hour, before storage and data transfer. Every row shows the date it was checked.
Tesla T4 price history and range
- Cheapest rate$0.35(unchanged since 20 July)
- Cheapest spot$0.21
Tesla T4 price range by billing type
Per GPU-hour, today's offers. Axis $0 to $1.00.
CheapestProvider median (each provider's cheapest rate counted once; shown with three or more providers)
Price changes
- 30 days: No matching dated observations for this comparison.
- 90 days: No matching dated observations for this comparison.
Changes use the geometric mean of price ratios for the same provider, variant, tier, GPU count, instance and region (RunPod's place is where that day's stock sat, so it is not matched). New listings are not counted as price changes. Full ledger on the history hub.
Tesla T4 daily figures (97 days)
| Date | Cheapest rate | Cheapest spot |
|---|---|---|
| 2026-10-22 | $0.35 | $0.21 |
| 2026-10-21 | $0.35 | $0.21 |
| 2026-10-20 | $0.35 | $0.21 |
| 2026-10-19 | $0.35 | $0.21 |
| 2026-10-18 | $0.35 | $0.20 |
| 2026-10-17 | $0.35 | $0.20 |
| 2026-10-16 | $0.35 | $0.20 |
| 2026-10-15 | $0.35 | $0.20 |
| 2026-10-14 | $0.35 | $0.20 |
| 2026-10-13 | $0.35 | $0.20 |
| 2026-10-12 | $0.35 | $0.21 |
| 2026-10-11 | $0.35 | $0.21 |
| 2026-10-10 | $0.35 | $0.21 |
| 2026-10-09 | $0.35 | $0.21 |
| 2026-10-08 | $0.35 | $0.21 |
| 2026-10-07 | $0.35 | $0.21 |
| 2026-10-06 | $0.35 | $0.21 |
| 2026-10-05 | $0.35 | $0.20 |
| 2026-10-04 | $0.35 | $0.20 |
| 2026-10-03 | $0.35 | $0.20 |
| 2026-10-02 | $0.35 | $0.20 |
| 2026-10-01 | $0.35 | $0.20 |
| 2026-09-30 | $0.35 | $0.20 |
| 2026-09-29 | $0.35 | $0.20 |
| 2026-09-28 | $0.35 | $0.21 |
| 2026-09-27 | $0.35 | $0.21 |
| 2026-09-26 | $0.35 | $0.21 |
| 2026-09-25 | $0.35 | $0.21 |
| 2026-09-24 | $0.35 | $0.21 |
| 2026-09-23 | $0.35 | $0.21 |
| 2026-09-22 | $0.35 | $0.21 |
| 2026-09-21 | $0.35 | $0.20 |
| 2026-09-20 | $0.35 | $0.20 |
| 2026-09-19 | $0.35 | $0.20 |
| 2026-09-18 | $0.35 | $0.20 |
| 2026-09-17 | $0.35 | $0.20 |
| 2026-09-16 | $0.35 | $0.20 |
| 2026-09-15 | $0.35 | $0.20 |
| 2026-09-14 | $0.35 | $0.19 |
| 2026-09-13 | $0.35 | $0.19 |
| 2026-09-12 | $0.35 | $0.19 |
| 2026-09-11 | $0.35 | $0.19 |
| 2026-09-10 | $0.35 | $0.19 |
| 2026-09-09 | $0.35 | $0.19 |
| 2026-09-08 | $0.35 | $0.19 |
| 2026-09-07 | $0.35 | $0.20 |
| 2026-09-06 | $0.35 | $0.20 |
| 2026-09-05 | $0.35 | $0.20 |
| 2026-09-04 | $0.35 | $0.20 |
| 2026-09-03 | $0.35 | $0.20 |
| 2026-09-02 | $0.35 | $0.20 |
| 2026-09-01 | $0.35 | $0.20 |
| 2026-08-31 | $0.35 | $0.20 |
| 2026-08-30 | $0.35 | $0.20 |
| 2026-08-29 | $0.35 | $0.20 |
| 2026-08-28 | $0.35 | $0.20 |
| 2026-08-27 | $0.35 | $0.20 |
| 2026-08-26 | $0.35 | $0.20 |
| 2026-08-25 | $0.35 | $0.20 |
| 2026-08-24 | $0.35 | $0.19 |
| 2026-08-23 | $0.35 | $0.19 |
| 2026-08-22 | $0.35 | $0.19 |
| 2026-08-21 | $0.35 | $0.19 |
| 2026-08-20 | $0.35 | $0.19 |
| 2026-08-19 | $0.35 | $0.19 |
| 2026-08-18 | $0.35 | $0.19 |
| 2026-08-17 | $0.35 | $0.18 |
| 2026-08-16 | $0.35 | $0.18 |
| 2026-08-15 | $0.35 | $0.18 |
| 2026-08-14 | $0.35 | $0.18 |
| 2026-08-13 | $0.35 | $0.18 |
| 2026-08-12 | $0.35 | $0.18 |
| 2026-08-11 | $0.35 | $0.18 |
| 2026-08-10 | $0.35 | $0.19 |
| 2026-08-09 | $0.35 | $0.19 |
| 2026-08-08 | $0.35 | $0.19 |
| 2026-08-07 | $0.35 | $0.19 |
| 2026-08-06 | $0.35 | $0.19 |
| 2026-08-05 | $0.35 | $0.19 |
| 2026-08-04 | $0.35 | $0.19 |
| 2026-08-03 | $0.35 | $0.19 |
| 2026-08-02 | $0.35 | $0.18 |
| 2026-08-01 | $0.35 | $0.18 |
| 2026-07-31 | $0.35 | $0.18 |
| 2026-07-30 | $0.35 | $0.18 |
| 2026-07-29 | $0.35 | $0.18 |
| 2026-07-28 | $0.35 | $0.18 |
| 2026-07-27 | $0.35 | $0.18 |
| 2026-07-26 | $0.35 | $0.18 |
| 2026-07-25 | $0.35 | $0.18 |
| 2026-07-24 | $0.35 | $0.18 |
| 2026-07-23 | $0.35 | $0.18 |
| 2026-07-22 | $0.35 | $0.18 |
| 2026-07-21 | $0.35 | $0.18 |
| 2026-07-20 | $0.35 | $0.18 |
| 2026-07-19 | $0.59 | – |
| 2026-07-18 | $0.59 | – |
Tesla T4 prices by provider and billing type
Each provider's cheapest rate in each billing type, per GPU-hour. The provider name opens its Tesla T4 page with node sizes, fees and its own history.
| Provider | On-demand | Spot & community | Serverless |
|---|---|---|---|
| Google Cloud | $0.35 | $0.21 | – |
| Modal | – | – | $0.59 |
| Cerebrium | – | – | $0.59 |
| Baseten | – | – | $0.63 |
| Replicate | – | – | $0.81 |
Tesla T4 hardware specs
| Architecture | Turing |
|---|---|
| VRAM | 16 GB |
| FP16 TFLOPS (dense) | 65 |
| Memory bandwidth | 320 GB/s |
| TDP | 70 W |
| Interconnect | PCIe Gen3 |
| Launched | 2018 |
Manufacturer datasheet figures for the Tesla T4. Source: www.nvidia.com.
LLM memory estimates for this GPU
These models have an estimated inference footprint within 16 GB at one or more precisions. The scenario uses 4,096 tokens, batch 1, a 16-bit KV cache and 20% runtime headroom. A memory fit does not establish speed or software compatibility.
| Model | 16-bit GB | 8-bit GB | 4-bit GB |
|---|---|---|---|
| Mistral Small 3.2 24B 2506 | 58.4 | 29.6 | 15.2 ✓ |
| Mistral Small 24B 2501 | 57.4 | 29.1 | 14.9 ✓ |
| Devstral Small 2507 | 57.4 | 29.1 | 14.9 ✓ |
| Qwen2.5 14B | 36.4 | 18.7 | 9.8 ✓ |
| Qwen2.5 Coder 14B | 36.4 | 18.7 | 9.8 ✓ |
| DeepSeek R1 Distill Qwen 14B | 36.4 | 18.7 | 9.8 ✓ |
| Qwen3 14B | 36.2 | 18.5 | 9.7 ✓ |
| phi 4 | 36.2 | 18.6 | 9.8 ✓ |
| Phi 4 reasoning | 36.2 | 18.6 | 9.8 ✓ |
| Phi 4 reasoning plus | 36.2 | 18.6 | 9.8 ✓ |
| Mistral Nemo 2407 | 30.2 | 15.5 ✓ | 8.2 ✓ |
| Qwen3 8B | 20.4 | 10.6 ✓ | 5.6 ✓ |
| DeepSeek R1 Distill Llama 8B | 19.9 | 10.3 ✓ | 5.5 ✓ |
| Qwen2.5 7B | 18.6 | 9.4 ✓ | 4.9 ✓ |
| Qwen2.5 Coder 7B | 18.6 | 9.4 ✓ | 4.9 ✓ |
| DeepSeek R1 Distill Qwen 7B | 18.6 | 9.4 ✓ | 4.9 ✓ |
| Mistral 7B v0.3 | 18.0 | 9.3 ✓ | 5.0 ✓ |
| Qwen3 4B | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen3 4B 2507 | 10.4 ✓ | 5.6 ✓ | 3.1 ✓ |
| Qwen2.5 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen2.5 Coder 3B | 7.6 ✓ | 3.9 ✓ | 2.0 ✓ |
| Qwen3 1.7B | 5.4 ✓ | 3.0 ✓ | 1.8 ✓ |
| DeepSeek R1 Distill Qwen 1.5B | 4.4 ✓ | 2.3 ✓ | 1.2 ✓ |
| Qwen2.5 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen2.5 Coder 1.5B | 3.8 ✓ | 2.0 ✓ | 1.1 ✓ |
| Qwen3 0.6B | 2.4 ✓ | 1.5 ✓ | 1.0 ✓ |
| Qwen2.5 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
| Qwen2.5 Coder 0.5B | 1.2 ✓ | 0.7 ✓ | 0.4 ✓ |
Models that need more than one Tesla T4
- Mixtral 8x7B v0.1 at 16-bit needs about 113 GB with the same context and headroom, so at least 8 cards. No provider we track publishes a Tesla T4 node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
- Qwen2.5 32B at 16-bit needs about 80 GB with the same context and headroom, so at least 5 cards. No provider we track publishes a Tesla T4 node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
- Qwen2.5 Coder 32B at 16-bit needs about 80 GB with the same context and headroom, so at least 5 cards. No provider we track publishes a Tesla T4 node of that size today. At 8 or 4 bit it needs less; the model page recalculates.
Compare model memory requirements or change context and memory assumptions on a model's page.
When to choose the Tesla T4, and what to pick instead
Start from memory: your model, its context and your batch must fit in 16 GB (the model-fit table above estimates it). Then the Tesla T4 is the right card unless one of these fits your job better.
- Pick the A30 (24 GB, from $0.35/hr) when the model or its cache does not fit in 16 GB.
- Pick the Tesla V100 (16 GB, from $0.17/hr) when finishing sooner is worth paying more: it has 1.9 times the Tesla T4's 16-bit compute.
Rent or buy the Tesla T4
Confirmed Tesla T4 purchase listings start at $950 (T4 16GB, NetworkOutlet, checked 22 October 2026). That sum rents about 2,714 GPU-hours at today's cheapest on-demand rate of $0.35, about 1.3 years at 40 hours a week, before electricity, hosting and resale.
Compare Tesla T4 purchase prices and quote availability, then enter your usage and electricity costs in the rent-versus-buy calculator. Purchase listings have their own variants, stock status and update dates. Compare two GPUs.
Tesla T4 questions
- How much does it cost to rent a Tesla T4?
- The cheapest Tesla T4 rental we have is $0.35 per GPU-hour on Google Cloud (on-demand), checked 22 October 2026.
- How much VRAM does a Tesla T4 have?
- 16 GB.
- Where is the Tesla T4 cheapest right now?
- Google Cloud has the cheapest checked on-demand rate today at $0.35 per GPU-hour; interruptible spot or community capacity starts at $0.21 (Google Cloud).
GPUs near the Tesla T4
- RTX 2000 Ada16 GB$0.24/hrcheapest on-demand
- A3024 GB$0.35/hrcheapest on-demand
- Quadro RTX 500016 GB$0.60/hrcheapest on-demand
- RTX A450020 GB$0.25/hrcheapest on-demand
- L424 GB$0.44/hrcheapest on-demand
Related
All 24 GB+ GPUs · GPUs under $1/hr · Price movers this week · Google Cloud review · A10 vs Tesla T4 · A30 vs Tesla T4 · A40 vs Tesla T4