vastai search offers

Search for instance types using custom query

Usage

vastai search offers [--help] [--api-key API_KEY] [--raw] <query>

Arguments

query · string · required

Query to search for. default: ‘external=false rentable=true verified=true’, pass -n to ignore default

Options

-t · string · default: "on-demand"

Show ‘on-demand’, ‘reserved’, or ‘bid’(interruptible) pricing. default: on-demand (alias: --type)

-i · string

Alias for --type=bid (alias: --interruptible)

-b · string

Alias for --type=bid (alias: --bid)

-r · string

Alias for --type=reserved (alias: --reserved)

-d · string

Alias for --type=on-demand (alias: --on-demand)

-n · boolean

Disable default query (alias: --no-default)

--new · boolean

Experimental search path — not recommended for production use. Prefer the default search for SLA filtering.

--limit · integer

Maximum number of offers to return. Prefer an explicit limit when comparing SLA-inclusive dph_total results; combine with --order / -o as needed.

--storage · number · default: "5.0"

Amount of storage to use for pricing, in GiB. default=5.0GiB

-o · string · default: "score-"

Comma-separated list of fields to sort on. postfix field with - to sort desc. ex: -o ‘num_gpus,total_flops-’. default=‘score-’ (alias: --order)

Description

Query syntax

query      = comparison comparison...
comparison = field op value
field      = <name of a field>
op         = one of: <, <=, ==, !=, >=, >, in, notin
value      = <bool, int, float, string> | 'any' | [value0, value1, ...]
bool       = True | False

• Wrap > and < in quotes on the command line
• For string values (e.g. gpu_name), replace spaces with underscores: RTX_3090 not RTX 3090

Examples

Search quotes SLA pricing only. vastai create instance cannot pass target_reliability today — use the web console or REST to enable coverage; see SLA Coverage.

# reliable single RTX 3090, no conflicts with stopped instances
vastai search offers 'reliability > 0.98 num_gpus=1 gpu_name=RTX_3090 rented=False'

# SLA search quote (enable coverage at rent via console/REST — see SLA Coverage)
# Always set --storage explicitly when comparing dph_total (CLI default 5 GiB ≠ REST 8 GB).
vastai search offers 'has_sla=true expected_reliability>=0.99 target_reliability=0.95' --storage 50 --order dph_total

# datacenter GPUs with minimum compute capability and TFLOPs
vastai search offers 'compute_cap > 610 total_flops > 5 datacenter=True'

# reliable 4-GPU offers in Taiwan or Sweden
vastai search offers 'reliability>0.99 num_gpus=4 geolocation in [TW,SE]'

# reliable RTX 3090 or 4090 NOT in China or Vietnam
vastai search offers 'reliability>0.99 gpu_name in [RTX_4090, RTX_3090] geolocation notin [CN,VN]'

# nvidia driver 535.86.05 or greater with various constraints
vastai search offers 'disk_space>146 duration>24 gpu_ram>10 cuda_vers>=12.1 direct_port_count>=2 driver_version >= 535.86.05'

# reliable 4+ GPU offers, unverified allowed, sort by num_gpus desc
vastai search offers 'reliability > 0.99  num_gpus>=4 verified=False rented=any' -o 'num_gpus-'

# arm64 cpu architecture only
vastai search offers 'cpu_arch=arm64'

Available Fields

Field	Type	Description
bw_nvlink	float	bandwidth NVLink
compute_cap	int	CUDA compute capability ×100 (e.g. 650 for 6.5, 700 for 7.0)
cpu_arch	string	host machine cpu architecture (e.g. amd64, arm64)
cpu_cores	int	number of virtual cpus
cpu_ghz	float	cpu clock speed in GHz
cpu_cores_effective	float	virtual cpus you get
cpu_ram	float	system RAM in gigabytes
cuda_vers	float	machine max supported cuda version (based on driver version)
datacenter	bool	show only datacenter offers
direct_port_count	int	open ports on host’s router
disk_bw	float	disk read bandwidth, in MB/s
disk_space	float	disk storage space, in GB
dlperf	float	DL-perf score (see FAQ for explanation)
dlperf_usd	float	DL-perf per dollar
dph	float	$/hour rental cost
driver_version	string	machine’s nvidia/amd driver version as 3 digit string ex. “535.86.05”
duration	float	max rental duration in days
external	bool	show external offers in addition to datacenter offers
flops_usd	float	TFLOPs per dollar
geolocation	string	two letter country code; supports =, !=, in, notin
gpu_arch	string	host machine gpu architecture (e.g. nvidia, amd)
gpu_max_power	float	GPU power limit (watts)
gpu_max_temp	float	GPU temp limit (°C)
gpu_mem_bw	float	GPU memory bandwidth in GB/s
gpu_name	string	GPU model name (no quotes, replace spaces with underscores, ie: RTX_3090)
gpu_ram	float	per GPU RAM in GB
gpu_total_ram	float	total GPU RAM in GB
gpu_frac	float	ratio of GPUs in the offer to GPUs in the system
gpu_display_active	bool	True if the GPU has a display attached
has_avx	bool	CPU supports AVX instruction set
id	int	Offer/ask ID. Use this value when renting via create-instance (PUT /api/v0/asks/{id}/)
inet_down	float	internet download speed in Mb/s
inet_down_cost	float	internet download bandwidth cost in $/GB
inet_up	float	internet upload speed in Mb/s
inet_up_cost	float	internet upload bandwidth cost in $/GB
machine_id	int	machine id of instance
min_bid	float	current minimum bid price in $/hr for interruptible
num_gpus	int	number of GPUs
pci_gen	float	PCIE generation
pcie_bw	float	PCIE bandwidth (CPU to GPU)
dph_total	float	total $/hr in search results (compute + storage + SLA charge when applicable)
reliability	float	machine reliability score (see FAQ for explanation)
expected_reliability	float	host’s advertised SLA reliability claim on the offer
has_sla	bool	restrict to offers with SLA enabled (true) or without (false)
target_reliability	float	desired SLA coverage (0–1 exclusive); prices dph_total in search only — see SLA Coverage to enable at rent

SLA query keys (has_sla, expected_reliability, target_reliability) are accepted by search. Older CLI builds may print a stderr warning that a field is unrecognized while still applying the filter — prefer a current CLI, or ignore the warning when results look correct.

| rentable | bool | is the instance currently rentable | | rented | bool | allow/disallow duplicates and potential conflicts with existing stopped instances | | storage_cost | float | storage cost in $/GB/month | | static_ip | bool | is the IP addr static/stable | | total_flops | float | total TFLOPs from all GPUs | | ubuntu_version | string | host machine ubuntu OS version | | verified | bool | is the machine verified | | vms_enabled | bool | is the machine a VM instance |

Global Options

The following options are available for all commands:

Option	Description
--url URL	Server REST API URL
--retry N	Retry limit
--raw	Output machine-readable JSON
--explain	Verbose explanation of API calls
--api-key KEY	API key (defaults to ~/.config/vastai/vast_api_key)