TaifoonTAIFOON
SIGN IN
Resold prices

Pricing · Taifoon Cloud

Resold prices

Taifoon resells models from other providers. For each model you get one route: the cheapest Taifoon sells now. You pay that provider’s own price plus one cut of 20 %, and nothing else. Every price below can be checked against the provider’s own sheet.

1. How a resold price is made

Taifoon buys each call from the provider at the provider’s published price. It adds one cut of 20 % over that price, rounded up to the micro-USDC, and that sum is the price you pay. The search, the gateway and every channel quote the same price: there is no second cut.

What you pay leaves again in two named legs, and they add up to your payment exactly:

LegGoes toHow much
seller_sharethe provider that served the callits own published price
reseller_markupTaifoonthe cut, 20 % over the provider’s price

A channel that takes its own fee at the source, such as an agent marketplace, adds that fee as a third leg of its own. It is shown on the quote and is never part of Taifoon’s leg.

One minimum applies: a single x402 payment is at least 0.0012 USDC, because smaller payments are refused by the payment network. A call priced below that is charged the minimum, and the difference is Taifoon’s. Paying from a key’s balance has no minimum.

2. Who allows each resale

Taifoon publishes prices only for these providers. Their terms, or their written permission, allow resale. A provider still waiting on a reseller agreement is not on the list.

ProviderWhat allows itPrice sheet
Akash Networkpermissionless leases: no resale restriction found in the network terms; a provider runs our container, we serve our endpointconsole-api.akash.network/v1/gpu-prices
DeepInfraYou are allowed to serve our models through your gateway. (DeepInfra, 2026-10-28, the express permission its terms 11(a)(viii) ask for)api.deepinfra.com/models/list
NEAR AI CloudNEAR AI's written yes of 2026-10-22: it supports routing inference through our gateway, x402 payments and prepaid credits included; ToS §4.2(x) alone forbids resale; Chutes routes follow Chutes' terms (§7.1)cloud-api.near.ai/v1/models
Venice AIToS 7.3: a reseller serves end users bound by terms as protective and is primarily liable; resale allowed by the owner 2026-11-03 (_VENICE_SELLS_v1_); the partner discount stays owner step venice-reseller-agreementapi.venice.ai/api/v1/models?type=text

3. Check a price yourself

Three public calls, no key needed. The first names, for every resold model, the provider’s price, the cut and where the price was read. The second is the provider’s own sheet. The third shows the legs of a quote.

check
# what you pay, what the provider charges, the cut, and where its price was read
curl -s https://coord.taifoon.dev/v1/models | jq '.data[] | select(.taifoon.resold) | {id, owned_by, pay: .taifoon.usd_per_1m, resold: .taifoon.resold}'

# the provider's own sheet (DeepInfra: cents per token × 10,000 = USD per 1M tokens)
curl -s https://api.deepinfra.com/models/list | jq '.[] | select(.model_name == "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo") | .pricing'

# the legs of one quote: the provider's share, the cut, the sum
curl -s 'https://coord.taifoon.dev/v1/match/search?tag=llama-3.1-8b' | jq '.hits[] | {venue, legs: .legs.legs}'

4. The price list

One route per model: the one on sale now, and of those the cheapest. USD per 1 million tokens, input / output. Under each model: the day its price was read from the provider’s sheet, and how you can tell which model answered (TEE-signed: the answer is signed by a sealed machine). “Not on sale yet” means no provider on this list sells that model yet: the price is set, but Taifoon has not yet opened or funded its account there.

ModelServed byProvider priceYou pay
deepseek-r1-0528
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.5 / 2.150.6 / 2.58
deepseek-v3.1
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.25 / 0.950.3 / 1.14
deepseek-v3.2
read 2026-10-16 · model named by the provider · on sale
DeepInfra0.26 / 0.380.312 / 0.456
deepseek-v4-flash
read 2026-10-19 · model named by the provider · on sale
DeepInfra0.09 / 0.180.108 / 0.216
deepseek-v4-flash-0731
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.06 / 0.180.072 / 0.216
deepseek-v4-flash-vision-exp
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.44 / 1.320.528 / 1.584
deepseek-v4-pro
read 2026-10-28 · model named by the provider · on sale
DeepInfra1.3 / 2.61.56 / 3.12
deepseek-v4-pro-0813
read 2026-10-28 · model named by the provider · on sale
DeepInfra1.3 / 2.61.56 / 3.12
deepseek-v4.1-flash
read 2026-10-27 · model named by the provider · on sale
DeepInfra0.2 / 0.60.24 / 0.72
deepseek-v4.1-flash-1017
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.2 / 0.60.24 / 0.72
gemma-3-12b-it
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.05 / 0.150.06 / 0.18
gemma-3-27b-it
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.08 / 0.160.096 / 0.192
gemma-3-4b-it
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.05 / 0.10.06 / 0.12
gemma-4-26b-a4b-it
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.07 / 0.340.084 / 0.408
gemma-4-26b-a4b-it-heretic
read 2026-10-28 · model named by the provider · on sale
Venice AI0.19 / 0.880.228 / 1.056
gemma-4-31b-it
read 2026-10-28 · model named by the provider · on sale
Venice AI0.12 / 0.360.144 / 0.432
glm-4.6
read 2026-10-28 · model named by the provider · on sale
Venice AI0.43 / 1.750.516 / 2.1
glm-4.7
read 2026-10-19 · model named by the provider · on sale
DeepInfra0.4 / 1.750.48 / 2.1
glm-4.7-flash-heretic
read 2026-10-28 · model named by the provider · on sale
Venice AI0.07 / 0.40.084 / 0.48
glm-5
read 2026-10-28 · model named by the provider · on sale
Venice AI1 / 3.21.2 / 3.84
glm-5.1
read 2026-10-28 · model named by the provider · on sale
Venice AI1.54 / 4.841.848 / 5.808
glm-5.2
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.75 / 2.40.9 / 2.88
glm-5.3
read 2026-10-27 · model named by the provider · on sale
DeepInfra0.9 / 41.08 / 4.8
glm-5.3-flash
read 2026-10-22 · TEE-signed · on sale
NEAR AI Cloud0.08 / 0.50.096 / 0.6
gpt-oss-120b
read 2026-10-19 · model named by the provider · on sale
DeepInfra0.037 / 0.170.0444 / 0.204
gpt-oss-20b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.03 / 0.140.036 / 0.168
granite-4.2-8b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.06 / 0.250.072 / 0.3
hy4-preview
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.834 / 2.5011.0008 / 3.0012
inkling-small
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.45 / 1.20.54 / 1.44
kimi-k2.5
read 2026-10-28 · model named by the provider · on sale
Venice AI0.56 / 3.50.672 / 4.2
kimi-k2.6
read 2026-10-27 · model named by the provider · on sale
DeepInfra0.75 / 3.50.9 / 4.2
kimi-k2.7-code
read 2026-10-28 · model named by the provider · on sale
Venice AI0.75 / 3.50.9 / 4.2
kimi-k3
read 2026-10-27 · model named by the provider · on sale
DeepInfra2.85 / 14.253.42 / 17.1
l3-8b-lunaris-v1
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.04 / 0.050.048 / 0.06
ling-3.0-flash
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.06 / 0.180.072 / 0.216
ling-3.0-flash-vl
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.06 / 0.180.072 / 0.216
ling-3.1-flash
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.3 / 0.90.36 / 1.08
llama-3.1-8b-instruct
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.02 / 0.040.024 / 0.048
llama-3.2-3b
read 2026-10-28 · model named by the provider · on sale
Venice AI0.15 / 0.60.18 / 0.72
llama-3.3-70b-instruct
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.1 / 0.320.12 / 0.384
llama-4-scout-17b-16e-instruct
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.1 / 0.30.12 / 0.36
llama-guard-4-12b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.18 / 0.180.216 / 0.216
mimo-v2.5
read 2026-10-28 · model named by the provider · on sale
Venice AI0.4 / 20.48 / 2.4
mimo-v2.6-flash-rl
read 2026-10-28 · model named by the provider · on sale
Venice AI0.175 / 0.350.21 / 0.42
minimax-m2.5
read 2026-10-28 · model named by the provider · on sale
Venice AI0.27 / 0.950.324 / 1.14
minimax-m2.7
read 2026-10-28 · model named by the provider · on sale
Venice AI0.375 / 1.50.45 / 1.8
minimax-m3
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.28 / 1.10.336 / 1.32
mistral-small-24b-instruct-2501
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.05 / 0.080.06 / 0.096
mistral-small-3.2-24b-instruct-2506
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.075 / 0.20.09 / 0.24
muse-glimmer-30b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.3 / 1.20.36 / 1.44
muse-spark-open-816b-a42b
read 2026-10-28 · model named by the provider · on sale
Venice AI1.5625 / 5.31251.875 / 6.375
nemotron-3-nano-4b
read 2026-10-19 · our container · on sale
Taifoon GPU (our own)our own price0.04 / 0.04
phi-4
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.07 / 0.140.084 / 0.168
qwen2.5-72b-instruct
read 2026-10-16 · model named by the provider · on sale
DeepInfra0.36 / 0.40.432 / 0.48
qwen2.5-7b-instruct
read 2026-10-28 · model named by the provider · on sale
Venice AI0.05 / 0.130.06 / 0.156
qwen3-14b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.12 / 0.240.144 / 0.288
qwen3-235b-a22b-instruct-2507
read 2026-10-19 · model named by the provider · on sale
DeepInfra0.09 / 0.550.108 / 0.66
qwen3-235b-a22b-thinking-2507
read 2026-10-28 · model named by the provider · on sale
Venice AI0.45 / 3.50.54 / 4.2
qwen3-30b-a3b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.12 / 0.50.144 / 0.6
qwen3-coder-480b-a35b-instruct
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.3 / 10.36 / 1.2
qwen3-next-80b-a3b-instruct
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.09 / 1.10.108 / 1.32
qwen3-vl-235b-a22b-instruct
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.2 / 0.880.24 / 1.056
qwen3-vl-30b-a3b-instruct
read 2026-10-22 · TEE-signed · on sale
NEAR AI Cloud0.15 / 0.550.18 / 0.66
qwen3.5-27b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.26 / 2.60.312 / 3.12
qwen3.5-35b-a3b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.14 / 10.168 / 1.2
qwen3.5-397b-a17b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.45 / 30.54 / 3.6
qwen3.5-9b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.1 / 0.150.12 / 0.18
qwen3.6-27b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.32 / 3.20.384 / 3.84
qwen3.6-35b-a3b
read 2026-10-28 · model named by the provider · on sale
DeepInfra0.1 / 0.950.12 / 1.14
qwen3.8-2.4t-a95b
read 2026-10-28 · model named by the provider · on sale
Venice AI2.5 / 7.53 / 9
qwen3.8-27b
read 2026-10-22 · TEE-signed · on sale
NEAR AI Cloud0.04 / 1.350.048 / 1.62

Live availability per model, on this deployment, is https://coord.taifoon.dev/v1/models (taifoon.available).

5. Partners: your own markup

A partner, for example one building on n8n, resells under its own key. For each customer it creates a child with its own markup. The customer pays the price above plus that markup. The markup is the partner’s own leg on every call. Taifoon’s leg stays the same and is never raised by a partner’s markup.

a child with a markup
POST https://coord.taifoon.dev/v1/tenant/keys
{ "action": "child", "label": "customer-a", "markup_bps": 500, "cap_day_usdc": 5 }
PartnerMarkup it may setSet by
self-serve (any key)0 % to 500 % per childthe partner, when it creates the child
enrolled partner0 % to 100 %its enrolment with Taifoon

Each child’s calls, what it owes and the partner’s margin: GET https://coord.taifoon.dev/v1/access/reseller. Revoke or re-cap a child with POST https://coord.taifoon.dev/v1/tenant/keys.