One price per model.
Always the fastest node.

Every model below routes across multiple providers. You pay the published rate no matter which one serves you, no platform fee.

NewAvailable

qwen3.8-2.4t-a95b

Alibaba · 986K context
54 tok/s1.36s TTFT
$2.50 / $6.25 per 1MView ↗
cached input $0.50 / 1M
NewAvailable

deepseek-v4-flash-0731

DeepSeek · 1M context
90 tok/s0.70s TTFT
$0.14 / $0.28 per 1MView ↗
cached input $0.07 / 1M
Available

kimi-k3

Moonshot · 1M context
87 tok/s1.14s TTFT
$3.00 / $15.00 per 1MView ↗
cached input $0.60 / 1M
Available

deepseek-v4-pro

DeepSeek · 1M context
88 tok/s0.81s TTFT
$1.74 / $3.48 per 1MView ↗
cached input $0.43 / 1M
Available

glm-5.2

Z.ai · 1M context
120 tok/s1.17s TTFT
$1.40 / $4.40 per 1MView ↗
cached input $0.35 / 1M
Available

kimi-k2.6

Moonshot · 256K context
52 tok/s0.77s TTFT
$0.95 / $4.00 per 1MView ↗
cached input $0.34 / 1M
Available

kimi-k2.7-code

Moonshot · 256K context
158 tok/s0.59s TTFT
$0.95 / $4.00 per 1MView ↗
cached input $0.24 / 1M
Available

mimo-v2.5-pro

Xiaomi · 1M context
58 tok/s4.00s TTFT
$0.50 / $1.50 per 1MView ↗
cached input $0.13 / 1M
Available

minimax-m3

MiniMax · 1M context
67 tok/s0.66s TTFT
$0.30 / $1.20 per 1MView ↗
cached input $0.12 / 1M
Available

step-3.7-flash

StepFun · 256K context
173 tok/s2.40s TTFT
$0.20 / $1.15 per 1MView ↗
cached input $0.05 / 1M
Available

gemma-4-26b-a4b-it

Google · 1M context
80 tok/s1.02s TTFT
$0.13 / $0.40 per 1MView ↗
cached input $0.03 / 1M
Available

gemma-4-31b-it

Google · 1M context
116 tok/s0.62s TTFT
$0.15 / $0.46 per 1MView ↗
cached input $0.12 / 1M
Available

gpt-oss-120b

OpenAI · 128K context
273 tok/s0.51s TTFT
$0.10 / $0.60 per 1MView ↗
cached input $0.10 / 1M
Available

gpt-oss-20b

OpenAI · 128K context
126 tok/s0.50s TTFT
$0.05 / $0.20 per 1MView ↗
cached input $0.01 / 1M
Available

mimo-v2.5

Xiaomi · 1M context
61 tok/s1.55s TTFT
$0.17 / $0.33 per 1MView ↗
cached input $0.04 / 1M
Available

nemotron-3-ultra-550b-a55b

NVIDIA · 500K context
246 tok/s0.69s TTFT
$0.80 / $3.00 per 1MView ↗
cached input $0.20 / 1M
Available

qwen3.6-27b

Alibaba · 256K context
89 tok/s0.97s TTFT
$0.60 / $3.60 per 1MView ↗
cached input $0.15 / 1M
Available

qwen3.6-35b-a3b

Alibaba · 256K context
117 tok/s0.70s TTFT
$0.25 / $1.49 per 1MView ↗
cached input $0.20 / 1M

Throughput and TTFT are live medians, measured continuously.

Predictable pricing

Top up, spend against it, auto-refill when low.

No commitment

Just plug in and start building. Stop anytime.

Volume & enterprise

High-volume discounts, dedicated support and SLAs at scale. Talk to us ↗

FAQ

How models are priced and billed on Keln. Still have questions?
Reach out anytime.

FAQ page ↗

One published rate per model, billed per token, the same rate no matter which provider or node serves the request. Keln takes no platform fee and adds no per-provider markup, so your cost is predictable even as routing changes underneath you.

No. Price is fixed per model, so Keln is free to send every request to the fastest verified capacity. Faster nodes cost you the same as slow ones.

Yes. Every model lists an input and an output rate per 1M tokens. Reasoning tokens are billed as output tokens, and cached input is billed at a reduced rate.

Prepaid credits. Top up a balance, spend against it, and set auto-refill so you never hit zero. Spend is visible live per project and per key. Keln auto-generates invoices for business.

You are billed once, for the tokens you receive. Failed attempts and Keln-initiated failovers are on us. Recovery is part of the service.

Contact us ↗ to get more information on high-volume discounts.

Ready to try Keln?

Start building in minutes.