NewAvailable
Kimi-K3
Moonshot · 1M context
66 tok/s0.71s TTFT
$3.00 / $15.00 per 1M
cached input $0.30 / 1M
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
DeepSeek-V4-Flash
DeepSeek · 1M context
70 tok/s0.88s TTFT
$0.14 / $0.28 per 1M
cached input $0.04 / 1M
Available
DeepSeek-V4-Pro
DeepSeek · 1M context
66 tok/s0.89s TTFT
$1.74 / $3.48 per 1M
cached input $0.43 / 1M
Available
GLM-5.2
Z.ai · 1M context
97 tok/s0.91s TTFT
$1.40 / $4.40 per 1M
cached input $0.35 / 1M
Available
Kimi-K2.6
Moonshot · 256K context
80 tok/s0.66s TTFT
$0.95 / $4.00 per 1M
cached input $0.24 / 1M
Available
Kimi-K2.7-Code
Moonshot · 256K context
168 tok/s0.55s TTFT
$0.95 / $4.00 per 1M
cached input $0.24 / 1M
Available
MiMo-V2.5-Pro
Xiaomi · 1M context
97 tok/s1.76s TTFT
$0.80 / $3.00 per 1M
cached input $0.20 / 1M
Available
MiniMax-M3
MiniMax · 1M context
121 tok/s0.69s TTFT
$0.30 / $1.20 per 1M
cached input $0.07 / 1M
Available
Step-3.7-Flash
StepFun · 256K context
227 tok/s3.76s TTFT
$0.25 / $1.30 per 1M
cached input $0.06 / 1M
Available
DeepSeek-V3.2
DeepSeek · 160K context
25 tok/s2.84s TTFT
$0.50 / $1.50 per 1M
cached input $0.16 / 1M
Available
gemma-4-26b-a4b-it
Google · 1M context
71 tok/s1.02s TTFT
$0.13 / $0.40 per 1M
cached input $0.13 / 1M
Available
gemma-4-31b-it
Google · 1M context
75 tok/s1.03s TTFT
$0.15 / $0.46 per 1M
cached input $0.15 / 1M
Available
GLM-5
Z.ai · 200K context
44 tok/s1.25s TTFT
$1.00 / $3.20 per 1M
cached input $0.25 / 1M
Available
gpt-oss-120b
OpenAI · 128K context
249 tok/s0.35s TTFT
$0.15 / $0.60 per 1M
cached input $0.15 / 1M
Available
gpt-oss-20b
OpenAI · 128K context
143 tok/s0.28s TTFT
$0.07 / $0.30 per 1M
cached input $0.07 / 1M
Available
MiMo-V2.5
Xiaomi · 1M context
86 tok/s1.43s TTFT
$0.14 / $0.28 per 1M
cached input $0.05 / 1M
Available
MiniMax-M2.7
MiniMax · 192K context
143 tok/s1.09s TTFT
$0.30 / $1.20 per 1M
cached input $0.30 / 1M
Available
Mistral-Nemo-Instruct-2407
Mistral · 128K context
65 tok/s1.32s TTFT
$0.04 / $0.17 per 1M
cached input $0.04 / 1M
Available
Nemotron-3-Ultra-550B-A55B
NVIDIA · 500K context
241 tok/s0.56s TTFT
$0.60 / $2.40 per 1M
cached input $0.24 / 1M
Available
Qwen3.6-27B
Alibaba · 256K context
65 tok/s1.07s TTFT
$0.60 / $3.60 per 1M
cached input $0.60 / 1M
Available
Qwen3.6-35B-A3B
Alibaba · 256K context
189 tok/s0.64s TTFT
$0.25 / $1.49 per 1M
cached input $0.25 / 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 ↗
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.