2KEN
claude-fable-5$1.50/$7.50↑ 85%
claude-haiku-4-5-20251001$0.15/$0.75↑ 85%
claude-opus-4-6$0.75/$3.75↑ 85%
claude-opus-4-7$0.75/$3.75↑ 85%
claude-opus-4-8$0.75/$3.75↑ 85%
claude-opus-5$0.75/$3.75↑ 85%
claude-sonnet-4-6$0.45/$2.25↑ 85%
claude-sonnet-5$0.45/$2.25↑ 85%
deepseek-v4-flash$0.14/$0.28→ 0%
deepseek-v4-pro$0.435/$0.87→ 0%
MiniMax-M2$0.30/$1.20→ 0%
MiniMax-M2.5$0.30/$1.20→ 0%
MiniMax-M2.7$0.30/$1.20→ 0%
MiniMax-M3$0.30/$1.20→ 0%
kimi-k2$0.60/$3.00→ 0%
kimi-k2.5$0.60/$3.00→ 0%
kimi-k2.6$0.95/$4.0001→ 0%
kimi-k2.7-code$0.95/$4.0001→ 0%
kimi-k3$3.00/$15.00→ --
gpt-5.4$0.146/$0.876↑ 94%
gpt-5.5$0.292/$1.752↑ 94%
gpt-5.6-luna$0.0584/$0.3504↑ 94%
gpt-5.6-sol$0.292/$1.752↑ 94%
gpt-5.6-terra$0.146/$0.876↑ 94%
grok-4.3$0.0092/$0.0183↑ 99%
grok-4.5$0.0146/$0.0438↑ 99%
grok-build-0.1$0.0073/$0.0146↑ 99%
glm-5$1.00/$3.20→ 0%
glm-5.1$1.40/$4.40→ 0%
GLM-5.2$1.40/$4.40→ 0%
ERNIE-4.0-8K$2.94/$8.83→ 0%
qwen-flash$0.25/$2.00→ 0%
qwen-max-latest$1.60/$6.40→ 0%
qwen-plus-latest$1.20/$12.00→ 0%
qwen-turbo$0.05/$0.50→ 0%
qwen-vl-max-latest$0.80/$3.20→ 0%
qwen3-max$3.00/$15.00→ 0%
qwen3-max-preview$2.50/$7.50→ 0%
qwen3-vl-flash$0.12/$0.96→ 0%
qwen3-vl-plus$0.60/$4.80→ 0%
qwen3.5-plus$0.50/$3.00→ 0%
qwen3.6-plus$2.00/$6.00→ 0%
qwen3.7-max$2.50/$7.50→ 0%
qwen3.7-plus$1.20/$4.80→ 0%

One key, every model.

Ship against one OpenAI-compatible endpoint, keep routing flexible, and tell a sharper story about model access, budgets, and latency from day one.

Open quickstartBrowse models
69Supported models
11Vendors covered
32.4BLifetime tokens
Deepseek
Moonshot
Zhipu
Qwen
OpenAI
Anthropic
Google Gemini
xAI
Mistral
Meta
MiniMax

Model list

view all
ModelInputOutputCacheGenerationDiscount
claude-fable-5Anthropic
InputOfficial: $10.00/1M2ken: $1.50/1M
OutputOfficial: $50.00/1M2ken: $7.50/1M
CacheOfficial: $1.00/1M2ken: $0.15/1M
Generation--
Discount↑ Savings 85%
claude-haiku-4-5-20251001Anthropic
InputOfficial: $1.00/1M2ken: $0.15/1M
OutputOfficial: $5.00/1M2ken: $0.75/1M
CacheOfficial: $0.10/1M2ken: $0.015/1M
Generation--
Discount↑ Savings 85%
claude-opus-4-6Anthropic
InputOfficial: $5.00/1M2ken: $0.75/1M
OutputOfficial: $25.00/1M2ken: $3.75/1M
CacheOfficial: $0.50/1M2ken: $0.075/1M
Generation--
Discount↑ Savings 85%
claude-opus-4-7Anthropic
InputOfficial: $5.00/1M2ken: $0.75/1M
OutputOfficial: $25.00/1M2ken: $3.75/1M
CacheOfficial: $0.50/1M2ken: $0.075/1M
Generation--
Discount↑ Savings 85%
claude-opus-4-8Anthropic
InputOfficial: $5.00/1M2ken: $0.75/1M
OutputOfficial: $25.00/1M2ken: $3.75/1M
CacheOfficial: $0.50/1M2ken: $0.075/1M
Generation--
Discount↑ Savings 85%

Why 2KEN

Extreme speed and stability

Global route acceleration, smart retries, and load balancing keep output stable and low-latency under high concurrency, with time-to-first-token under 1 second.

Full-spectrum coverage

Aggregate GPT, Claude, Gemini, Grok, DeepSeek, Qwen, and CLI capabilities in one place across chat, Responses, Realtime, Embedding, Rerank, multimodal, and tool-calling workflows.

Plug and play

A standardized unified entry point stays compatible with Claude Messages, Gemini, Responses, and other protocol shapes. Go live in 5 minutes.

Closed-loop cost governance

From request-level usage metrics and cache-hit cost accounting to top-ups and quotas, 2KEN creates an auditable cost-management chain. Set budgets by API key and track billing by token.

FAQ