LISTED VND PRICES · VIETQR TOP-UP · VAT INVOICE ON REQUEST

Clear pricing. Pay in VND, no subscription.

One gateway for 110+ models, using the Anthropic or OpenAI SDK.Top up with VietQR, skip the international card, and request a VAT invoice when you need the paperwork.

Model Pool
110+

Claude, GPT, Gemini, DeepSeek, and the rest of the catalogue

Starting From
$0.0682

Price per 1 Million Tokens (1M Tokens), billed on actual usage

Cost Optimization
VND

Pay in VND. No international card required.

Full VAT Invoices
On request

Electronic VAT invoice when a business needs the paperwork

Cost estimate

Estimate a month of usage

Move the slider to estimate tokens and see the cost at the listed price.

Estimate from the listed unit price
2. Tokens expected per month20 million tokens (20M)
1M Token25M Token50M Token75M Token100M Token

* Rough estimate: 1 million tokens is about 750,000 English words. Real chat turns depend on the length of each turn.

Estimate at the MonkeyTech API unit priceListed unit price
Cost at the listed unit price2.000 ₫ / 1 million tokens
40.000 ₫
Model catalogue

Price of each model

Search, filter by vendor, and watch the live status of the whole catalogue.

claude
Operating normally
Claude Fable 5
claude-fable-5
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.3773/1M tok
Use now
claude
Operating normally
Claude Fable 5.1
claude-fable-5-1
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.9091/1M tok
Use now
claude
Operating normally
Claude Fable 5
req/claude-fable-5
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0227/req
Use now
claude
Operating normally
Claude Fable 5.1
req/claude-fable-5.1
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0295/req
Use now
claude
Operating normally
Claude Opus 4.6
claude-opus-4-6
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2955/1M tok
Use now
claude
Operating normally
Claude Opus 4.7
claude-opus-4-7
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2955/1M tok
Use now
claude
Operating normally
Claude Opus 4.8
claude-opus-4-8
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2955/1M tok
Use now
claude
Operating normally
Claude Opus 5
claude-opus-5
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2955/1M tok
Use now
claude
Operating normally
Claude Opus 5.5
claude-opus-5-5
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.6818/1M tok
Use now
claude
Operating normally
Claude Opus 5
req/claude-opus-5
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0182/req
Use now
claude
Operating normally
Claude Opus 5.5
req/claude-opus-5-5
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0295/req
Use now
claude
Operating normally
Claude Opus 4.8
req/claude-opus-4-8
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
claude
Operating normally
Claude Opus 4.6
req/claude-opus-4-6
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
claude
Operating normally
Claude Sonnet 4.6
claude-sonnet-4-6
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2955/1M tok
Use now
claude
Operating normally
Claude Sonnet 5
claude-sonnet-5
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2955/1M tok
Use now
claude
Operating normally
Claude Sonnet 5.5
claude-sonnet-5-5
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.6818/1M tok
Use now
claude
Operating normally
Claude Haiku 4.5
claude-haiku-4-5
200k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2727/1M tok
Use now
claude
Operating normally
Claude Haiku 5.5
claude-haiku-5-5
200k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2727/1M tok
Use now
claude
Operating normally
Claude Sonnet 5
req/claude-sonnet-5
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0182/req
Use now
claude
Operating normally
Claude Sonnet 5.5
req/claude-sonnet-5-5
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0205/req
Use now
claude
Operating normally
Claude Sonnet 4.6
req/claude-sonnet-4-6
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
claude
Operating normally
Claude Haiku 4.5
req/claude-haiku-4-5
200k ContextStandard LaneReasoningVision
Cost per call
$0.015/req
Use now
claude
Operating normally
Claude Haiku 5.5
req/claude-haiku-5-5
200k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
gpt
Operating normally
GPT 5.5
gpt-5.5
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1091/1M tok
Use now
gpt
Operating normally
GPT 5.5
req/gpt-5.5
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0136/req
Use now
gpt
Operating normally
GPT 5.6 Luna
gpt-5.6-luna
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1091/1M tok
Use now
gpt
Operating normally
GPT 5.6 Luna
req/gpt-5.6-luna
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0136/req
Use now
gpt
Operating normally
GPT 5.6 Sol
gpt-5.6-sol
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1273/1M tok
Use now
gpt
Operating normally
GPT 5.6 Sol
req/gpt-5.6-sol
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
gpt
Operating normally
GPT 5.6 Terra
gpt-5.6-terra
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1182/1M tok
Use now
gpt
Operating normally
GPT 5.6 Terra
req/gpt-5.6-terra
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0123/req
Use now
gpt
Operating normally
GPT 6 Astra
gpt-6-astra
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.8182/1M tok
Use now
gpt
Operating normally
GPT 6 Sol
gpt-6-sol
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.5455/1M tok
Use now
gpt
Operating normally
GPT 6.1 Sol
gpt-6.1-sol
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.6818/1M tok
Use now
gpt
Operating normally
GPT 6 Luna
gpt-6-luna
1050k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.3636/1M tok
Use now
gpt
Operating normally
GPT 6 Astra
req/gpt-6-astra
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0455/req
Use now
gpt
Operating normally
GPT 6 Sol
req/gpt-6-sol
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0273/req
Use now
gpt
Operating normally
GPT 6 Luna
req/gpt-6-luna
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0205/req
Use now
gpt
Operating normally
GPT 6.1 Sol
req/gpt-6.1-sol
1050k ContextStandard LaneReasoningVision
Cost per call
$0.0295/req
Use now
gpt
Operating normally
GPT Image 2
req/gpt-image-2
Standard LaneImage generationOpenAI API
Cost per call
$0.0455/req
Use now
deepseek
Operating normally
DeepSeek V4 Pro
req/deepseek-v4-pro
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0118/req
Use now
deepseek
Operating normally
DeepSeek V4 Pro
deepseek-v4-pro
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.0909/1M tok
Use now
deepseek
Operating normally
DeepSeek V4 Flash
req/deepseek-v4-flash
1000k ContextStandard LaneReasoningTool use
Cost per call
$0.0105/req
Use now
deepseek
Operating normally
DeepSeek V4 Flash
deepseek-v4-flash
1000k ContextStandard LaneReasoningTool use
Cost per 1M tokens
$0.0682/1M tok
Use now
deepseek
Operating normally
DeepSeek V4.1 Flash
req/deepseek-v4.1-flash
1000k ContextStandard LaneReasoningTool use
Cost per call
$0.0114/req
Use now
deepseek
Operating normally
DeepSeek V4.1 Flash
deepseek-v4.1-flash
1000k ContextStandard LaneReasoningTool use
Cost per 1M tokens
$0.0909/1M tok
Use now
minimax
Operating normally
Minimax M3
req/minimax-m3
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0114/req
Use now
minimax
Operating normally
Minimax M3.1 Flash
req/minimax-m3.1-flash
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0136/req
Use now
minimax
Operating normally
Minimax M3
minimax-m3
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1136/1M tok
Use now
minimax
Operating normally
Minimax M2.7
req/minimax-m2.7
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0114/req
Use now
minimax
Operating normally
Minimax M2.7
minimax-m2.7
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1136/1M tok
Use now
gemini
Operating normally
Gemini 3.5 Flash
req/gemini-3.5-flash
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
gemini
Operating normally
Gemini 3.5 Flash
gemini-3.5-flash
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1636/1M tok
Use now
gemini
Operating normally
Gemini 3.6 Flash
gemini-3.6-flash
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1773/1M tok
Use now
gemini
Operating normally
Gemini 3.7 Flash
gemini-3.7-flash
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1818/1M tok
Use now
gemini
Operating normally
Gemini 3.8 Flash
gemini-3.8-flash
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2045/1M tok
Use now
gemini
Operating normally
Gemini 3.6 Flash High
req/gemini-3.6-flash-high
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0182/req
Use now
gemini
Operating normally
Gemini 3.7 Flash High
req/gemini-3.7-flash-high
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0205/req
Use now
gemini
Operating normally
Gemini 3.8 Flash
req/gemini-3.8-flash
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0227/req
Use now
gemini
Operating normally
Gemini 3.1 Pro
gemini-3.1-pro
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1591/1M tok
Use now
gemini
Operating normally
Gemini 3.0 Pro Image
req/gemini-3.0-pro-image
Standard LaneImage generationOpenAI API
Cost per call
$0.0455/req
Use now
google
Operating normally
Google Omni Flash
google-omni-flash
Standard LaneVideo generationOpenAI API
Cost per call
$0.15/req
Use now
google
Operating normally
Veo 3.1
veo-3.1
Standard LaneVideo generationOpenAI API
Cost per call
$0.1136/req
Use now
seedance
Operating normally
Seedance 2.0 Fast
seedance-2.0-fast
Standard LaneVideo generationOpenAI API
Cost per call
$0.10/req
Use now
seedance
Operating normally
Seedance 2.5
seedance-2.5
Standard LaneVideo generationOpenAI API
Cost per call
$0.1273/req
Use now
kimi
Operating normally
Kimi K3
kimi-k3
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1727/1M tok
Use now
kimi
Operating normally
Kimi 2.7
kimi-2.7
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1273/1M tok
Use now
kimi
Operating normally
Kimi K3
req/kimi-k3
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
qwen
Operating normally
Qwen 3.8 Max
qwen3.8-max
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1773/1M tok
Use now
qwen
Operating normally
Qwen 3.8 Flash
qwen3.8-flash
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1273/1M tok
Use now
qwen
Operating normally
Qwen 3.7 Max
qwen3.7-max
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1591/1M tok
Use now
qwen
Operating normally
Qwen 3.8 Max
req/qwen3.8-max
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
qwen
Operating normally
Qwen 3.8 Flash
req/qwen3.8-flash
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0114/req
Use now
qwen
Operating normally
Qwen 3.7 Max
req/qwen3.7-max
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0136/req
Use now
glm
Operating normally
GLM 5.2
glm-5.2
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1091/1M tok
Use now
glm
Operating normally
GLM 5.2
req/glm-5.2
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
glm
Operating normally
GLM 5.3
glm-5.3
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1364/1M tok
Use now
glm
Operating normally
GLM 5.3
req/glm-5.3
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0159/req
Use now
glm
Operating normally
GLM 5.3 Flash
glm-5.3-flash
1000k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1818/1M tok
Use now
glm
Operating normally
GLM 5.3 Flash
req/glm-5.3-flash
1000k ContextStandard LaneReasoningVision
Cost per call
$0.0182/req
Use now
grok
Operating normally
Grok 4.5
grok-4.5
500k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1364/1M tok
Use now
grok
Operating normally
Grok 4.5
req/grok-4.5
500k ContextStandard LaneReasoningVision
Cost per call
$0.0114/req
Use now
grok
Operating normally
Grok 4.6
grok-4.6
500k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.1818/1M tok
Use now
grok
Operating normally
Grok 4.6
req/grok-4.6
500k ContextStandard LaneReasoningVision
Cost per call
$0.0114/req
Use now
grok
Operating normally
Grok 4.7
req/grok-4.7
500k ContextStandard LaneReasoningVision
Cost per call
$0.0136/req
Use now
grok
Operating normally
Grok 4.7
grok-4.7
500k ContextStandard LaneReasoningVision
Cost per 1M tokens
$0.2273/1M tok
Use now
qwen
Operating normally
Qwen3 Codex
monkeytech/qwen3-codex
256k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.0909/1M tok
Use now
minimax
Operating normally
MiniMax M2.1
monkeytech/minimax-m2.1
196k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.1227/1M tok
Use now
minimax
Operating normally
MiniMax M2.5
monkeytech/minimax-m2.5
196k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.1955/1M tok
Use now
claude
Operating normally
Claude Haiku 4.5
monkeytech/claude-haiku-4-5
200k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.3682/1M tok
Use now
glm
Operating normally
GLM 5
monkeytech/glm-5
200k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.3682/1M tok
Use now
gpt
Operating normally
GPT 5.6 Luna
monkeytech/gpt-5.6-luna
1050k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.40/1M tok
Use now
claude
Operating normally
Claude Sonnet 5 Medium
monkeytech/claude-sonnet-5-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.6455/1M tok
Use now
gpt
Operating normally
GPT 5.6 Terra
monkeytech/gpt-5.6-terra
1050k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.8227/1M tok
Use now
claude
Operating normally
Claude Sonnet 4.6 Medium
monkeytech/claude-sonnet-4-6-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$0.8273/1M tok
Use now
claude
Operating normally
Claude Sonnet 5 Max Thinking
monkeytech/claude-sonnet-5-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.01/1M tok
Use now
claude
Operating normally
Claude Opus 5 Medium
monkeytech/claude-opus-5-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.09/1M tok
Use now
gpt
Operating normally
GPT 5.6 Sol
monkeytech/gpt-5.6-sol
1050k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.13/1M tok
Use now
claude
Operating normally
Claude Opus 4.6 Medium
monkeytech/claude-opus-4-6-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.10/1M tok
Use now
claude
Operating normally
Claude Sonnet 4.6 Max Thinking
monkeytech/claude-sonnet-4-6-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.10/1M tok
Use now
claude
Operating normally
Claude Opus 4.7 Medium
monkeytech/claude-opus-4-7-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.16/1M tok
Use now
claude
Operating normally
Claude Opus 4.8 Medium
monkeytech/claude-opus-4-8-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.16/1M tok
Use now
claude
Operating normally
Claude Opus 5 Max Thinking
monkeytech/claude-opus-5-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.25/1M tok
Use now
claude
Operating normally
Claude Opus 4.6 Max Thinking
monkeytech/claude-opus-4-6-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.25/1M tok
Use now
claude
Operating normally
Claude Opus 4.7 Max Thinking
monkeytech/claude-opus-4-7-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.25/1M tok
Use now
claude
Operating normally
Claude Opus 4.8 Max Thinking
monkeytech/claude-opus-4-8-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.25/1M tok
Use now
claude
Operating normally
Claude Opus 5.5 Medium
monkeytech/claude-opus-5-5-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.27/1M tok
Use now
claude
Operating normally
Claude Opus 5.5 Max Thinking
monkeytech/claude-opus-5-5-max-thinking
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.36/1M tok
Use now
claude
Operating normally
Claude Fable 5
monkeytech/claude-fable-5
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$1.59/1M tok
Use now
claude
Operating normally
Claude Fable 5.1 Medium
monkeytech/claude-fable-5-1-medium
1000k ContextAWS LaneAWSPremium
Cost per 1M tokens
$2.50/1M tok
Use now
Transparent Billing Mechanism

Simple & Clear Pricing Policy

No monthly lock-in and no maintenance fee. The wallet balance is the money you topped up.

1. Token-Based Billing

Applies to Large Language Models (LLMs). The system precisely tallies input and output tokens.

  • Flexible top-up from 50,000 ₫ via VietQR
  • Permanent balance, never expires
  • Real-time telemetry tracking

2. Per-Request Billing

Applies to image generation, text-to-speech (TTS), and video generation models.

  • Fixed price per successful request
  • No charge on failed requests (4xx / 5xx)
  • Instant auto-refund if task times out

3. Security & VAT Invoicing

Protect enterprise finances with spending limits and compliant accounting vouchers.

  • Configure spending limits
  • Automated balance alerts via Email & Telegram
  • Fast e-VAT invoice issuance
Answers

Pricing questions

Questions about payment, exchange rates, integration, and invoices are answered here.

The minimum VietQR top-up is 50,000 VND. A new account can make one 10,000 VND trial top-up. The wallet balance does not expire.
Get started

Create an account · top up from 50,000 VND

No international card. Scan VietQR to top up, then attach the API key in Cursor, Cline, or your own system.

Create a free accountGroup Zalo
Group ZaloGroup TelegramWhatsApp