Transparent pay-as-you-go pricing

All FlowBar AI model prices

Prices are listed in USD per 1M tokens. Input and output prices are calculated from the live FlowBar AI ModelRatio configuration. Free or benefit routes are shown when enabled.

Top Up / 充值

Imported Models - GPT

ModelInput priceOutput price
openai/gpt-3.5-turbo
OpenAI-compatible model route for general reasoning, coding, and multimodal workflows.
$0.65 / 1M$1.95 / 1M
openai/gpt-4.1-mini
OpenAI-compatible model route for general reasoning, coding, and multimodal workflows.
$0.50 / 1M$2.00 / 1M
openai/gpt-4.1-nano
OpenAI-compatible model route for general reasoning, coding, and multimodal workflows.
$0.15 / 1M$0.60 / 1M
openai/gpt-4o
OpenAI-compatible model route for general reasoning, coding, and multimodal workflows.
$3.20 / 1M$12.80 / 1M
openai/gpt-4o-mini
OpenAI-compatible model route for general reasoning, coding, and multimodal workflows.
$0.20 / 1M$0.80 / 1M
openai/o3-mini
OpenAI-compatible model route for general reasoning, coding, and multimodal workflows.
$1.40 / 1M$5.60 / 1M

Imported Models - Claude

ModelInput priceOutput price
anthropic/claude-haiku-4.5
Anthropic Claude route for writing, analysis, coding, and long-context reasoning.
$1.30 / 1M$6.50 / 1M
anthropic/claude-opus-4.7
Anthropic Claude route for writing, analysis, coding, and long-context reasoning.
$6.50 / 1M$32.50 / 1M
anthropic/claude-sonnet-4.6
Anthropic Claude route for writing, analysis, coding, and long-context reasoning.
$3.90 / 1M$19.50 / 1M

Imported Models - Gemini

ModelInput priceOutput price
google/gemini-2.5-flash
Google Gemini route for fast multimodal and reasoning tasks.
$0.40 / 1M$3.20 / 1M
google/gemini-2.5-pro
Google Gemini route for fast multimodal and reasoning tasks.
$1.60 / 1M$12.80 / 1M
google/gemini-3.1-flash-lite
Google Gemini route for fast multimodal and reasoning tasks.
$0.30 / 1M$1.80 / 1M
google/gemini-3.1-pro-preview
Google Gemini route for fast multimodal and reasoning tasks.
$2.60 / 1M$15.60 / 1M

Imported Models - Other

ModelInput priceOutput price
meta-llama/llama-4-maverick
OpenRouter imported model route.
$0.20 / 1M$0.80 / 1M
mistralai/mistral-large
OpenRouter imported model route.
$2.60 / 1M$7.80 / 1M
moonshotai/kimi-k2.6
OpenRouter imported model route.
$0.95 / 1M$4.75 / 1M
moonshotai/Kimi-K2-Thinking
OpenRouter imported model route.
$0.95 / 1M$4.75 / 1M
inclusionAI/Ring-flash-2.0
OpenRouter imported model route.
$1.50 / 1M$1.50 / 1M
stepfun-ai/step-3.5-flash
OpenRouter imported model route.
$1.50 / 1M$1.50 / 1M
stepfun-ai/Step-3.5-Flash
OpenRouter imported model route.
$1.50 / 1M$1.50 / 1M

Domestic Models - DeepSeek

ModelInput priceOutput price
deepseek-chat
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.30 / 1M$1.20 / 1M
deepseek-v3.2
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.35 / 1M$0.70 / 1M
DeepSeek-V3.2-Pro
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.35 / 1M$0.70 / 1M
deepseek-v4-flash
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.15 / 1M$0.30 / 1M
deepseek-v4-pro
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.55 / 1M$1.10 / 1M
deepseek-ai/deepseek-v4-flash
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.15 / 1M$0.30 / 1M
deepseek-ai/deepseek-v4-pro
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.55 / 1M$1.10 / 1M
deepseek-ai/DeepSeek-OCR
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$1.50 / 1M$1.50 / 1M
deepseek-reasoner
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$1.50 / 1M$1.50 / 1M
deepseek-r1
DeepSeek route for coding, reasoning, OCR, and cost-effective chat workloads.
$0.90 / 1M$3.60 / 1M

Domestic Models - Qwen

ModelInput priceOutput price
qwen3.6-plus
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$0.40 / 1M$2.40 / 1M
qwen3.6-flash
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$0.25 / 1M$1.50 / 1M
Qwen/Qwen3-32B
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$0.10 / 1M$0.40 / 1M
Qwen/Qwen3.6-27B
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$0.40 / 1M$4.40 / 1M
Qwen/Qwen3.6-35B-A3B
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$0.20 / 1M$1.40 / 1M
Qwen3.5-35B-A3B
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$1.50 / 1M$1.50 / 1M
Qwen3.5-397B-A17B-Pro
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$1.50 / 1M$1.50 / 1M
Qwen/Qwen3-Coder-30B-A3B-Instruct
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$0.09 / 1M$0.36 / 1M
Qwen/Qwen-Image
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$1.50 / 1M$1.50 / 1M
Tongyi-MAI/Z-Image-Turbo
Qwen route for Chinese and multilingual chat, coding, and tool-use workflows.
$1.50 / 1M$1.50 / 1M

Domestic Models - GLM / Kimi / MiniMax

ModelInput priceOutput price
glm-5
Domestic model route via Chinese cloud providers.
$1.50 / 1M$1.50 / 1M
glm-5.1
Domestic model route via Chinese cloud providers.
$1.50 / 1M$1.50 / 1M
Pro/zai-org/GLM-5
Domestic model route via Chinese cloud providers.
$1.50 / 1M$1.50 / 1M
Pro/zai-org/GLM-5.1
Domestic model route via Chinese cloud providers.
$1.50 / 1M$1.50 / 1M
kimi-k2.5
Domestic model route via Chinese cloud providers.
$0.50 / 1M$2.50 / 1M
kimi-k2.6
Domestic model route via Chinese cloud providers.
$0.95 / 1M$4.75 / 1M
minimax-m2.5
Domestic model route via Chinese cloud providers.
$0.20 / 1M$1.60 / 1M
minimax-m2.7
Domestic model route via Chinese cloud providers.
$0.35 / 1M$1.40 / 1M
MiniMax-M2.5
Domestic model route via Chinese cloud providers.
$0.20 / 1M$1.60 / 1M
MiniMaxAI/MiniMax-M2.5
Domestic model route via Chinese cloud providers.
$0.20 / 1M$1.60 / 1M
minimaxai/minimax-m2.7
Domestic model route via Chinese cloud providers.
$0.35 / 1M$1.40 / 1M