Pricing
Models & pricing
Every model currently on sale, with its list price. Use the slug as the model parameter when calling the API.
These are list prices. Accounts on a custom pricing plan may have different unit prices — after logging in, see the prices that apply to you on the Models page in the dashboard.
14 models
deepseek-ai/DeepSeek-V4-Flash
deepseek-ai-deepseek-v4-flashChat- Input / 1M
- $0.11628≈ $0.000117 / 1K
- Output / 1M
- $0.232559≈ $0.000233 / 1K
- Context
- —
- Max output
- —
deepseek-ai/DeepSeek-V4.1-Flash
deepseek-ai-deepseek-v4-1-flashChat- Input / 1M
- $0.271318≈ $0.000272 / 1K
- Output / 1M
- $0.697675≈ $0.000698 / 1K
- Context
- —
- Max output
- —
google/gemma-3-12b-it
google-gemma-3-12b-itChat- Input / 1M
- $0.0969≈ $0.000097 / 1K
- Output / 1M
- $0.193799≈ $0.000194 / 1K
- Context
- —
- Max output
- —
google/gemma-3-27b-it
google-gemma-3-27b-itChat- Input / 1M
- $0.07752≈ $0.000078 / 1K
- Output / 1M
- $0.174419≈ $0.000175 / 1K
- Context
- —
- Max output
- —
google/gemma-3-4b-it
google-gemma-3-4b-itChat- Input / 1M
- $0.05814≈ $0.000059 / 1K
- Output / 1M
- $0.124032≈ $0.000125 / 1K
- Context
- —
- Max output
- —
ibm-granite/granite-4.2-3b
ibm-granite-granite-4-2-3bChat- Input / 1M
- $0.03876≈ $0.000039 / 1K
- Output / 1M
- $0.143411≈ $0.000144 / 1K
- Context
- —
- Max output
- —
meta-llama/Llama-4-Scout-17B-16E-Instruct
meta-llama-llama-4-scout-17b-16e-instructChat- Input / 1M
- $0.124032≈ $0.000125 / 1K
- Output / 1M
- $0.329458≈ $0.00033 / 1K
- Context
- —
- Max output
- —
mistralai/Mistral-Nemo-Instruct-2407
mistralai-mistral-nemo-instruct-2407Chat- Input / 1M
- $0.025969≈ $0.000026 / 1K
- Output / 1M
- $0.036822≈ $0.000037 / 1K
- Context
- —
- Max output
- —
mistralai/Mistral-Small-24B-Instruct-2501
mistralai-mistral-small-24b-instruct-2501Chat- Input / 1M
- $0.05814≈ $0.000059 / 1K
- Output / 1M
- $0.0969≈ $0.000097 / 1K
- Context
- —
- Max output
- —
nvidia/Nemotron-3-Nano-30B-A3B
nvidia-nemotron-3-nano-30b-a3bChat- Input / 1M
- $0.05814≈ $0.000059 / 1K
- Output / 1M
- $0.286822≈ $0.000287 / 1K
- Context
- —
- Max output
- —
openai/gpt-oss-120b
openai-gpt-oss-120bChat- Input / 1M
- $0.05814≈ $0.000059 / 1K
- Output / 1M
- $0.224807≈ $0.000225 / 1K
- Context
- —
- Max output
- —
openai/gpt-oss-20b
openai-gpt-oss-20bChat- Input / 1M
- $0.046512≈ $0.000047 / 1K
- Output / 1M
- $0.166667≈ $0.000167 / 1K
- Context
- —
- Max output
- —
Qwen/Qwen3-14B
qwen-qwen3-14bChat- Input / 1M
- $0.135659≈ $0.000136 / 1K
- Output / 1M
- $0.267442≈ $0.000268 / 1K
- Context
- —
- Max output
- —
Qwen/Qwen3-32B
qwen-qwen3-32bChat- Input / 1M
- $0.11628≈ $0.000117 / 1K
- Output / 1M
- $0.35659≈ $0.000357 / 1K
- Context
- —
- Max output
- —
How billing works
- Prices are in USD per 1,000,000 tokens; input (prompt) and output (completion) are billed separately.
- Cost per request = tokens × unit price ÷ 1,000,000, rounded up to $0.000001. The “≈ / 1K” column is for quick reference only.
- Each request places a hold for its estimated maximum cost, then only the actual tokens used are charged.
- No monthly fees, no minimum commitment. Your wallet is in USD; top up by VND bank transfer via VietQR (converted at the rate when the QR code is created).
Details: Billing docs