Docs
Getting Started

Models & Pricing

Current public model IDs, capabilities, availability, and pricing from the Qufas Runtime Model Registry.

Pricing source

This page reads the current enabled public models and prices directly from the Runtime Model Registry. It does not maintain a separate pricing table.

Prices are USD. Token rates are per one million tokens; image rates are per generated image unless the table states another unit. Current pricing is shown below. Pricing may change; billing reads the registry rate at final settlement, not a price reserved at request start.

Available models

Public model IDTypeInput priceOutput / unit priceCapabilitiesContext windowMax outputSupported sizesAvailability
deepseek-v4-flash-0731DeepSeek V4 Flash · Jul 31chat$0.44 / 1M input tokens$1.32 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
deepseek-v4-pro-0813DeepSeek V4 Pro · Aug 13chat$1.32 / 1M input tokens$3.96 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
glm-5.2GLM 5.2chat$1.40 / 1M input tokens$4.40 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
kimi-k2.7-codeKimi K2.7 Codechat$0.95 / 1M input tokens$4.00 / 1M output tokensChat Completions, Streaming, Image input, Function callingNot publishedNot publishedNot publishedAvailable
kimi-k3Kimi K3chat$3.00 / 1M input tokens$15.00 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen-image-2.0-pro-2026-06-22Qwen Image 2.0 Pro · Jun 22imageNot applicable$0.075 / imageimageNot publishedNot publishedNot publishedAvailable
qwen-image-3.0Qwen Image 3.0imageNot applicable$0.03 / imageimageNot publishedNot publishedNot publishedAvailable
qwen-image-3.0-proQwen Image 3.0 ProimageNot applicable$0.04 / imageimageNot publishedNot publishedNot publishedAvailable
qwen-mt-image-2.0Qwen Image Translation 2.0imageNot applicable$0.0006 / imageimageNot publishedNot publishedNot publishedAvailable
qwen3.7-flashQwen 3.7 Flashchat$0.03 / 1M input tokens$0.13 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen3.7-flash-2026-07-15Qwen 3.7 Flash · Jul 15chat$0.03 / 1M input tokens$0.13 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen3.8-2.4t-a95bQwen 3.8 2.4T A95Bchat$2.00 / 1M input tokens$6.00 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen3.8-27bQwen 3.8 27Bchat$0.50 / 1M input tokens$3.00 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen3.8-flashQwen 3.8 Flashchat$0.15 / 1M input tokens$0.47 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen3.8-maxQwen 3.8 Maxchat$2.00 / 1M input tokens$6.00 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable
qwen3.8-max-0902Qwen 3.8 Max · Sep 02chat$2.00 / 1M input tokens$6.00 / 1M output tokensChat Completions, StreamingNot publishedNot publishedNot publishedAvailable

Use the public model ID shown here. Provider-native identifiers are internal routing details and are not part of the public API contract.

Usage cost vs. top-up fee

The prices above determine model usage cost. The separate payment processing fee applies only when buying prepaid credits. See Billing & Credits for the top-up formula and examples.

Was this page helpful?