Models overview
Nodaryx serves models from several providers through one unified
/v1/chat/completions endpoint. To switch models, just change the model field
to one of the model IDs below — everything else stays the same.
Choosing a model
- Free trial:
gemini-flash - Chinese / code / low cost: DeepSeek and Qwen families
- Long context: Kimi (Moonshot) large-context variants
- See each model's detail page for context length, access tier, and examples.
Available models
Google (Gemini)
- Gemini Flash-Lite Trial —
gemini-flash
DeepSeek
- DeepSeek V4 Flash —
deepseek-v4-flash - DeepSeek V4 Pro —
deepseek-v4-pro
Kimi / Moonshot
- Kimi v1 128K —
kimi-128k - Kimi v1 32K —
kimi-32k - Kimi v1 8K —
kimi-8k - Kimi v1 Auto —
kimi-auto - Kimi K2.5 —
kimi-k2.5 - Kimi K2.6 —
kimi-k2.6 - Kimi K2.7 Code —
kimi-k2.7-code - Kimi K2.7 Code Highspeed —
kimi-k2.7-code-highspeed
Qwen
- Qwen Flash —
qwen-flash - Qwen Long —
qwen-long - Qwen Max —
qwen-max - Qwen Plus —
qwen-plus - Qwen Turbo —
qwen-turbo
Access notes
Models have different access tiers (FREE / PAID / TRUSTED / ENTERPRISE). If a
call returns MODEL_NOT_ALLOWED, your account or API key doesn't have access to
that model — see Permissions & model scope.
Pricing
Catalog prices are estimates pending calibration against each provider's official rates; actual billing always follows your account usage records. Verify current official prices here:
- Google (Gemini): https://ai.google.dev/gemini-api/docs/pricing
- DeepSeek: https://api-docs.deepseek.com/quick_start/pricing
- Kimi (Moonshot): https://platform.moonshot.cn/docs/price/chat
- Qwen (Alibaba Model Studio): https://help.aliyun.com/zh/model-studio/models