Models
Public model IDs users can select from Web, API, Claude CLI, and Codex CLI.
How model IDs work
Built-in provider models are exposed through the public `conflux/` namespace. The real upstream provider is intentionally hidden from end users, so users select stable IDs such as `conflux/deepseek-v4-pro` instead of provider-specific cloud names.
The exact list returned by `/v1/models` can be narrower than this documentation. Workspace policy, API key policy, user policy, disabled models, and CLI override rules can all restrict what a specific user or key is allowed to see and run.
GET https://api.yoiyoi.xyz/v1/models
Authorization: Bearer <CONFLUX_API_KEY>System model catalog
| Model ID | Provider | Role | Context | Price / 1M tokens | Capabilities | Status / limitations |
|---|---|---|---|---|---|---|
deepseek-v4-pro bd/deepseek-v4-pro-260425 | bd | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
GLM 5.1 bd/glm-5.1 | bd | BOTH | 203Ksafe 192.8K | In $0Out $0 | TextToolsCompletionsConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
DeepSeek V4 Pro conflux/deepseek-v4-pro | Built-in | BOTH | 1.0Msafe 996.1K | In $0.435Out $0.870 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Gemma 4 31B conflux/gemma4-31b | Built-in | FUSE | 262.1Ksafe 249.0K | In $0.130Out $0.380 | TextToolsVisionFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
GLM 5.1 conflux/glm-5.1 | Built-in | BOTH | 202.8Ksafe 192.6K | In $1.05Out $3.50 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
GLM 5.2 conflux/glm-5.2 | Built-in | BOTH | 1Msafe 950K | In $0Out $0 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Kimi K2.5 conflux/kimi-k2.5 | Built-in | BOTH | 262.1Ksafe 249.0K | In $0.440Out $2.00 | TextToolsVisionFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Kimi K2.6 conflux/kimi-k2.6 | Built-in | BOTH | 262.1Ksafe 250K | In $0.7448Out $4.655 | TextToolsVisionFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Kimi K2.7 Code conflux/kimi-k2.7-code | Built-in | BOTH | 262Ksafe 248.9K | In $0Out $0 | TextToolsVisionFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
MiniMax M2.7 conflux/minimax-m2.7 | Built-in | SOURCE | 196.6Ksafe 186.8K | In $0.300Out $1.20 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
MiniMax M3 conflux/minimax-m3 | Built-in | BOTH | 512Ksafe 486.4K | In $0Out $0 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Nemotron 3 Super conflux/nemotron-3-super | Built-in | BOTH | 262.1Ksafe 249.0K | In $0.090Out $0.450 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Nemotron 3 Ultra conflux/nemotron-3-ultra | Built-in | BOTH | 262.1Ksafe 249.0K | In $0.600Out $3.60 | TextToolsFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
Qwen 3.5 397B conflux/qwen3.5-397b | Built-in | FUSE | 262.1Ksafe 249.0K | In $0.390Out $2.34 | TextToolsVisionFilesWeb searchCompletions | Enabled Runtime vision support is probed from the active Built-in route and can differ across cloud and local variants. |
glm-5.1 glm/glm-5.1 | glm | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
glm-5.2 glm/glm-5.2 | glm | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
GPT-5.3 Codex High codex/gpt-5.3-codex-high | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.3 Codex Low codex/gpt-5.3-codex-low | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.3 Codex Medium codex/gpt-5.3-codex-medium | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.3 Codex Spark High codex/gpt-5.3-codex-spark-high | GPT | BOTH | 128Ksafe 121.6K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.3 Codex Spark Low codex/gpt-5.3-codex-spark-low | GPT | BOTH | 128Ksafe 121.6K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.3 Codex Spark Medium codex/gpt-5.3-codex-spark-medium | GPT | BOTH | 128Ksafe 121.6K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.3 Codex Spark XHigh codex/gpt-5.3-codex-spark-xhigh | GPT | BOTH | 128Ksafe 121.6K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Enabled Connected-account providers require admin entitlement and active account credentials before requests can run. |
GPT-5.3 Codex XHigh codex/gpt-5.3-codex-xhigh | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 High codex/gpt-5.4-high | GPT | BOTH | 1.1Msafe 997.5K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 Low codex/gpt-5.4-low | GPT | BOTH | 1.1Msafe 997.5K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 Medium codex/gpt-5.4-medium | GPT | BOTH | 1.1Msafe 997.5K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 Mini High codex/gpt-5.4-mini-high | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 Mini Low codex/gpt-5.4-mini-low | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 Mini Medium codex/gpt-5.4-mini-medium | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 Mini XHigh codex/gpt-5.4-mini-xhigh | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.4 XHigh codex/gpt-5.4-xhigh | GPT | BOTH | 1.1Msafe 997.5K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Disabled Disabled in the system catalog. It will not be advertised until enabled by an admin. |
GPT-5.5 High codex/gpt-5.5-high | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Enabled Connected-account providers require admin entitlement and active account credentials before requests can run. |
GPT-5.5 Low codex/gpt-5.5-low | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Enabled Connected-account providers require admin entitlement and active account credentials before requests can run. |
GPT-5.5 Medium codex/gpt-5.5-medium | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Enabled Connected-account providers require admin entitlement and active account credentials before requests can run. |
GPT-5.5 XHigh codex/gpt-5.5-xhigh | GPT | BOTH | 400Ksafe 380K | In $0Out $0 | TextToolsVisionFilesWeb searchConflux compat | Enabled Connected-account providers require admin entitlement and active account credentials before requests can run. |
MiniMax-M3 minimax/minimax-m3 | minimax | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
deepseek-ai/deepseek-v4-pro nvidia/deepseek-v4-pro | nvidia | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
google/gemma-4-31b-it nvidia/gemma-4-31b-it | nvidia | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
moonshotai/kimi-k2.6 nvidia/kimi-k2.6 | nvidia | BOTH | -safe 250K | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
nvidia/llama-3.1-nemotron-ultra-253b-v1 nvidia/llama-3.1-nemotron-ultra-253b-v1 | nvidia | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
minimaxai/minimax-m2.7 nvidia/minimax-m2.7 | nvidia | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
minimaxai/minimax-m3 nvidia/minimax-m3 | nvidia | BOTH | -safe - | In $0Out $0 | TextToolsFilesConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
Nemotron 3 Super 120B A12B nvidia/nemotron-3-super-120b-a12b | nvidia | BOTH | 262Ksafe 248.9K | In $0Out $0 | TextToolsCompletionsConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
Nemotron 3 Ultra 550B A55B nvidia/nemotron-3-ultra-550b-a55b | nvidia | BOTH | 262Ksafe 248.9K | In $0Out $0 | TextToolsCompletionsConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
Qwen 3.5 397B A17B nvidia/qwen3.5-397b-a17b | nvidia | BOTH | 1Msafe 950K | In $0Out $0 | TextToolsCompletionsConflux compat | Enabled Custom OpenAI-compatible models stream through Conflux buffering unless a provider-specific passthrough adapter is added. |
Google: Gemma 4 31B (free) openrouter/gemma-4-31b-it | OpenRouter | BOTH | 262.1Ksafe 249.0K | In $0Out $0 | TextToolsVisionFiles | Enabled OpenRouter-backed models currently stream through Conflux buffering instead of direct protocol passthrough. |
NVIDIA: Nemotron 3 Super (free) openrouter/nemotron-3-super-120b-a12b | OpenRouter | BOTH | 1Msafe 950K | In $0Out $0 | TextToolsFiles | Enabled OpenRouter-backed models currently stream through Conflux buffering instead of direct protocol passthrough. |
Selection examples
Use the same public model ID in the web selector, OpenAI-compatible requests, and Anthropic-compatible CLI requests.
{
"model": "conflux/deepseek-v4-pro",
"messages": [{ "role": "user", "content": "Review this API design." }]
}claude --model conflux/minimax-m2.7 --dangerously-skip-permissions