Available Model List
This page lists current mainstream AI provider models and capabilities for lookup and integration. For pricing, see Model Pricing.
Model Notes
- The system uses the latest available models from each AI provider by default
- Different API keys are mapped to different provider groups
- Model availability depends on group authorization
- Model calls stay highly compatible with official APIs
Available Model List (Updated Daily)
OpenAI (GPT Series)
Focuses on deep reasoning and native multimodal capabilities, evolving towards strong logic and complex system coordination.
| Model Name | Max Input / Output Tokens | Operating Mode | OpenAI Protocol |
|---|---|---|---|
| gpt-6.1-sol | 922K / 128K | chat | ✅ Supported |
| gpt-6-sol | 922K / 128K | chat | ✅ Supported |
| gpt-6-luna | 922K / 128K | chat | ✅ Supported |
| gpt-6-astra | 922K / 128K | chat | ✅ Supported |
| gpt-5.6-sol | 1050K / 128K | chat | ✅ Supported |
| gpt-5.6-terra | 1050K / 128K | chat | ✅ Supported |
| gpt-5.6-luna | 1050K / 128K | chat | ✅ Supported |
| gpt-5.5 | 1050K / 128K | chat | ✅ Supported |
| gpt-5.4-mini | 400K / 128K | chat | ✅ Supported |
| gpt-5.3-codex-spark | 272K / 128K | chat | ✅ Supported |
| gpt-image-2.5-flare | - / - | image_generation | ✅ Supported |
| gpt-image-2.5-sunburst | - / - | image_generation | ✅ Supported |
| gpt-image-2-medium | - / - | image_generation | ✅ Supported |
| gpt-image-1.5 | - / - | image_generation | ✅ Supported |
| gpt-image-1 | - / - | image_generation | ✅ Supported |
Anthropic (Claude 4 Family)
Focuses on long-text fidelity, elegant code architecture, and highly human-like natural writing style.
| Model Name | Max Input / Output Tokens | Operating Mode | OpenAI Protocol |
|---|---|---|---|
| claude-fable-5-1 | 1000K / 128K | chat | ✅ Supported |
| claude-fable-5 | 1000K / 128K | chat | ✅ Supported |
| claude-opus-5-5 | 1000K / 128K | chat | ✅ Supported |
| claude-opus-5 | 1000K / 128K | chat | ✅ Supported |
| claude-opus-4-8 | 1000K / 128K | chat | ✅ Supported |
| claude-opus-4-7 | 1000K / 128K | chat | ✅ Supported |
| claude-opus-4-6 | 1000K / 128K | chat | ✅ Supported |
| claude-sonnet-5-5 | 1000K / 128K | chat | ✅ Supported |
| claude-sonnet-5 | 1000K / 128K | chat | ✅ Supported |
| claude-sonnet-4-6 | 1000K / 64K | chat | ✅ Supported |
| claude-haiku-4-5-20251001 | 200K / 64K | chat | ✅ Supported |
Google (Gemini 3 Series)
Focuses on native ultra-large context throughput, deep web search (Deep Research), and Google ecosystem integration.
| Model Name | Max Input / Output Tokens | Operating Mode | OpenAI Protocol |
|---|---|---|---|
| gemini-3.8-flash | 1048K / 65K | chat | ✅ Supported |
| gemini-3.7-flash | 1048K / 65K | chat | ✅ Supported |
| gemini-3.6-flash | 1048K / 65K | chat | ✅ Supported |
| gemini-3.5-flash | 1048K / 65K | chat | ✅ Supported |
| gemini-3.5-flash-lite | 1048K / 65K | chat | ✅ Supported |
| gemini-3.1-flash-lite | 1048K / 65K | chat | ✅ Supported |
| gemini-3.1-pro-preview | 1048K / 65K | chat | ✅ Supported |
| gemini-3-flash-preview | 1048K / 65K | chat | ✅ Supported |
| gemini-2.5-flash | 1048K / 65K | chat | ✅ Supported |
| gemini-2.5-flash-lite | 1048K / 65K | chat | ✅ Supported |
| gemini-2.5-pro | 1048K / 65K | chat | ✅ Supported |
| gemini-3.1-flash-image | 131K / 32K | image_generation | ⚠️ Native only |
| gemini-3.1-flash-lite-image | 65K / 4K | image_generation | ⚠️ Native only |
| gemini-3.1-flash-image-preview | 65K / 32K | image_generation | ⚠️ Native only |
| gemini-3-pro-image | 65K / 32K | image_generation | ⚠️ Native only |
| gemini-3-pro-image-preview | 65K / 32K | image_generation | ⚠️ Native only |
| gemini-2.5-flash-image | 32K / 32K | image_generation | ⚠️ Native only |
xAI (Grok Series)
Focuses on long-context multimodal reasoning, tool use, and web-assisted workflows for complex Q&A, code analysis, and research tasks.
| Model Name | Max Input / Output Tokens | Operating Mode | OpenAI Protocol |
|---|---|---|---|
| grok-4.5 | 500K / 500K | chat | ✅ Supported |
| grok-4.3 | 1000K / 1000K | chat | ✅ Supported |
Notes
- "OpenAI Protocol" column: ✅ means callable via OpenAI-compatible endpoints (e.g.
/v1/chat/completions); ⚠️ Native only means Google native:generateContentonly (Gemini image models) — generating images via OpenAIchat/completionssilently drops the image and still bills output tokens. - Gemini image models (6 current IDs, including compatibility aliases, with names containing
-image) support the native protocol only:gemini-2.5-flash-image,gemini-3-pro-image,gemini-3-pro-image-preview,gemini-3.1-flash-image,gemini-3.1-flash-image-preview, andgemini-3.1-flash-lite-image. Generating images via OpenAI/v1/chat/completions"falsely succeeds" — it returns HTTP 200 but the image is silently dropped while output tokens are still billed; use Google's native:generateContentfor image generation instead. - The Gemini list was checked against the current platform inventory on 2026-08-24 and is updated daily around 08:00 Beijing time. For real-time availability, use the Available Models API.
- Model names and capabilities stay aligned with official APIs
- New models are added when released