opencode/yao
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
yao/llmprovider/presets.yml
Max af0d4edd74 feat(image): add image generation and enhanced reading capabilities 
- Introduced `image_generate` tool for generating images from text prompts, with options for specifying output file paths and image dimensions.
- Updated `image_read` functionality to allow optional provider specification for enhanced image analysis.
- Implemented new `GenerateImage` method in the LLM API for seamless integration of image generation capabilities.
- Enhanced documentation to include detailed usage examples for both image reading and generation tools.
- Updated tests to validate new image generation features and ensure robust functionality across image tools.
2026-05-06 10:59:35 +08:00

1744 lines
53 KiB
YAML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# ─── OpenRouter ─────────────────────────────────────────
- key: openrouter
name: OpenRouter
type: openai
api_url: https://openrouter.ai/api/v1/
require_key: true
default_models:
- id: openrouter-auto
model: openrouter/auto
name: Auto (Smart Route)
max_input_tokens: 2000000
capabilities: [vision, tool_calls, streaming, json]
enabled: true
- id: openrouter-pareto-code
model: openrouter/pareto-code
name: Pareto Code
max_input_tokens: 200000
capabilities: [tool_calls, streaming, json]
enabled: false
- id: openrouter-owl-alpha
model: openrouter/owl-alpha
name: Owl Alpha
max_input_tokens: 1048576
max_output_tokens: 262144
capabilities: [tool_calls, streaming, json]
enabled: false
- id: anthropic-claude-sonnet-4.6
model: anthropic/claude-sonnet-4.6
name: Claude Sonnet 4.6
max_input_tokens: 1000000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
budget_tokens: 32000
enabled: false
- id: google-gemini-3-flash-preview
model: google/gemini-3-flash-preview
name: Gemini 3 Flash
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinkingConfig:
thinkingBudget: 32768
enabled: false
- id: moonshotai-kimi-k2.6
model: moonshotai/kimi-k2.6
name: Kimi K2.6
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: moonshotai-kimi-k2.6-thinking
model: moonshotai/kimi-k2.6
name: Kimi K2.6 Thinking
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: false
- id: deepseek-deepseek-v3.2
model: deepseek/deepseek-v3.2
name: DeepSeek V3.2
max_input_tokens: 131072
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: deepseek-deepseek-v3.2-thinking
model: deepseek/deepseek-v3.2
name: DeepSeek V3.2 Thinking
max_input_tokens: 131072
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: false
- id: tencent-hy3-preview
model: tencent/hy3-preview:free
name: Hunyuan 3 Preview (Free)
max_input_tokens: 262144
max_output_tokens: 262144
capabilities: [tool_calls, streaming, json]
options:
reasoning:
level: disabled
enabled: false
- id: tencent-hy3-preview-reasoning-high
model: tencent/hy3-preview:free
name: Hunyuan 3 Preview Reasoning (Free)
max_input_tokens: 262144
max_output_tokens: 262144
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
level: high
enabled: false
- id: xiaomi-mimo-v2.5-pro
model: xiaomi/mimo-v2.5-pro
name: MiMo V2.5 Pro
max_input_tokens: 1048576
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: xiaomi-mimo-v2.5-pro-thinking
model: xiaomi/mimo-v2.5-pro
name: MiMo V2.5 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: false
- id: inclusionai-ling-2.6-1t
model: inclusionai/ling-2.6-1t:free
name: Ling 2.6 1T (Free)
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── Anthropic ──────────────────────────────────────────
- key: anthropic
name: Anthropic
type: anthropic
api_url: https://api.anthropic.com
require_key: true
default_models:
- id: claude-opus-4-7
name: Claude Opus 4.7
max_input_tokens: 1000000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: claude-opus-4-7-thinking
model: claude-opus-4-7
name: Claude Opus 4.7 Thinking
max_input_tokens: 1000000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
budget_tokens: 32000
enabled: false
- id: claude-sonnet-4-6
name: Claude Sonnet 4.6
max_input_tokens: 1000000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: true
- id: claude-sonnet-4-6-thinking
model: claude-sonnet-4-6
name: Claude Sonnet 4.6 Thinking
max_input_tokens: 1000000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
budget_tokens: 32000
enabled: false
- id: claude-haiku-4-5-20251001
name: Claude Haiku 4.5
max_input_tokens: 200000
max_output_tokens: 64000
capabilities: [vision, tool_calls, streaming, json]
enabled: true
- id: claude-haiku-4-5-thinking
model: claude-haiku-4-5-20251001
name: Claude Haiku 4.5 Thinking
max_input_tokens: 200000
max_output_tokens: 64000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
budget_tokens: 16000
enabled: false
# ─── OpenAI ─────────────────────────────────────────────
# reasoning_effort levels: low | medium | high (5.4-mini/o4-mini)
# low | medium | high | xhigh (5.5/5.4/codex/5)
- key: openai
name: OpenAI
type: openai
api_url: https://api.openai.com
require_key: true
default_models:
# --- GPT-5.5 ---
- id: gpt-5.5
name: GPT-5.5
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: gpt-5.5-reasoning-low
model: gpt-5.5
name: GPT-5.5 Reasoning (Low)
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: low
enabled: false
- id: gpt-5.5-reasoning-medium
model: gpt-5.5
name: GPT-5.5 Reasoning (Medium)
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: gpt-5.5-reasoning-high
model: gpt-5.5
name: GPT-5.5 Reasoning (High)
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- GPT-5.4 ---
- id: gpt-5.4
name: GPT-5.4
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: true
- id: gpt-5.4-reasoning-low
model: gpt-5.4
name: GPT-5.4 Reasoning (Low)
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: low
enabled: false
- id: gpt-5.4-reasoning-medium
model: gpt-5.4
name: GPT-5.4 Reasoning (Medium)
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: gpt-5.4-reasoning-high
model: gpt-5.4
name: GPT-5.4 Reasoning (High)
max_input_tokens: 1050000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- GPT-5.4 Mini ---
- id: gpt-5.4-mini
name: GPT-5.4 Mini
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: true
- id: gpt-5.4-mini-reasoning-low
model: gpt-5.4-mini
name: GPT-5.4 Mini Reasoning (Low)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: low
enabled: false
- id: gpt-5.4-mini-reasoning-medium
model: gpt-5.4-mini
name: GPT-5.4 Mini Reasoning (Medium)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: gpt-5.4-mini-reasoning-high
model: gpt-5.4-mini
name: GPT-5.4 Mini Reasoning (High)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- GPT-5.4 Nano (no thinking) ---
- id: gpt-5.4-nano
name: GPT-5.4 Nano
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
# --- GPT-5.3 Codex ---
- id: gpt-5.3-codex
name: GPT-5.3 Codex
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: gpt-5.3-codex-reasoning-medium
model: gpt-5.3-codex
name: GPT-5.3 Codex Reasoning (Medium)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: gpt-5.3-codex-reasoning-high
model: gpt-5.3-codex
name: GPT-5.3 Codex Reasoning (High)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- GPT-5 ---
- id: gpt-5
name: GPT-5
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: gpt-5-reasoning-medium
model: gpt-5
name: GPT-5 Reasoning (Medium)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: gpt-5-reasoning-high
model: gpt-5
name: GPT-5 Reasoning (High)
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- GPT-5 Mini (no thinking) ---
- id: gpt-5-mini
name: GPT-5 Mini
max_input_tokens: 400000
max_output_tokens: 128000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
# --- o4-mini (native reasoning, reasoning_effort: low|medium|high) ---
- id: o4-mini-low
model: o4-mini
name: o4-mini (Low)
max_input_tokens: 200000
max_output_tokens: 100000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: low
enabled: false
- id: o4-mini
name: o4-mini (Medium)
max_input_tokens: 200000
max_output_tokens: 100000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: o4-mini-high
model: o4-mini
name: o4-mini (High)
max_input_tokens: 200000
max_output_tokens: 100000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- o3 (native reasoning, reasoning_effort: low|medium|high) ---
- id: o3-low
model: o3
name: o3 (Low)
max_input_tokens: 200000
max_output_tokens: 100000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: low
enabled: false
- id: o3
name: o3 (Medium)
max_input_tokens: 200000
max_output_tokens: 100000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: medium
enabled: false
- id: o3-high
model: o3
name: o3 (High)
max_input_tokens: 200000
max_output_tokens: 100000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- Legacy ---
- id: gpt-4.1
name: GPT-4.1
max_input_tokens: 1047576
max_output_tokens: 32000
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: gpt-4o
name: GPT-4o
max_input_tokens: 128000
max_output_tokens: 16384
capabilities: [vision, tool_calls, streaming, json]
enabled: false
# --- Embedding ---
- id: text-embedding-3-large
name: Embedding 3 Large
max_input_tokens: 8191
capabilities: [embedding]
enabled: false
- id: text-embedding-3-small
name: Embedding 3 Small
max_input_tokens: 8191
capabilities: [embedding]
enabled: false
# --- STT ---
- id: gpt-4o-transcribe
name: GPT-4o Transcribe
capabilities: [audio]
enabled: false
- id: gpt-4o-mini-transcribe
name: GPT-4o Mini Transcribe
capabilities: [audio]
enabled: false
- id: whisper-1
name: Whisper-1
capabilities: [audio]
enabled: false
# --- TTS ---
- id: gpt-4o-mini-tts
name: GPT-4o Mini TTS
capabilities: [audio]
enabled: false
- id: tts-1
name: TTS-1
capabilities: [audio]
enabled: false
- id: tts-1-hd
name: TTS-1 HD
capabilities: [audio]
enabled: false
# --- Image Generation ---
- id: gpt-image-2
name: GPT Image 2
capabilities: [image_generation]
enabled: false
- id: gpt-image-1.5
name: GPT Image 1.5
capabilities: [image_generation]
enabled: false
- id: gpt-image-1
name: GPT Image 1
capabilities: [image_generation]
enabled: false
- id: gpt-image-1-mini
name: GPT Image 1 Mini
capabilities: [image_generation]
enabled: false
# ─── DeepSeek (OpenAI) ──────────────────────────────────
- key: deepseek
name: DeepSeek
type: openai
api_url: https://api.deepseek.com
require_key: true
default_models:
- id: deepseek-v4-pro
name: DeepSeek V4 Pro
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json]
options:
thinking:
type: disabled
enabled: false
- id: deepseek-v4-pro-thinking
model: deepseek-v4-pro
name: DeepSeek V4 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
enabled: true
- id: deepseek-v4-flash
name: DeepSeek V4 Flash
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json]
options:
thinking:
type: disabled
enabled: true
- id: deepseek-v4-flash-thinking
model: deepseek-v4-flash
name: DeepSeek V4 Flash Thinking
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
enabled: false
# ─── DeepSeek (Anthropic) ───────────────────────────────
- key: deepseek_anthropic
name: DeepSeek (Anthropic)
type: anthropic
api_url: https://api.deepseek.com/anthropic
require_key: true
default_models:
- id: deepseek-v4-pro
name: DeepSeek V4 Pro
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json]
options:
thinking:
type: disabled
enabled: false
- id: deepseek-v4-pro-thinking
model: deepseek-v4-pro
name: DeepSeek V4 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
budget_tokens: 32000
enabled: true
- id: deepseek-v4-flash
name: DeepSeek V4 Flash
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json]
options:
thinking:
type: disabled
enabled: true
- id: deepseek-v4-flash-thinking
model: deepseek-v4-flash
name: DeepSeek V4 Flash Thinking
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
budget_tokens: 32000
enabled: false
# ─── Kimi / Moonshot (International) ────────────────────
- key: kimi_intl
name: Kimi (Moonshot)
type: openai
api_url: https://api.moonshot.ai/v1/
require_key: true
default_models:
- id: kimi-k2.6
name: Kimi K2.6
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: kimi-k2.6-thinking
model: kimi-k2.6
name: Kimi K2.6 Thinking
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: kimi-k2.5
name: Kimi K2.5
max_input_tokens: 262144
max_output_tokens: 65535
capabilities: [vision, tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: kimi-k2.5-thinking
model: kimi-k2.5
name: Kimi K2.5 Thinking
max_input_tokens: 262144
max_output_tokens: 65535
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: moonshot-v1-128k
name: Moonshot V1 128K
max_input_tokens: 128000
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── Kimi / 月之暗面 (CN) ───────────────────────────────
- key: kimi_cn
name: Kimi 月之暗面
locale: zh-cn
type: openai
api_url: https://api.moonshot.cn/v1/
require_key: true
default_models:
- id: kimi-k2.6
name: Kimi K2.6
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: kimi-k2.6-thinking
model: kimi-k2.6
name: Kimi K2.6 Thinking
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: kimi-k2-thinking
name: Kimi K2 Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: kimi-k2-thinking-turbo
name: Kimi K2 Thinking Turbo
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: kimi-k2-turbo-preview
name: Kimi K2 Turbo
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── 智谱 GLM (CN) ─────────────────────────────────────
- key: zhipu_cn
name: 智谱 GLM
locale: zh-cn
type: openai
api_url: https://open.bigmodel.cn/api/paas/v4/
require_key: true
default_models:
- id: glm-5
name: GLM-5
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: glm-5-thinking
model: glm-5
name: GLM-5 Thinking
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: glm-5-turbo
name: GLM-5 Turbo
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: glm-5-turbo-thinking
model: glm-5-turbo
name: GLM-5 Turbo Thinking
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: glm-5.1
name: GLM-5.1
max_input_tokens: 202752
max_output_tokens: 65535
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: glm-5.1-thinking
model: glm-5.1
name: GLM-5.1 Thinking
max_input_tokens: 202752
max_output_tokens: 65535
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: glm-4.7
name: GLM-4.7
max_input_tokens: 202752
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: glm-4.7-thinking
model: glm-4.7
name: GLM-4.7 Thinking
max_input_tokens: 202752
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: glm-5v-turbo
name: GLM-5V Turbo
max_input_tokens: 8192
max_output_tokens: 4096
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: glm-4-flash
name: GLM-4 Flash
max_input_tokens: 128000
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── Google DeepMind (AI Studio) ────────────────────────
# thinkingConfig.thinkingBudget: 0 = disabled, 1–32768 = enabled
- key: google
name: Google DeepMind
type: openai
api_url: https://generativelanguage.googleapis.com/v1beta/openai/
require_key: true
default_models:
- id: gemini-3.1-pro-preview
model: models/gemini-3.1-pro-preview
name: Gemini 3.1 Pro
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json]
options:
thinkingConfig:
thinkingBudget: 0
enabled: false
- id: gemini-3.1-pro-thinking
model: models/gemini-3.1-pro-preview
name: Gemini 3.1 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinkingConfig:
thinkingBudget: 32768
enabled: true
- id: gemini-3-pro-preview
model: models/gemini-3-pro-preview
name: Gemini 3 Pro
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json]
options:
thinkingConfig:
thinkingBudget: 0
enabled: false
- id: gemini-3-pro-thinking
model: models/gemini-3-pro-preview
name: Gemini 3 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinkingConfig:
thinkingBudget: 32768
enabled: false
- id: gemini-3-flash-preview
model: models/gemini-3-flash-preview
name: Gemini 3 Flash
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json]
options:
thinkingConfig:
thinkingBudget: 0
enabled: false
- id: gemini-3-flash-thinking
model: models/gemini-3-flash-preview
name: Gemini 3 Flash Thinking
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinkingConfig:
thinkingBudget: 32768
enabled: false
- id: gemini-2.5-pro
model: models/gemini-2.5-pro
name: Gemini 2.5 Pro
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json]
options:
thinkingConfig:
thinkingBudget: 0
enabled: false
- id: gemini-2.5-pro-thinking
model: models/gemini-2.5-pro
name: Gemini 2.5 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
thinkingConfig:
thinkingBudget: 32768
enabled: false
- id: gemini-2.5-flash
model: models/gemini-2.5-flash
name: Gemini 2.5 Flash
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json]
options:
thinkingConfig:
thinkingBudget: 0
enabled: false
- id: gemini-2.5-flash-lite
model: models/gemini-2.5-flash-lite
name: Gemini 2.5 Flash Lite
max_input_tokens: 1048576
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json]
enabled: false
# --- Image Generation ---
- id: imagen-4
model: models/imagen-4.0-generate-001
name: Imagen 4
capabilities: [image_generation]
enabled: false
- id: imagen-4-ultra
model: models/imagen-4.0-ultra-generate-001
name: Imagen 4 Ultra
capabilities: [image_generation]
enabled: false
- id: imagen-4-fast
model: models/imagen-4.0-fast-generate-001
name: Imagen 4 Fast
capabilities: [image_generation]
enabled: false
# ─── xAI (Grok) ────────────────────────────────────────
# grok-4.x: reasoning.enabled true|false
# grok-3-mini: reasoning_effort low|high
- key: xai
name: xAI (Grok)
type: openai
api_url: https://api.x.ai/v1/
require_key: true
default_models:
- id: grok-4.3
name: Grok 4.3
max_input_tokens: 1000000
max_output_tokens: 32000
capabilities: [vision, tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: grok-4.3-thinking
model: grok-4.3
name: Grok 4.3 Thinking
max_input_tokens: 1000000
max_output_tokens: 32000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: true
- id: grok-4-1-fast-reasoning
name: Grok 4.1 Fast Reasoning
max_input_tokens: 2000000
max_output_tokens: 30000
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: false
- id: grok-4-1-fast-non-reasoning
name: Grok 4.1 Fast
max_input_tokens: 2000000
max_output_tokens: 30000
capabilities: [vision, tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: grok-3-mini-low
model: grok-3-mini
name: Grok 3 Mini (Low)
max_input_tokens: 131072
max_output_tokens: 32000
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning_effort: low
enabled: false
- id: grok-3-mini-high
model: grok-3-mini
name: Grok 3 Mini (High)
max_input_tokens: 131072
max_output_tokens: 32000
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning_effort: high
enabled: false
# --- Image Generation ---
- id: grok-imagine-image
name: Grok Imagine
capabilities: [image_generation]
enabled: false
- id: grok-imagine-image-pro
name: Grok Imagine Pro
capabilities: [image_generation]
enabled: false
- id: grok-imagine-image-quality
name: Grok Imagine Quality
capabilities: [image_generation]
enabled: false
# ─── MiniMax (International) ────────────────────────────
- key: minimax_intl
name: MiniMax
type: openai
api_url: https://api.minimaxi.chat/v1/
require_key: true
default_models:
- id: MiniMax-M2.7
name: MiniMax M2.7
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: MiniMax-M2.7-thinking
model: MiniMax-M2.7
name: MiniMax M2.7 Thinking
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: MiniMax-M2.5
name: MiniMax M2.5
max_input_tokens: 196608
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: MiniMax-Text-01
name: MiniMax Text-01 (1M)
max_input_tokens: 1000000
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
enabled: false
- id: MiniMax-M2.1
name: MiniMax M2.1
max_input_tokens: 196608
max_output_tokens: 196608
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── MiniMax (国内) ─────────────────────────────────────
- key: minimax_cn
name: MiniMax 国内
locale: zh-cn
type: openai
api_url: https://api.minimax.chat/v1/
require_key: true
default_models:
- id: MiniMax-M2.7
name: MiniMax M2.7
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: MiniMax-M2.7-thinking
model: MiniMax-M2.7
name: MiniMax M2.7 Thinking
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: MiniMax-M2.5
name: MiniMax M2.5
max_input_tokens: 196608
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
# ─── 小米 MiMo ─────────────────────────────────────────
- key: xiaomimimo
name: 小米 MiMo
locale: zh-cn
type: openai
api_url: https://api.xiaomimimo.com/v1/
require_key: true
default_models:
- id: mimo-v2.5-pro
name: MiMo V2.5 Pro
max_input_tokens: 1048576
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: mimo-v2.5-pro-thinking
model: mimo-v2.5-pro
name: MiMo V2.5 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: mimo-v2-pro
name: MiMo V2 Pro
max_input_tokens: 1048576
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: mimo-v2.5
name: MiMo V2.5
max_input_tokens: 1048576
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: mimo-v2-omni
name: MiMo V2 Omni
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: mimo-v2-flash
name: MiMo V2 Flash
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── 阶跃星辰 StepFun ──────────────────────────────────
- key: stepfun
name: 阶跃星辰
locale: zh-cn
type: openai
api_url: https://api.stepfun.com/v1/
require_key: true
default_models:
- id: step-3.5-flash
name: Step 3.5 Flash
max_input_tokens: 262144
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: step-3.5-flash-thinking
model: step-3.5-flash
name: Step 3.5 Flash Thinking
max_input_tokens: 262144
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: step-2x-large
name: Step 2X Large
max_input_tokens: 262144
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: step-3
name: Step 3
max_input_tokens: 262144
max_output_tokens: 65536
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
# ─── 硅基流动 SiliconFlow ──────────────────────────────
- key: siliconflow
name: 硅基流动
locale: zh-cn
type: openai
api_url: https://api.siliconflow.cn/v1/
require_key: true
default_models:
- id: Pro-zai-org-GLM-5.1
model: Pro/zai-org/GLM-5.1
name: GLM-5.1
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Pro-zai-org-GLM-5.1-thinking
model: Pro/zai-org/GLM-5.1
name: GLM-5.1 Thinking
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: true
- id: Pro-moonshotai-Kimi-K2.6
model: Pro/moonshotai/Kimi-K2.6
name: Kimi K2.6
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [vision, tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Pro-moonshotai-Kimi-K2.6-thinking
model: Pro/moonshotai/Kimi-K2.6
name: Kimi K2.6 Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: deepseek-ai-DeepSeek-V4-Flash
model: deepseek-ai/DeepSeek-V4-Flash
name: DeepSeek V4 Flash
max_input_tokens: 131072
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json]
enabled: false
- id: Qwen-Qwen3.5-397B-A17B
model: Qwen/Qwen3.5-397B-A17B
name: Qwen 3.5 397B
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Qwen-Qwen3.5-397B-A17B-thinking
model: Qwen/Qwen3.5-397B-A17B
name: Qwen 3.5 397B Thinking
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: Qwen-Qwen3-Coder-30B-A3B-Instruct
model: Qwen/Qwen3-Coder-30B-A3B-Instruct
name: Qwen3 Coder 30B
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Qwen-Qwen3-Coder-30B-A3B-Instruct-thinking
model: Qwen/Qwen3-Coder-30B-A3B-Instruct
name: Qwen3 Coder 30B Thinking
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: Pro-zai-org-GLM-4.7
model: Pro/zai-org/GLM-4.7
name: GLM-4.7
max_input_tokens: 204800
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Pro-zai-org-GLM-4.7-thinking
model: Pro/zai-org/GLM-4.7
name: GLM-4.7 Thinking
max_input_tokens: 204800
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: Pro-moonshotai-Kimi-K2-Thinking
model: Pro/moonshotai/Kimi-K2-Thinking
name: Kimi K2 Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: Pro-deepseek-ai-DeepSeek-V3.2
model: Pro/deepseek-ai/DeepSeek-V3.2
name: DeepSeek V3.2
max_input_tokens: 131072
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Pro-deepseek-ai-DeepSeek-V3.2-thinking
model: Pro/deepseek-ai/DeepSeek-V3.2
name: DeepSeek V3.2 Thinking
max_input_tokens: 131072
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: Qwen-Qwen3-235B-A22B
model: Qwen/Qwen3-235B-A22B
name: Qwen3 235B
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: Qwen-Qwen3-235B-A22B-thinking
model: Qwen/Qwen3-235B-A22B
name: Qwen3 235B Thinking
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: tencent-Hunyuan-A13B-Instruct
model: tencent/Hunyuan-A13B-Instruct
name: 混元 A13B
max_input_tokens: 256000
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: tencent-Hunyuan-A13B-Instruct-thinking
model: tencent/Hunyuan-A13B-Instruct
name: 混元 A13B Thinking
max_input_tokens: 256000
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: stepfun-ai-Step-3.5-Flash
model: stepfun-ai/Step-3.5-Flash
name: Step 3.5 Flash
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: stepfun-ai-Step-3.5-Flash-thinking
model: stepfun-ai/Step-3.5-Flash
name: Step 3.5 Flash Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
# --- Embedding ---
- id: BAAI-bge-m3
model: BAAI/bge-m3
name: BGE-M3
max_input_tokens: 8192
capabilities: [embedding]
enabled: false
- id: Pro-BAAI-bge-large-zh-v1.5
model: Pro/BAAI/bge-large-zh-v1.5
name: BGE Large ZH v1.5
max_input_tokens: 512
capabilities: [embedding]
enabled: false
# --- STT ---
- id: FunAudioLLM-SenseVoiceSmall
model: FunAudioLLM/SenseVoiceSmall
name: SenseVoice Small
capabilities: [audio]
enabled: false
- id: TeleAI-TeleSpeechASR
model: TeleAI/TeleSpeechASR
name: TeleSpeech ASR
capabilities: [audio]
enabled: false
# ─── 火山方舟 Volcengine ARK ───────────────────────────
# thinking.type: enabled | disabled
- key: volcengine
name: 火山方舟
locale: zh-cn
type: openai
api_url: https://ark.cn-beijing.volces.com/api/v3/
require_key: true
url_editable: true
default_models:
- id: doubao-seed-2-0-pro-260215
name: 豆包 Seed 2.0 Pro
max_input_tokens: 256000
max_output_tokens: 64000
capabilities: [tool_calls, streaming, json]
options:
thinking:
type: disabled
enabled: false
- id: doubao-seed-2-0-pro-thinking
model: doubao-seed-2-0-pro-260215
name: 豆包 Seed 2.0 Pro Thinking
max_input_tokens: 256000
max_output_tokens: 64000
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
enabled: true
- id: doubao-seed-1-6-thinking-250715
name: 豆包 Seed 1.6 Thinking
max_input_tokens: 256000
max_output_tokens: 16000
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
enabled: false
- id: doubao-seed-1-6-vision-250815
name: 豆包 Seed 1.6 Vision
max_input_tokens: 256000
max_output_tokens: 32768
capabilities: [vision, tool_calls, streaming, json]
enabled: false
- id: doubao-seed-2-0-code-preview-260215
name: 豆包 Seed 2.0 Code
max_input_tokens: 256000
max_output_tokens: 64000
capabilities: [tool_calls, streaming, json]
enabled: false
- id: doubao-pro-256k
name: 豆包 Pro 256K
max_input_tokens: 256000
max_output_tokens: 16000
capabilities: [tool_calls, streaming, json]
enabled: false
- id: kimi-k2-thinking-251104
name: Kimi K2 Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
enabled: false
- id: deepseek-v3-2-251201
name: DeepSeek V3.2
max_input_tokens: 131072
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json, reasoning]
options:
thinking:
type: enabled
enabled: false
# --- Embedding ---
- id: doubao-embedding-large-text-240915
name: 豆包 Embedding Large
max_input_tokens: 4096
capabilities: [embedding]
enabled: false
# --- 图片生成 ---
- id: doubao-seedream-5-0-260128
name: 豆包 Seedream 5.0
capabilities: [image_generation]
enabled: false
- id: doubao-seedream-4-5-251128
name: 豆包 Seedream 4.5
capabilities: [image_generation]
enabled: false
- id: doubao-seedream-4-0-250828
name: 豆包 Seedream 4.0
capabilities: [image_generation]
enabled: false
# ─── 腾讯混元 MaaS ─────────────────────────────────────
# hy3-preview: reasoning.level disabled | low | high
- key: tencent_maas
name: 腾讯混元
locale: zh-cn
type: openai
api_url: https://tokenhub.tencentmaas.com/v1/
require_key: true
default_models:
- id: hy3-preview
name: 混元 3 Preview
max_input_tokens: 262144
max_output_tokens: 262144
capabilities: [tool_calls, streaming, json]
options:
reasoning:
level: disabled
enabled: false
- id: hy3-preview-reasoning-low
model: hy3-preview
name: 混元 3 Preview Reasoning (Low)
max_input_tokens: 262144
max_output_tokens: 262144
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
level: low
enabled: false
- id: hy3-preview-reasoning-high
model: hy3-preview
name: 混元 3 Preview Reasoning (High)
max_input_tokens: 262144
max_output_tokens: 262144
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
level: high
enabled: true
- id: deepseek-v4-pro
name: DeepSeek V4 Pro
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: glm-5.1
name: GLM-5.1
max_input_tokens: 256000
max_output_tokens: 131072
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: kimi-k2.6
name: Kimi K2.6
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: deepseek-v4-flash
name: DeepSeek V4 Flash
max_input_tokens: 131072
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json]
enabled: false
- id: minimax-m2.7
name: MiniMax M2.7
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: hunyuan-turbos-latest
name: 混元 Turbo S
max_input_tokens: 128000
max_output_tokens: 8192
capabilities: [tool_calls, streaming, json]
enabled: false
# ─── NVIDIA Build ───────────────────────────────────────
- key: nvidia
name: NVIDIA Build
type: openai
api_url: https://integrate.api.nvidia.com/v1/
require_key: true
default_models:
- id: nvidia-nemotron-3-super-120b-a12b
model: nvidia/nemotron-3-super-120b-a12b
name: Nemotron 3 Super 120B
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: nvidia-nemotron-3-super-120b-a12b-thinking
model: nvidia/nemotron-3-super-120b-a12b
name: Nemotron 3 Super 120B Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: true
- id: deepseek-ai-deepseek-v4-pro
model: deepseek-ai/deepseek-v4-pro
name: DeepSeek V4 Pro
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: deepseek-ai-deepseek-v4-pro-thinking
model: deepseek-ai/deepseek-v4-pro
name: DeepSeek V4 Pro Thinking
max_input_tokens: 1048576
max_output_tokens: 384000
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: moonshotai-kimi-k2.6
model: moonshotai/kimi-k2.6
name: Kimi K2.6
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: moonshotai-kimi-k2.6-thinking
model: moonshotai/kimi-k2.6
name: Kimi K2.6 Thinking
max_input_tokens: 262142
max_output_tokens: 262142
capabilities: [vision, tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: qwen-qwen3-coder-480b-a35b-instruct
model: qwen/qwen3-coder-480b-a35b-instruct
name: Qwen3 Coder 480B
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: qwen-qwen3-coder-480b-a35b-instruct-thinking
model: qwen/qwen3-coder-480b-a35b-instruct
name: Qwen3 Coder 480B Thinking
max_input_tokens: 131072
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: nvidia-nemotron-3-nano-30b-a3b
model: nvidia/nemotron-3-nano-30b-a3b
name: Nemotron 3 Nano 30B
max_input_tokens: 262144
max_output_tokens: 228000
capabilities: [tool_calls, streaming, json]
options:
reasoning:
enabled: false
enabled: false
- id: nvidia-nemotron-3-nano-30b-a3b-thinking
model: nvidia/nemotron-3-nano-30b-a3b
name: Nemotron 3 Nano 30B Thinking
max_input_tokens: 262144
max_output_tokens: 228000
capabilities: [tool_calls, streaming, json, reasoning]
options:
reasoning:
enabled: true
enabled: false
- id: qwen-qwen3.5-397b-a17b
model: qwen/qwen3.5-397b-a17b
name: Qwen 3.5 397B
max_input_tokens: 262144
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: qwen-qwen3.5-397b-a17b-thinking
model: qwen/qwen3.5-397b-a17b
name: Qwen 3.5 397B Thinking
max_input_tokens: 262144
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: z-ai-glm-5.1
model: z-ai/glm-5.1
name: GLM-5.1
max_input_tokens: 202752
max_output_tokens: 65535
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: z-ai-glm-5.1-thinking
model: z-ai/glm-5.1
name: GLM-5.1 Thinking
max_input_tokens: 202752
max_output_tokens: 65535
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: deepseek-ai-deepseek-v3.2
model: deepseek-ai/deepseek-v3.2
name: DeepSeek V3.2
max_input_tokens: 131072
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: deepseek-ai-deepseek-v3.2-thinking
model: deepseek-ai/deepseek-v3.2
name: DeepSeek V3.2 Thinking
max_input_tokens: 131072
max_output_tokens: 65536
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: minimaxai-minimax-m2.7
model: minimaxai/minimax-m2.7
name: MiniMax M2.7
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: minimaxai-minimax-m2.7-thinking
model: minimaxai/minimax-m2.7
name: MiniMax M2.7 Thinking
max_input_tokens: 196608
max_output_tokens: 40960
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
- id: stepfun-ai-step-3.5-flash
model: stepfun-ai/step-3.5-flash
name: Step 3.5 Flash
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json]
options:
enable_thinking: false
enabled: false
- id: stepfun-ai-step-3.5-flash-thinking
model: stepfun-ai/step-3.5-flash
name: Step 3.5 Flash Thinking
max_input_tokens: 262144
max_output_tokens: 32768
capabilities: [tool_calls, streaming, json, reasoning]
options:
enable_thinking: true
enabled: false
# ─── Ollama (Local) ─────────────────────────────────────
- key: ollama
name: Ollama
type: openai
api_url: http://localhost:11434
require_key: false
url_editable: true
default_models: []
# ─── Azure OpenAI ───────────────────────────────────────
- key: azure
name: Azure OpenAI
type: openai
api_url: ""
require_key: true
url_editable: true
default_models: []
Reference in a new issue View git blame Copy permalink