Poe
Provider ID: poe
Details
SDK package@ai-sdk/openai-compatible
Models137
APIhttps://api.poe.com/v1
Links
Documentation
Auth: POE_API_KEY
Models (137)
Claude-Haiku-3
Fast Claude model for responsive assistance, classification, and lightweight agents
189,096 ctx
Claude-Haiku-3.5
Fast Claude model for responsive assistance, classification, and lightweight agents
189,096 ctx
Claude-Haiku-4.5
Fast Claude model for responsive assistance, classification, and lightweight agents
192,000 ctxreasoning
Claude-Opus-4
Flagship Claude model for deep reasoning, coding, and long-horizon agents
192,512 ctxreasoning
Claude-Opus-4.1
Flagship Claude model for deep reasoning, coding, and long-horizon agents
196,608 ctxreasoning
Claude-Opus-4.5
Flagship Claude model for deep reasoning, coding, and long-horizon agents
196,608 ctxreasoning
Claude-Opus-4.6
Flagship Claude model for deep reasoning, coding, and long-horizon agents
983,040 ctxreasoning
Claude-Opus-4.7
Flagship Claude model for deep reasoning, coding, and long-horizon agents
1,048,576 ctxreasoning
Claude-Opus-4.8
Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents
1,048,576 ctxreasoning
Claude-Sonnet-3.5
Legacy model retained for compatibility with older integrations
189,096 ctx
Claude-Sonnet-3.5-June
Legacy model retained for compatibility with older integrations
189,096 ctx
Claude-Sonnet-3.7
Balanced Claude model for coding, analysis, agent workflows, and cost control
196,608 ctxreasoning
Claude-Sonnet-4
Balanced Claude model for coding, analysis, agent workflows, and cost control
983,040 ctxreasoning
Claude-Sonnet-4.5
Balanced Claude model for coding, analysis, agent workflows, and cost control
983,040 ctxreasoning
Claude-Sonnet-4.6
Balanced Claude model for coding, analysis, agent workflows, and cost control
983,040 ctxreasoning
GPT-OSS-120B-CS
Open-weight GPT model for self-hosted reasoning and instruction-following workloads
128,000 ctxreasoning
Llama-3.1-8B-CS
Open Llama instruction model for multilingual chat, reasoning, and coding
128,000 ctx
llama-3.3-70b-cs
Legacy model retained for compatibility with older integrations
0
qwen3-235b-2507-cs
Legacy model retained for compatibility with older integrations
0reasoning
qwen3-32b-cs
Legacy model retained for compatibility with older integrations
0reasoning
ElevenLabs-Music
Speech generation model for controllable voice, narration, and audio delivery
2,000 ctx
ElevenLabs-v2.5-Turbo
Speech generation model for controllable voice, narration, and audio delivery
128,000 ctx
ElevenLabs-v3
Speech generation model for controllable voice, narration, and audio delivery
128,000 ctx
DeepSeek-V4-Flash-EL
Fast DeepSeek model for efficient chat, coding help, and agent loops
1,000,000 ctxreasoning
DeepSeek-V4-Pro-EL
Flagship DeepSeek model for coding, reasoning, and agentic work
1,000,000 ctxreasoning
Kimi-K2.5-FW
Kimi multimodal agent model for visual understanding, coding, and planning
262,144 ctx
Gemini-2.0-Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
990,000 ctx
Gemini-2.0-Flash-Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
990,000 ctx
Gemini-2.5-Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,065,535 ctxreasoning
Gemini-2.5-Flash-Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
1,024,000 ctxreasoning
Gemini-2.5-Pro
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,065,535 ctxreasoning
Gemini-3-Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 ctxreasoning
Gemini-3-Pro
Legacy model retained for compatibility with older integrations
1,048,576 ctxreasoning
Gemini-3.1-Flash-Lite
Low-latency Gemini model for high-volume multimodal and agent workloads
1,048,576 ctxreasoning
Gemini-3.1-Pro
Advanced Gemini model for complex reasoning, coding, and multimodal analysis
1,048,576 ctxreasoning
Gemini-3.5-Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
1,048,576 ctxreasoning
gemini-deep-research
Legacy model retained for compatibility with older integrations
1,048,576 ctxreasoning
Gemma-4-31B
Open Gemma instruction model for efficient chat and self-hosted deployments
262,144 ctx
Imagen-3
Image model for prompt-driven generation, editing, and visual design workflows
480 ctx
Imagen-3-Fast
Image model for prompt-driven generation, editing, and visual design workflows
480 ctx
Imagen-4
Image model for prompt-driven generation, editing, and visual design workflows
480 ctx
Imagen-4-Fast
Image model for prompt-driven generation, editing, and visual design workflows
480 ctx
Imagen-4-Ultra
Image model for prompt-driven generation, editing, and visual design workflows
480 ctx
Lyria
Speech generation model for controllable voice, narration, and audio delivery
0
Nano-Banana
Image model for prompt-driven generation, editing, and visual design workflows
65,536 ctx
Nano-Banana-Pro
Image model for prompt-driven generation, editing, and visual design workflows
65,536 ctx
Veo-2
Video model for prompt-guided generation, editing, and motion workflows
480 ctx
Veo-3
Video model for prompt-guided generation, editing, and motion workflows
480 ctx
Veo-3-Fast
Video model for prompt-guided generation, editing, and motion workflows
480 ctx
Veo-3.1
Video model for prompt-guided generation, editing, and motion workflows
480 ctx
Veo-3.1-Fast
Video model for prompt-guided generation, editing, and motion workflows
480 ctx
Ideogram
Image model for prompt-driven generation, editing, and visual design workflows
150 ctx
Ideogram-v2
Image model for prompt-driven generation, editing, and visual design workflows
150 ctx
Ideogram-v2a
Image model for prompt-driven generation, editing, and visual design workflows
150 ctx
Ideogram-v2a-Turbo
Image model for prompt-driven generation, editing, and visual design workflows
150 ctx
Ray2
Video model for prompt-guided generation, editing, and motion workflows
5,000 ctx
DeepSeek-V3.2
DeepSeek chat model for instruction following, coding, and analysis
128,000 ctxreasoning
GLM-4.6
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
0
glm-4.6v
GLM vision model for visual reasoning, documents, and multimodal agents
131,000 ctxreasoning
glm-4.7
Legacy model retained for compatibility with older integrations
205,000 ctxreasoning
glm-4.7-flash
Efficient GLM model for fast reasoning, coding, and agent workflows
200,000 ctxreasoning
glm-4.7-n
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
205,000 ctxreasoning
GLM-5
Flagship GLM model for hybrid reasoning, coding, and agentic engineering
205,000 ctxreasoning
kimi-k2-thinking
Kimi reasoning model for long-horizon research, planning, and tool use
256,000 ctxreasoning
Kimi-K2.5
Kimi multimodal agent model for visual understanding, coding, and planning
128,000 ctxreasoning
Kimi-K2.6
Kimi multimodal agent model for visual understanding, coding, and planning
262,144 ctxreasoning
minimax-m2.1
MiniMax model for chat, coding, office work, and agentic tasks
205,000 ctxreasoning
ChatGPT-4o-Latest
Legacy model retained for compatibility with older integrations
128,000 ctx
DALL-E-3
Image model for prompt-driven generation, editing, and visual design workflows
800 ctx
GPT-3.5-Turbo
Compact GPT model for low-latency assistance and high-volume workloads
16,384 ctx
GPT-3.5-Turbo-Instruct
Compact GPT model for low-latency assistance and high-volume workloads
3,500 ctx
GPT-3.5-Turbo-Raw
Compact GPT model for low-latency assistance and high-volume workloads
4,524 ctx
GPT-4-Classic
Legacy model retained for compatibility with older integrations
8,192 ctx
GPT-4-Classic-0314
Legacy model retained for compatibility with older integrations
8,192 ctx
GPT-4-Turbo
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-4.1
GPT model for general reasoning, writing, coding, and tool-assisted tasks
1,047,576 ctx
GPT-4.1-mini
Compact GPT model for low-latency assistance and high-volume workloads
1,047,576 ctx
GPT-4.1-nano
Compact GPT model for low-latency assistance and high-volume workloads
1,047,576 ctx
GPT-4o
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT-4o-Aug
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT-4o-mini
Compact GPT model for low-latency assistance and high-volume workloads
124,096 ctx
GPT-4o-mini-Search
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-4o-Search
GPT model for general reasoning, writing, coding, and tool-assisted tasks
128,000 ctx
GPT-5
GPT model for general reasoning, writing, coding, and tool-assisted tasks
400,000 ctxreasoning
GPT-5-Chat
Chat-tuned GPT model for conversational assistance, writing, and tool workflows
128,000 ctx
GPT-5-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT-5-mini
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT-5-nano
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT-5-Pro
Frontier GPT model for professional reasoning, coding, and multimodal work
400,000 ctxreasoning
GPT-5.1
GPT model for general reasoning, writing, coding, and tool-assisted tasks
400,000 ctxreasoning
GPT-5.1-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT-5.1-Codex-Max
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT-5.1-Codex-Mini
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT-5.1-Instant
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctxreasoning
GPT-5.2
GPT model for general reasoning, writing, coding, and tool-assisted tasks
400,000 ctxreasoning
GPT-5.2-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT-5.2-Instant
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-5.2-Pro
Frontier GPT model for professional reasoning, coding, and multimodal work
400,000 ctxreasoning
GPT-5.3-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
400,000 ctxreasoning
GPT-5.3-Codex-Spark
Coding-optimized GPT model for repository edits, reviews, and agentic software work
128,000 ctxreasoning
GPT-5.3-Instant
Compact GPT model for low-latency assistance and high-volume workloads
128,000 ctx
GPT-5.4
Image model for prompt-driven generation, editing, and visual design workflows
1,050,000 ctxreasoning
GPT-5.4-Mini
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT-5.4-Nano
Compact GPT model for low-latency assistance and high-volume workloads
400,000 ctxreasoning
GPT-5.4-Pro
Image model for prompt-driven generation, editing, and visual design workflows
1,050,000 ctxreasoning
GPT-5.5
Default frontier GPT for coding, computer use, research, and knowledge work
400,000 ctxreasoning
GPT-5.5-Pro
Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding
400,000 ctxreasoning
GPT-Image-1
Image model for prompt-driven generation, editing, and visual design workflows
128,000 ctx
GPT-Image-1-Mini
Image model for prompt-driven generation, editing, and visual design workflows
0
gpt-image-1.5
Image model for prompt-driven generation, editing, and visual design workflows
128,000 ctx
GPT-Image-2
Image model for prompt-driven generation, editing, and visual design workflows
0
o1
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o1-pro
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o3
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o3-deep-research
Research model for long-horizon investigation, synthesis, and analytical reports
200,000 ctxreasoning
o3-mini
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o3-mini-high
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o3-pro
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o4-mini
O-series reasoning model for hard analysis, math, coding, and planning
200,000 ctxreasoning
o4-mini-deep-research
Research model for long-horizon investigation, synthesis, and analytical reports
200,000 ctxreasoning
Sora-2
Video model for prompt-guided generation, editing, and motion workflows
0
Sora-2-Pro
Video model for prompt-guided generation, editing, and motion workflows
0
claude-code
Claude model for careful reasoning, writing, coding, and tool use
0reasoning
Runway
Video model for prompt-guided generation, editing, and motion workflows
256 ctx
Runway-Gen-4-Turbo
Video model for prompt-guided generation, editing, and motion workflows
256 ctx
StableDiffusionXL
Image model for prompt-driven generation, editing, and visual design workflows
200 ctx
TopazLabs
Image model for prompt-driven generation, editing, and visual design workflows
204 ctx
Tako
Tool-capable chat model for instruction following and agentic application workflows
2,048 ctx
Grok 3
Grok model for agentic tool use, reasoning, coding, and live assistance
131,072 ctx
Grok 3 Mini
Fast Grok model for responsive chat, reasoning, and tool-assisted work
131,072 ctxreasoning
Grok-4
Grok model for agentic tool use, reasoning, coding, and live assistance
256,000 ctxreasoning
Grok-4-Fast-Non-Reasoning
Fast Grok model for responsive chat, reasoning, and tool-assisted work
2,000,000 ctx
Grok-4-Fast-Reasoning
Fast Grok model for responsive chat, reasoning, and tool-assisted work
2,000,000 ctxreasoning
Grok-4.1-Fast-Non-Reasoning
Fast Grok model for responsive chat, reasoning, and tool-assisted work
2,000,000 ctx
Grok-4.1-Fast-Reasoning
Fast Grok model for responsive chat, reasoning, and tool-assisted work
2,000,000 ctxreasoning
Grok-4.20-Multi-Agent
Grok model for agentic tool use, reasoning, coding, and live assistance
128,000 ctx
Grok Code Fast 1
Fast Grok model for responsive chat, reasoning, and tool-assisted work
256,000 ctxreasoning
Community Rating
—
No ratings yet
Sign in to rate