OpenAI
gpt-oss-120b
GPT OSS 120B
High performance open-source model
- Context
- 128.0K tokens
- Output rate
- Free
Fast
Live model directory
Compare the model before you choose the model.
Search the same registry that powers AIsentrix. Every card reflects a real model ID, current access tier, context window, and output credit rate.
13
Models in the current registry
Free models use no credits. Premium rates below are approximate credits per 1,000 output tokens.
Model directory
13 models shown
Meta
llama-3.3-70b-instruct
Llama 3.3 70B Instruct
Meta's powerful open-source instruction model
- Context
- 128.0K tokens
- Output rate
- Free
Text
StepFun
step-3.7-flash
Step 3.7 Flash
StepFun sparse-MoE multimodal model — strong for coding & reasoning
- Context
- 256.0K tokens
- Output rate
- Free
VisionFast
gemini-2.5-flash
Gemini 2.5 Flash
Google's fastest model — great for everyday tasks
- Context
- 1.0M tokens
- Output rate
- ≈ 0.09 credits / 1K output
VisionFast
OpenAI
gpt-4o-mini
GPT-4o mini
OpenAI's efficient model — fast and affordable
- Context
- 128.0K tokens
- Output rate
- ≈ 0.18 credits / 1K output
VisionEfficient
DeepSeek
deepseek-chat
DeepSeek V3
DeepSeek V3 — excellent for coding and analysis
- Context
- 64.0K tokens
- Output rate
- ≈ 0.33 credits / 1K output
Code
Anthropic
claude-sonnet-4-5
Claude Sonnet 4.5
Anthropic's best balance of intelligence and speed
- Context
- 200.0K tokens
- Output rate
- ≈ 4.5 credits / 1K output
Vision
Anthropic
claude-haiku-4-5
Claude Haiku 4.5
Claude's fastest model — ideal for high-volume tasks
- Context
- 200.0K tokens
- Output rate
- ≈ 1.2 credits / 1K output
VisionFast
OpenAI
gpt-4o
GPT-4o
OpenAI's flagship multimodal model
- Context
- 128.0K tokens
- Output rate
- ≈ 3 credits / 1K output
Vision
OpenAI
gpt-4.1
GPT-4.1
GPT-4.1 — OpenAI's capable long-context model
- Context
- 1.0M tokens
- Output rate
- ≈ 2.4 credits / 1K output
Vision
gemini-2.5-pro
Gemini 2.5 Pro
Google's most capable model with 1M context
- Context
- 1.0M tokens
- Output rate
- ≈ 3 credits / 1K output
Vision
OpenAI
o3-mini
o3 mini
OpenAI's compact reasoning model
- Context
- 200.0K tokens
- Output rate
- ≈ 1.32 credits / 1K output
Reasoning
DeepSeek
deepseek-reasoner
DeepSeek R1
DeepSeek R1 — open-source chain-of-thought reasoning
- Context
- 64.0K tokens
- Output rate
- ≈ 0.66 credits / 1K output
Reasoning