AI Models

52 models · 0 new in 60d

Compare →
Sort
NewestA→Z
Type
AllFlagshipSmallReasoningCodeEmbeddingImageVision
License
AllOpenClosed
  • o3

    OpenAI · 200K tokens · $2/M → $8/M

    ▾

    Best for: Hard math, science, multi-step planning, complex debugging

    How: Use reasoning_effort param: 'low'/'medium'/'high'. No system prompt — use developer message instead.

    Example: Debug a distributed system deadlock by feeding it the full trace + architecture.

    GPQA Diamond 79.7%AIME 2024 96.7%SWE-bench 69.1%
    reasoningmathscienceplanning

    API: api.openai.com — same SDK, just model='o3'

  • o4-mini

    OpenAI · 200K tokens · $1.10/M → $4.40/M

    ▾

    Best for: Coding with reasoning, moderate-complexity math, budget reasoning

    How: Cheaper reasoning model. Use when o3 is overkill but you need chain-of-thought.

    Example: Generate a migration plan for a database schema change with safety checks.

    AIME 2024 93.4%SWE-bench 68.1%
    reasoningcodingcost-efficient reasoning

    API: api.openai.com — same SDK

  • Grok 3 mini

    xAI · 128K tokens · $0.30/M → $0.50/M

    ▾

    Best for: Budget reasoning tasks, math, lightweight chain-of-thought

    How: Excellent cost-to-reasoning ratio. Use reasoning_effort param.

    Example: Validate Terraform plans with reasoning about dependency chains for pennies.

    fast reasoningvery cheapmath

    API: api.x.ai — same as Grok 3

  • DeepSeek R1Open

    DeepSeek · 128K tokens · self-host

    ▾

    Best for: Budget reasoning, self-hosted chain-of-thought, research

    How: API is OpenAI-compatible. Self-host the 70B distill on 2x A100. MIT license = no restrictions.

    Example: Run the 14B distill locally for debugging complex distributed system issues.

    AIME 2024 79.8%SWE-bench 49.2%GPQA Diamond 71.5%
    reasoningmathcodingMIT licensedistillable
    Hardware to self-host
    VRAM: 10GB (14B distill) / 48GB (70B distill) / 1TB+ (full 671B)
    GPU: RTX 4090 (14B) · 2× A100 (70B) · 8× H100 (full)
    RAM: Full model needs 256GB+ system RAM

    Full 671B MoE is massive. Distilled versions (14B, 32B, 70B) are far more practical.

    API: api.deepseek.com ($0.55/M in, $2.19/M out) OR self-host via vLLM/Ollama

  • GPT-Rosalind

    OpenAI · N/A · api

    ▾

    Best for: life sciences research

    How: N/A

    Example: N/A

    accelerate drug discoverygenomics analysisprotein reasoningscientific research workflows

    Auto-discovered from news articles.