Personal Trader
MODELS.
Brain models available for Personal Trader: provider pricing, intelligence scores, and internal speed benchmarks.
Personal Trader's main brain is a large language model you pick during setup. Each model trades off intelligence, response speed, and cost. Higher intelligence models tend to reason more deeply on complex strategies; faster models react quicker on short timeframes; cheaper models stretch your credits further.
Available models change often in this industry, new models launch and older ones get deprecated. We update the Personal Trader dashboard as soon as changes land. This docs list may already be outdated. For the source of truth, check the model picker in your Personal Trader dashboard.
1.How we score models
- Intelligence (1–100): a composite score derived from many popular public LLM benchmark tests. Higher means stronger general reasoning and instruction-following for trading decisions.
- Speed (ms): median response time from our internal tests, measured in milliseconds. Lower is faster.
- Pricing: per-million-token rates for model input and output. Actual credit use per decision cycle also depends on your strategy, analysis modules, and timeframe.
2.Available models
Sorted roughly from highest-tier pricing downward. Compare intelligence and speed against your budget and how actively your trader runs.
| # | Provider | Model | Input ($/M) | Output ($/M) | Intelligence | Speed |
|---|---|---|---|---|---|---|
| 1 | OpenAI | GPT-5.4 Pro | $30 | $180 | 96 | 21,572 ms |
| 2 | OpenAI | GPT-5.5 Pro | $30 | $180 | 96 | 16,931 ms |
| 3 | Anthropic | Claude Opus 4.8 Fast | $10 | $50 | 88 | 3,642 ms |
| 4 | OpenAI | GPT-5.5 | $5 | $30 | 85 | 9,857 ms |
| 5 | Anthropic | Claude Opus 4.6 | $5 | $25 | 92 | 13,762 ms |
| 6 | Anthropic | Claude Opus 4.7 | $5 | $25 | 93 | 10,985 ms |
| 7 | Anthropic | Claude Opus 4.8 | $5 | $25 | 94 | 9,803 ms |
| 8 | Anthropic | Claude Sonnet 4.6 | $3 | $15 | 80 | 9,099 ms |
| 9 | OpenAI | GPT-5.4 | $2.5 | $15 | 85 | 7,251 ms |
| 10 | OpenAI | GPT-4o | $2.5 | $10 | 76 | 3,128 ms |
| 11 | Gemini 3.1 Pro Preview | $2 | $12 | 86 | 7,579 ms | |
| 12 | OpenAI | GPT-5.3 Chat | $1.75 | $14 | 82 | 5,995 ms |
| 13 | OpenAI | GPT-5.3 Codex | $1.75 | $14 | 83 | 10,293 ms |
| 14 | Mistral | Mistral Medium 3.5 | $1.5 | $7.5 | 76 | 4,808 ms |
| 15 | xAI | Grok 4.20 | $1.25 | $2.5 | 80 | 4,493 ms |
| 16 | xAI | Grok 4.3 | $1.25 | $2.5 | 78 | 11,168 ms |
| 17 | Perplexity | Sonar | $1 | $1 | 64 | 4,774 ms |
| 18 | Amazon | Nova Pro 1.0 | $0.8 | $3.2 | 71 | 2,129 ms |
| 19 | OpenAI | GPT-5.4 Mini | $0.75 | $4.5 | 68 | 3,344 ms |
| 20 | Moonshot AI | Kimi K2.6 | $0.75 | $3.5 | 75 | 2,729 ms |
| 21 | Moonshot AI | Kimi K2.7 Code | $0.75 | $3.5 | 77 | 8,344 ms |
| 22 | Gemini 3 Flash Preview | $0.5 | $3 | 72 | 4,450 ms | |
| 23 | Mistral | Mistral Large 3 2512 | $0.5 | $1.5 | 74 | 5,671 ms |
| 24 | Moonshot AI | Kimi K2.5 | $0.45 | $2 | 72 | 42,847 ms |
| 25 | Baidu | ERNIE 4.5 VL | $0.42 | $1.25 | 75 | 8,600 ms |
| 26 | Mistral | Mistral Medium 3.1 | $0.4 | $2 | 70 | 11,704 ms |
| 27 | Qwen | Qwen3.6 Plus | $0.325 | $1.95 | 76 | 82,008 ms |
| 28 | Qwen | Qwen3.7 Plus | $0.32 | $1.28 | 78 | 57,534 ms |
| 29 | Gemini 2.5 Flash | $0.3 | $2.5 | 68 | 3,250 ms | |
| 30 | Qwen | Qwen3.5 Plus | $0.3 | $1.8 | 70 | 59,756 ms |
| 31 | MiniMax | MiniMax M3 | $0.3 | $1.2 | 70 | 11,036 ms |
| 32 | Z.ai | GLM 4.6V | $0.3 | $0.9 | 72 | 9,048 ms |
| 33 | Qwen | Qwen3 VL 235B Thinking | $0.26 | $2.6 | 78 | 66,935 ms |
| 34 | ByteDance | Seed 1.6 | $0.25 | $2 | 62 | 39,316 ms |
| 35 | ByteDance | Seed 2.0 Lite | $0.25 | $2 | 64 | 32,580 ms |
| 36 | Gemini 3.1 Flash Lite Preview | $0.25 | $1.5 | 58 | 3,513 ms | |
| 37 | Qwen | Qwen2.5 VL 72B | $0.25 | $0.75 | 68 | 10,008 ms |
| 38 | OpenAI | GPT-5.4 Nano | $0.2 | $1.25 | 52 | 2,895 ms |
| 39 | Qwen | Qwen3 VL 235B Instruct | $0.2 | $0.88 | 74 | 9,983 ms |
| 40 | Qwen | Qwen3.6 35B | $0.15 | $1 | 60 | 17,599 ms |
| 41 | OpenAI | GPT-4o Mini | $0.15 | $0.6 | 62 | 4,570 ms |
| 42 | Meta | Llama 4 Maverick | $0.15 | $0.6 | 68 | 8,456 ms |
| 43 | Qwen | Qwen3 VL 30B Instruct | $0.13 | $0.52 | 66 | 8,649 ms |
| 44 | Qwen | Qwen3 VL 32B Instruct | $0.1 | $0.42 | 65 | 5,575 ms |
| 45 | Gemini 2.5 Flash Lite | $0.1 | $0.4 | 55 | 2,016 ms | |
| 46 | Qwen | Qwen3 VL 8B Instruct | $0.08 | $0.5 | 52 | 6,420 ms |
| 47 | ByteDance | Seed 1.6 Flash | $0.075 | $0.3 | 54 | 8,845 ms |
| 48 | Gemma 4 26B | $0.06 | $0.33 | 58 | 19,764 ms |
Prices are per million tokens. Intelligence is scored 1–100. Speed is median latency from Yeagers internal tests.