Models & pricing
All prices are USD per 1 M tokens. Live tariffs: luckyapi.chat.
Anthropic — Claude
| Model | Strength | In · official | Out · official | In · ours | Out · ours |
|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Balanced default — most coding agents | $3.00 | $15.00 | $0.30 | $1.50 |
| Claude Opus 4.7 | Flagship reasoning, long sessions | $15.00 | $75.00 | $1.50 | $7.50 |
| Claude Haiku 4.5 | Fast, cheap, great for tools | $1.00 | $5.00 | $0.10 | $0.50 |
Prompt-cache reads on Claude models are billed at the upstream cache discount (≈ 0.1× input price).
OpenAI
| Model | Strength | In · official | Out · official | In · ours | Out · ours |
|---|---|---|---|---|---|
| GPT-5 | Flagship, agent-friendly | $10.00 | $30.00 | $1.00 | $3.00 |
| GPT-5 mini | Fast & cheap | $0.50 | $2.00 | $0.05 | $0.20 |
| o4-mini | Reasoning, cheap | $1.10 | $4.40 | $0.11 | $0.44 |
Google
| Model | Strength | In · official | Out · official | In · ours | Out · ours |
|---|---|---|---|---|---|
| Gemini 2.5 Pro | 1 M context, vision | $1.25 | $10.00 | $0.13 | $1.00 |
| Gemini 2.5 Flash | Fast multimodal | $0.30 | $2.50 | $0.03 | $0.25 |
Open source
DeepSeek and Qwen runs on our infrastructure — already cheap upstream, but we still pass volume savings through.
| Model | License | In · ours | Out · ours |
|---|---|---|---|
| DeepSeek V3.2 | MIT | $0.03 | $0.11 |
| DeepSeek R1 | MIT | $0.05 | $0.22 |
| Qwen 3 Coder 480B | Apache 2.0 | $0.06 | $0.24 |
| Llama 4 Maverick | Llama 4 | $0.04 | $0.16 |
Picking a model for coding
| Task | Recommended | Notes |
|---|---|---|
| Day-to-day editing in Claude Code | Sonnet 4.6 | Best speed/quality tradeoff |
| Hard refactors, architecture, debugging | Opus 4.7 | Worth the 5× cost |
| Tool calls, fast loops, agents | Haiku 4.5 | 90% of Sonnet quality at 10% cost |
| Long-context analysis (1M tokens) | Gemini 2.5 Pro | Best for whole-repo reads |
| Budget / personal projects | DeepSeek V3.2 | Surprisingly capable, dirt cheap |
How billing works
- Pay-as-you-go. No subscription, no monthly minimum.
- Top up any amount ≥ $5. Unused credit doesn't expire.
- Each request is billed at completion using the upstream provider's reported token counts.
- Run
/costinside Claude Code for a live session total. - Full history & exports at luckyapi.chat.