Compare pricing, context windows, and capabilities across all major AI models. Updated February 2026.
💰 Quick Cost Calculator
Estimate your monthly API costs:
📊 Output Cost Comparison ($/1M tokens)
📏 Context Window Comparison
🚀 Frontier Models (February 2026)
Anthropic Claude
| Model | Context | Input $/M | Output $/M | Best For |
|---|---|---|---|---|
| Claude Opus 4.6 NEW | 200K | $15.00 | $75.00 | Research, complex analysis |
| Claude Opus 4.5 BEST OVERALL | 200K | $15.00 | $75.00 | Extended thinking, agentic |
| Claude Sonnet 4 | 200K | $3.00 | $15.00 | Balanced performance/cost |
| Claude Haiku 3.5 | 200K | $0.80 | $4.00 | Fast, lightweight |
OpenAI
| Model | Context | Input $/M | Output $/M | Best For |
|---|---|---|---|---|
| GPT-4.1 NEW | 1M | $2.00 | $8.00 | Long context, coding |
| GPT-4o | 128K | $2.50 | $10.00 | Multimodal, balanced |
| GPT-4o-mini | 128K | $0.15 | $0.60 | Cost-effective |
| o3 | 200K | $10.00 | $40.00 | Advanced reasoning |
| o4-mini | 200K | $1.10 | $4.40 | Reasoning on budget |
| Model | Context | Input $/M | Output $/M | Best For |
|---|---|---|---|---|
| Gemini 2.5 Pro BEST CONTEXT | 1M | $1.25 | $5.00 | Long context, multimodal |
| Gemini 2.5 Flash | 1M | $0.075 | $0.30 | Fast, cost-effective |
xAI / DeepSeek / Mistral
| Model | Context | Input $/M | Output $/M | Best For |
|---|---|---|---|---|
| Grok 3 | 131K | $3.00 | $15.00 | Real-time info, X integration |
| DeepSeek V3 BEST VALUE | 64K | $0.27 | $1.10 | Open weights, coding |
| DeepSeek R1 | 64K | $0.55 | $2.19 | Reasoning, math |
| Mistral Large 2 | 128K | $2.00 | $6.00 | Enterprise, multilingual |
🖥️ Local/Open Models
Run on your own hardware. No API costs, full privacy.
| Model | Parameters | VRAM (Full) | VRAM (Q4) | Best For |
|---|---|---|---|---|
| Llama 3.3 70B OPEN | 70B | 140GB | ~40GB | Strong reasoning |
| Qwen 2.5 72B OPEN | 72B | 144GB | ~42GB | Multilingual, coding |
| Qwen 2.5 14B | 14B | 28GB | ~9GB | M1/M2 Macs |
| Kimi K2 NEW | 1T MoE | ~500GB | ~150GB | Frontier-class local |
| Phi-4 14B | 14B | 28GB | ~9GB | Reasoning, math |
🎯 Quick Recommendations
🏆 Best Overall
Claude Opus 4.5 — Highest capability for complex tasks.
💰 Best Value
DeepSeek V3 — Near-frontier at 10x lower cost.
📚 Best Long Context
Gemini 2.5 Pro — 1M tokens handles codebases.
🖥️ Best Local
Qwen 2.5 14B — Runs on M1/M2 Macs.