Best LLM APIs for Long Context Windows
LLM APIs with the largest context windows. Compare models that support 100K+ tokens for document analysis, codebase processing, and long conversations.
Cost calculator for this use case
🥇 Llama 4 Scout
$—
🥈 Llama 4 Scout
$—
🥉 Gemini 2.5 Pro
$—
Full ranking — top 15 models
| # | Model | Provider | Input $/Mtok | Output $/Mtok | Blended | Context | |
|---|---|---|---|---|---|---|---|
| 1 | Llama 4 Scout | Groq | $0.110 | $1.00 | $0.555 | 10M | → |
| 2 | Llama 4 Scout | Meta | $0.110 | $0.340 | $0.225 | 10M | → |
| 3 | Gemini 2.5 Pro | $1.25 | $10.00 | $5.63 | 2M | → | |
| 4 | Gemini 3.1 Pro | $2.00 | $12.00 | $7.00 | 2M | → | |
| 5 | Grok 4.1 Fast | xAI | $0.200 | $0.500 | $0.350 | 2M | → |
| 6 | Qwen-Flash | Alibaba | $0.115 | $0.460 | $0.288 | 1M | → |
| 7 | Qwen-Turbo | Alibaba | $0.050 | $0.200 | $0.125 | 1M | → |
| 8 | Nova Premier | Amazon | $2.50 | $12.50 | $7.50 | 1M | → |
| 9 | DeepSeek V4 Flash | DeepSeek | $0.140 | $0.280 | $0.210 | 1M | → |
| 10 | DeepSeek V4 Pro | DeepSeek | $0.435 | $0.870 | $0.652 | 1M | → |
| 11 | DeepSeek V4 Flash | Fireworks | $0.140 | $0.280 | $0.210 | 1M | → |
| 12 | DeepSeek V4 Pro | Fireworks | $1.74 | $3.48 | $2.61 | 1M | → |
| 13 | MiniMax M3 | Fireworks | $0.300 | $1.20 | $0.750 | 1M | → |
| 14 | Gemini 2.5 Flash | $0.075 | $0.300 | $0.188 | 1M | → | |
| 15 | Gemini 2.5 Flash-Lite | $0.100 | $0.400 | $0.250 | 1M | → |
How models are selected
Models with 100K+ token context windows, sorted by context size (largest first).
Prices are per million tokens (Mtok), sourced directly from official provider pricing pages and verified by our automated scraper pipeline that runs 3x daily. "Blended cost" is the average of input and output pricing — a quick proxy for typical 50/50 usage patterns.