Models are sorted by context window size. Use this page when your workflow needs long documents, large retrieval payloads, or multi-file context.
Best LLM API Models for RAG
RAG workloads often need enough context for retrieved passages plus economical input pricing. This page starts with large context windows and practical cost signals.
50Models listed
1M input + 500K outputCost example tokens
USD / 1MNormalized prices
Quick shortlist
Start with Llama 4 Scout.
This guide is sorted by context window, so the first rows are the strongest starting point for RAG, long documents, and large codebase context.
The ranking is a discovery aid, not a final recommendation. Always compare the model against your workload and verify provider pricing before production use.
Model Ranking
Browse all models| Model | Provider | Prompt | Output | Sample cost | Your Cost | Context | Popularity | Release |
|---|---|---|---|---|---|---|---|---|
| Llama 4 Scout | Meta | $0.1 | $0.3 | $0.25 | $0.25 | 10M | ||
| Grok 4.20 | xAI | $1.25 | $2.5 | $2.5 | $2.5 | 2M | #88 | |
| Grok 4.20 Multi-Agent | xAI | $1.25 | $2.5 | $2.5 | $2.5 | 2M | #155 | |
| 🔥GPT-5.5 | OpenAI | $5 | $30 | $20 | $20 | 1.05M | #19 | |
| GPT-5.4 | OpenAI | $2.5 | $15 | $10 | $10 | 1.05M | #30 | |
| GPT-5.5 Pro | OpenAI | $30 | $180 | $120 | $120 | 1.05M | #161 | |
| GPT-5.4 Pro | OpenAI | $30 | $180 | $120 | $120 | 1.05M | #251 | |
| OpenAI GPT Latest | OpenAI | $5 | $30 | $20 | $20 | 1.05M | ||
| 🔥Owl Alpha | OpenRouter | $0 | $0 | $0 | $0 | 1.05M | #7 | |
| Gemini 3.1 Pro Preview Custom Tools | $2 | $12 | $8 | $8 | 1.05M | #120 | ||
| 🔥DeepSeek V4 Flash | DeepSeek | $0.09 | $0.18 | $0.18 | $0.18 | 1.05M | #1 | |
| 🔥MiMo-V2.5 | Xiaomi | $0.105 | $0.28 | $0.24 | $0.24 | 1.05M | #3 | |
| New🔥MiniMax M3 | MiniMax | $0.3 | $1.2 | $0.9 | $0.9 | 1.05M | #4 | |
| 🔥DeepSeek V4 Pro | DeepSeek | $0.435 | $0.87 | $0.87 | $0.87 | 1.05M | #5 | |
| 🔥Gemini 3 Flash Preview | $0.5 | $3 | $2 | $2 | 1.05M | #10 | ||
| 🔥Gemini 2.5 Flash | $0.3 | $2.5 | $1.55 | $1.55 | 1.05M | #13 | ||
| 🔥Gemini 2.5 Flash Lite | $0.1 | $0.4 | $0.3 | $0.3 | 1.05M | #15 | ||
| 🔥Gemini 3.5 Flash | $1.5 | $9 | $6 | $6 | 1.05M | #16 | ||
| 🔥MiMo-V2.5-Pro | Xiaomi | $0.435 | $0.87 | $0.87 | $0.87 | 1.05M | #17 | |
| 🔥Gemini 3.1 Flash Lite | $0.25 | $1.5 | $1 | $1 | 1.05M | #20 | ||
| Gemini 3.1 Pro Preview | $2 | $12 | $8 | $8 | 1.05M | #31 | ||
| Gemini 3.1 Flash Lite Preview | $0.25 | $1.5 | $1 | $1 | 1.05M | #34 | ||
| Gemini 2.5 Pro | $1.25 | $10 | $6.25 | $6.25 | 1.05M | #57 | ||
| Qwen3 Coder 480B A35B | Qwen | $0.22 | $1.8 | $1.12 | $1.12 | 1.05M | #59 | |
| Gemini 2.5 Flash Lite Preview 09-2025 | $0.1 | $0.4 | $0.3 | $0.3 | 1.05M | #81 | ||
| Lyria 3 Pro Preview | $0 | $0 | $0 | $0 | 1.05M | #283 | ||
| Lyria 3 Clip Preview | $0 | $0 | $0 | $0 | 1.05M | #291 | ||
| NewGLM 5.2 | Z.ai | $0.95 | $3 | $2.45 | $2.45 | 1.05M | ||
| Google Gemini Pro Latest | $2 | $12 | $8 | $8 | 1.05M | |||
| Google Gemini Flash Latest | $1.5 | $9 | $6 | $6 | 1.05M | |||
| DeepSeek V4 Flash (free) | DeepSeek | $0 | $0 | $0 | $0 | 1.05M | ||
| MiMo-V2-Pro | Xiaomi | $1 | $3 | $2.5 | $2.5 | 1.05M | ||
| Qwen3 Coder 480B A35B (free) | Qwen | $0 | $0 | $0 | $0 | 1.05M | ||
| Gemini 2.5 Pro Preview 06-05 | $1.25 | $10 | $6.25 | $6.25 | 1.05M | |||
| Gemini 2.5 Pro Preview 05-06 | $1.25 | $10 | $6.25 | $6.25 | 1.05M | |||
| Llama 4 Maverick | Meta | $0.15 | $0.6 | $0.45 | $0.45 | 1.05M | ||
| Gemini 2.0 Flash Lite | $0.075 | $0.3 | $0.22 | $0.22 | 1.05M | |||
| Gemini 2.0 Flash | $0.1 | $0.4 | $0.3 | $0.3 | 1.05M | |||
| GPT-4.1 Mini | OpenAI | $0.4 | $1.6 | $1.2 | $1.2 | 1.05M | #52 | |
| GPT-4.1 Nano | OpenAI | $0.1 | $0.4 | $0.3 | $0.3 | 1.05M | #58 | |
| GPT-4.1 | OpenAI | $2 | $8 | $6 | $6 | 1.05M | #66 | |
| Palmyra X5 | Writer | $0.6 | $6 | $3.6 | $3.6 | 1.04M | #264 | |
| MiniMax-01 | MiniMax | $0.2 | $1.1 | $0.75 | $0.75 | 1M | #215 | |
| 🔥Claude Sonnet 4.6 | Anthropic | $3 | $15 | $10.5 | $10.5 | 1M | #6 | |
| 🔥Claude Opus 4.7 | Anthropic | $5 | $25 | $17.5 | $17.5 | 1M | #8 | |
| New🔥Nemotron 3 Ultra (free) | NVIDIA | $0 | $0 | $0 | $0 | 1M | #12 | |
| 🔥Claude Opus 4.6 | Anthropic | $5 | $25 | $17.5 | $17.5 | 1M | #18 | |
| Nemotron 3 Super (free) | NVIDIA | $0 | $0 | $0 | $0 | 1M | #23 | |
| Qwen3.7 Max | Qwen | $1.25 | $3.75 | $3.12 | $3.12 | 1M | #35 | |
| NewQwen3.7 Plus | Qwen | $0.32 | $1.28 | $0.96 | $0.96 | 1M | #51 |
Pricing FAQ
How is the sample workload cost calculated?
The sample workload uses 1,000,000 input tokens plus 500,000 output tokens, then applies each model's normalized USD price per 1 million tokens.
Why do input and output token prices matter separately?
Many applications are output-token heavy, while retrieval and classification workloads may be input-token heavy. Comparing both prices helps avoid picking a model that is cheap for the wrong workload shape.
Should I verify prices before production use?
Yes. AI Model Matrix normalizes public pricing metadata for comparison, but provider availability, limits, and prices can change. Always verify the final contract or provider dashboard before production use.
Related Guides
Cheapest LLM APIs
Sort models by estimated workload cost and normalized token prices.
Open guideLargest Context Windows
Find models for long documents, retrieval, and codebase context.
Open guideCoding Models
Compare code-oriented models by cost, context, and practical popularity signals.
Open guideFree Models
Browse zero-price models for prototypes and evaluation.
Open guideRAG Models
Start from large context windows and practical input-cost constraints.
Open guideChatbot Costs
Find budget-sensitive models for output-heavy assistant traffic.
Open guideCost Calculator
Enter your own input and output token volume before narrowing the shortlist.
Estimate costAlternatives
Find cheaper candidates around popular model anchors.
Find alternatives