Rankings
Best Value per Context Token
Models offering the most context window per dollar of input cost.
Models ranked
833
Top context
10M
Llama 4 Scout 17b 16e
Leading provider
Openai
136 models in this ranking
Leaderboard
Tap any row to see full specs and comparisons.
| Rank | Model | Context | Max output | Input $/M | Value score |
|---|---|---|---|---|---|
| 1 | Llama 4 Scout 17b 16eMeta | 10M | 16K | $0.050/M | 10000K / $0.05 |
| 2 | Llama 4 Scout 17b 128e Instruct MaasMeta | 10M | 10M | $0.250/M | 10000K / $0.25 |
| 3 | Llama 4 Scout 17b 16e Instruct MaasMeta | 10M | 10M | $0.250/M | 10000K / $0.25 |
| 4 | Llama 4 Maverick 17b 128e Instruct Fp8Meta | 1M | 16K | $0.050/M | 1000K / $0.05 |
| 5 | Qwen Turbo LatestAlibaba | 1M | 16K | $0.050/M | 1000K / $0.05 |
| 6 | Qwen Turbo 2024 11 01Alibaba | 1M | 8K | $0.050/M | 1000K / $0.05 |
| 7 | Qwen Turbo 2025 04 28Alibaba | 1M | 16K | $0.050/M | 1000K / $0.05 |
| 8 | Gemini 2 0 Flash LiteGoogle | 1.0M | 8K | $0.075/M | 1048K / $0.07 |
| 9 | Gemini 2.0 Flash LiteGoogle | 1.0M | 8K | $0.075/M | 1048K / $0.07 |
| 10 | Gemini 2.5 Flash LiteGoogle | 1.0M | 66K | $0.100/M | 1048K / $0.10 |
| 11 | Gemini 2 5 Flash Lite Preview 06 17Google | 1.0M | 66K | $0.100/M | 1048K / $0.10 |
| 12 | Gemini Flash Lite LatestGoogle | 1.0M | 66K | $0.100/M | 1048K / $0.10 |
| 13 | Gemini 2 0 FlashGoogle | 1.0M | 8K | $0.100/M | 1048K / $0.10 |
| 14 | Gemini 2.5 Flash Lite Preview 09-2025Google | 1.0M | 66K | $0.100/M | 1048K / $0.10 |
| 15 | GPT-4.1 NanoOpenai | 1.0M | 33K | $0.100/M | 1047K / $0.10 |
| 16 | Gpt 4 1 Nano 2025 04 14Openai | 1.0M | 33K | $0.100/M | 1047K / $0.10 |
| 17 | Qwen3.5-FlashAlibaba | 1M | 66K | $0.100/M | 1000K / $0.10 |
| 18 | Grok 4 1 FastXai | 2M | 2M | $0.200/M | 2000K / $0.20 |
| 19 | Grok 4 1 Fast Non Reasoning LatestXai | 2M | 2M | $0.200/M | 2000K / $0.20 |
| 20 | Grok 4 1 Fast Reasoning LatestXai | 2M | 2M | $0.200/M | 2000K / $0.20 |
| 21 | Gemini 2.0 FlashGoogle | 1M | 1M | $0.100/M | 1000K / $0.10 |
| 22 | Llama3 2 11b VisionMeta | 131K | 131K | $0.015/M | 131K / $0.01 |
| 23 | Llama3 2 3bMeta | 131K | 131K | $0.015/M | 131K / $0.01 |
| 24 | Llama 3 2 3bMeta | 131K | 131K | $0.020/M | 131K / $0.02 |
| 25 | Llama Guard 3 8BMeta | 131K | 131K | $0.020/M | 131K / $0.02 |
Showing 25 of 833 models
More rankings
Explore other model leaderboards.
Largest Context Window
Models ranked by maximum context window size.
Best for RAG
Models best suited for Retrieval-Augmented Generation workloads.
Best for AI Agents
Models with the capabilities needed to power autonomous agent workflows.
Best for Document Processing
Models with large enough context to process long documents in one pass.
Best Multimodal
Vision-capable models with the largest context windows.
Best Reasoning
Models with extended thinking or strong reasoning capabilities.
Best for Chatbots
Fast, cost-efficient models ideal for real-time conversational applications.