Context windows
What does a full context window actually cost?
SpaceXAI: Grok 4.20 has the largest tracked context window at 2.0M tokens - filling it costs $2.50 in input tokens alone. The cheapest way to fill a large context window right now is DeepSeek: DeepSeek V4 Flash Latest, at $0.04. Window size alone doesn't tell you the real cost of using it.
| # | Model | Context window | $/1M input | Cost to fill | Quality |
|---|---|---|---|---|---|
| 01 | SpaceXAI: Grok 4.20 | 2.0M | $1.25 | $2.50 | - |
| 02 | SpaceXAI: Grok 4.20 Multi-Agent | 2.0M | $1.25 | $2.50 | - |
| 03 | DeepSeek: DeepSeek V4 Flash 0423 | 1.3M | $0.04 | $0.05 | 34.3 |
| 04 | Z.ai: GLM 5.3 (batch) | 1.3M | $0.84 | $1.10 | 44.8 |
| 05 | Z.ai: GLM 5.3 Flash (batch) | 1.3M | $0.15 | $0.20 | 41.8 |
| 06 | DeepSeek: DeepSeek V4 Flash Latest | 1.3M | $0.03 | $0.04 | - |
| 07 | Z.ai: GLM Flash Latest | 1.3M | $0.07 | $0.10 | - |
| 08 | Z.ai: GLM Latest | 1.3M | $0.56 | $0.74 | - |
| 09 | OpenAI: GPT-5.4 (batch) | 1.1M | $2.50 | $2.63 | - |
| 10 | OpenAI: GPT-5.4 Pro (batch) | 1.1M | $30.00 | $31.50 | - |
| 11 | OpenAI: GPT-5.5 (batch) | 1.1M | $5.00 | $5.25 | 38.4 |
| 12 | OpenAI: GPT-5.5 Pro (batch) | 1.1M | $30.00 | $31.50 | - |
| 13 | OpenAI: GPT-5.6 Luna (batch) | 1.1M | $0.20 | $0.21 | 37.3 |
| 14 | OpenAI: GPT-5.6 Luna Pro (batch) | 1.1M | $0.20 | $0.21 | - |
| 15 | OpenAI: GPT-5.6 Sol (batch) | 1.1M | $2.00 | $2.10 | 47 |
| 16 | OpenAI: GPT-5.6 Sol Pro (batch) | 1.1M | $2.00 | $2.10 | - |
| 17 | OpenAI: GPT-5.6 Terra (batch) | 1.1M | $2.00 | $2.10 | 42.1 |
| 18 | OpenAI: GPT-5.6 Terra Pro (batch) | 1.1M | $2.00 | $2.10 | - |
| 19 | OpenAI: GPT-6 Astra (batch) | 1.1M | $10.00 | $10.50 | 52.7 |
| 20 | OpenAI: GPT-6 Astra Pro (batch) | 1.1M | $10.00 | $10.50 | - |
| 21 | OpenAI: GPT-6 Luna (batch) | 1.1M | $0.10 | $0.10 | 37.3 |
| 22 | OpenAI: GPT-6 Luna Pro (batch) | 1.1M | $0.10 | $0.10 | - |
| 23 | OpenAI: GPT-6 Sol (batch) | 1.1M | $2.00 | $2.10 | 47.5 |
| 24 | OpenAI: GPT-6 Sol Pro (batch) | 1.1M | $2.00 | $2.10 | - |
| 25 | Xiaomi: MiMo-V2.5 | 1.1M | $0.14 | $0.15 | - |
| 26 | Xiaomi: MiMo-V2.5-Pro | 1.1M | $0.43 | $0.46 | 26 |
| 27 | OpenAI: GPT Astra Latest | 1.1M | $10.00 | $10.50 | - |
| 28 | OpenAI GPT Latest | 1.1M | $2.00 | $2.10 | - |
| 29 | OpenAI: GPT Luna Latest | 1.1M | $0.10 | $0.10 | - |
| 30 | OpenAI: GPT Sol Latest | 1.1M | $2.00 | $2.10 | - |
Cost to fill = context window (tokens) × prompt price per token. This is the cost of one request using the full window as input - real output tokens and multi-turn conversations cost more.
A big context window and a high-quality model aren't the same thing - among models with a window of 1M+ tokens, OpenAI: GPT-6 Astra (batch) scores highest on quality (see the Context window and Quality columns above).
Frequently asked questions
Which AI model has the largest context window?
SpaceXAI: Grok 4.20 has the largest tracked context window at 2.0M tokens.
How much does it cost to use a model's full context window?
Filling SpaceXAI: Grok 4.20's 2.0M-token context window costs $2.50 in input tokens at current pricing.