AI models with the longest context windows

Updated February 2026 · 14 models · ranked by context window (large → small)

Context window sets how much you can feed a model in one shot: long documents, large codebases, or big RAG payloads. These models are ranked from the largest context window down.

#ModelInputOutputContext
1Gemini 2.5 Pro
Google
$5.00$15.002M
2Gemini 2.5 Flash
Google
$0.30$1.201M
3Llama 4 Maverick
Meta
$0.60$0.901M
4Llama 4 Scout
Meta
$0.20$0.40512K
5Claude Opus 4.8
Anthropic
$15.00$75.00500K
6Claude Sonnet 5
Anthropic
$3.00$15.00400K
7GPT-5
OpenAI
$10.00$30.00256K
8Mistral Large 3
Mistral
$2.00$6.00256K
9Codestral 2
Mistral
$0.50$1.50256K
10DeepSeek V4
DeepSeek
$0.40$1.20256K
11Grok 4
xAI
$5.00$15.00256K
12Claude Haiku 4.5
Anthropic
$0.80$4.00200K
13GPT-5 mini
OpenAI
$0.45$1.80128K
14GPT-5 nano
OpenAI
$0.15$0.60128K

1. Gemini 2.5 Pro

Google · $5.00 in / $15.00 out per 1M · 2M context · Sep 2025

Massive context window and strong multimodal grounding for document-heavy tasks.

2. Gemini 2.5 Flash

Google · $0.30 in / $1.20 out per 1M · 1M context · Sep 2025

Ultra-cheap, ultra-fast model with a huge context — ideal for RAG at scale.

3. Llama 4 Maverick

Meta · $0.60 in / $0.90 out per 1M · 1M context · Aug 2025

Open-weight model you can self-host — strong coding with permissive licensing.

4. Llama 4 Scout

Meta · $0.20 in / $0.40 out per 1M · 512K context · Aug 2025

Compact open-weight model for cheap, self-hosted inference and edge deployment.

5. Claude Opus 4.8

Anthropic · $15.00 in / $75.00 out per 1M · 500K context · Jan 2026

Flagship for the hardest reasoning, agentic, and coding workloads.

6. Claude Sonnet 5

Anthropic · $3.00 in / $15.00 out per 1M · 400K context · Feb 2026

Balanced frontier model — near-Opus quality at a fraction of the price.

7. GPT-5

OpenAI · $10.00 in / $30.00 out per 1M · 256K context · Dec 2025

Top general-purpose model with strong tool-use and multimodal reasoning.

8. Mistral Large 3

Mistral · $2.00 in / $6.00 out per 1M · 256K context · Feb 2026

European frontier model with strong multilingual and function-calling support.

9. Codestral 2

Mistral · $0.50 in / $1.50 out per 1M · 256K context · Nov 2025

Code-specialized model tuned for autocomplete, fill-in-the-middle, and refactors.

10. DeepSeek V4

DeepSeek · $0.40 in / $1.20 out per 1M · 256K context · Jan 2026

Open-weight MoE model with strong reasoning and coding at a very low price.

11. Grok 4

xAI · $5.00 in / $15.00 out per 1M · 256K context · Dec 2025

Real-time knowledge model with strong reasoning and a conversational style.

12. Claude Haiku 4.5

Anthropic · $0.80 in / $4.00 out per 1M · 200K context · Oct 2025

Fast, low-cost model tuned for high-volume chat and lightweight agents.

13. GPT-5 mini

OpenAI · $0.45 in / $1.80 out per 1M · 128K context · Jan 2026

Cost-efficient GPT-5 variant for scale — snappy responses at a low price.

14. GPT-5 nano

OpenAI · $0.15 in / $0.60 out per 1M · 128K context · Jan 2026

Smallest GPT-5 tier — ultra-cheap classification and routing at massive scale.

Pricing is illustrative and per 1M tokens. Not sure which to pick? Run the model finder for a recommendation, or browse the full directory.