Context · 200K+

Cheapest 200K context LLMs

Every LLM with a 200,000+ token context window. Ranked by input price per 1M tokens.

Models40
Cheapest$-1000000.00
Min context200K tokens
What this page is
200K context is the modern default for frontier models. This page lists every priced 200K+ model, cheapest first. For long docs that fit in 200K, this tier offers the best balance of price, recall, and model diversity.

200K+ context models, cheapest first.

#ModelIn $/1MOut $/1MType
1openrouter logoAuto Router$-1000000.00$-1000000.00Closed
2openrouter logoFusion$-1000000.00$-1000000.00Closed
3openrouter logoPareto Code Router$-1000000.00$-1000000.00Closed
4openrouter logoElephant$0.00$0.00Closed
5openrouter logoFree Models Router$0.00$0.00Closed
6Google DeepMind logoGemma 4 26B A4B (free)$0.00$0.00OSS
7Google DeepMind logoGemma 4 31B (free)$0.00$0.00OSS
8tencent logoHy3 (free)$0.00$0.00Closed
9tencent logoHy3 preview (free)$0.00$0.00Closed
10
P
Laguna M.1 (free)
$0.00$0.00OSS
11
P
Laguna XS.2 (free)
$0.00$0.00OSS
12Google DeepMind logoLyria 3 Clip Preview$0.00$0.00Closed
13Google DeepMind logoLyria 3 Pro Preview$0.00$0.00Closed
14NVIDIA logoNemotron 3 Nano 30B A3B (free)$0.00$0.00OSS
15NVIDIA logoNemotron 3 Nano Omni (free)$0.00$0.00OSS
16NVIDIA logoNemotron 3 Super (free)$0.00$0.00OSS
17NVIDIA logoNemotron 3 Ultra (free)$0.00$0.00OSS
18nex-agi logoNex-N2-Pro (free)$0.00$0.00OSS
19Cohere logoNorth Mini Code (free)$0.00$0.00OSS
20openrouter logoOwl Alpha$0.00$0.00Closed
21Alibaba Qwen logoQwen3 Coder 480B A35B (free)$0.00$0.00OSS
22Alibaba Qwen logoQwen3 Next 80B A3B Instruct (free)$0.00$0.00OSS
23Alibaba Qwen logoQwen3.6 Plus (free)$0.00$0.00Closed
24Alibaba Qwen logoQwen3.6 Plus Preview (free)$0.00$0.00OSS
25stepfun logoStep 3.5 Flash (free)$0.00$0.00OSS
26
I
Ling-2.6-flash
$0.01$0.03Closed
27nex-agi logoNex-N2-Mini$0.03$0.10Closed
28OpenAI logoGPT-5 Nano$0.05$0.40Closed
29NVIDIA logoNemotron 3 Nano 30B A3B$0.05$0.20OSS
30Google DeepMind logoGemma 4 26B A4B $0.06$0.33OSS
31z-ai logoGLM 4.7 Flash$0.06$0.40OSS
32Amazon logoNova Lite 1.0$0.06$0.24Closed
33tencent logoHy3 preview$0.06$0.21OSS
34Alibaba Qwen logoQwen3.5-Flash$0.07$0.26OSS
35Google DeepMind logoGemini 2.0 Flash Lite$0.07$0.30Closed
36
I
Ling-2.6-1T
$0.07$0.63Closed
37
I
Ring-2.6-1T
$0.07$0.63Closed
38ByteDance logoSeed 1.6 Flash$0.07$0.30Closed
39NVIDIA logoNemotron 3 Super$0.08$0.45OSS
40DeepSeek logoDeepSeek V4 Flash$0.08$0.17OSS
Cheapest
Auto Router
$-1000000.00/M
$ per 1M input tokens
Why the gap

At the 200K tier, premium pricing buys better tail-end retrieval and higher overall reasoning. For retrieval-heavy RAG, cheap models often match premium ones.

Most expensive
DeepSeek V4 Flash
$0.08/M
$ per 1M input tokens
Yes. 200K handles a full novel, a medium-sized codebase, or 100+ pages of PDFs. Only use 1M when you truly need whole-repo or multi-book context.