Beta
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 logoElephant$0.00$0.00Closed
3openrouter logoFree Models Router$0.00$0.00Closed
4Google DeepMind logoGemma 4 26B A4B (free)$0.00$0.00OSS
5Google DeepMind logoGemma 4 31B (free)$0.00$0.00OSS
6Google DeepMind logoLyria 3 Clip Preview$0.00$0.00Closed
7Google DeepMind logoLyria 3 Pro Preview$0.00$0.00Closed
8NVIDIA logoNemotron 3 Nano 30B A3B (free)$0.00$0.00OSS
9NVIDIA logoNemotron 3 Super (free)$0.00$0.00OSS
10Alibaba Qwen logoQwen3 Coder 480B A35B (free)$0.00$0.00OSS
11Alibaba Qwen logoQwen3 Next 80B A3B Instruct (free)$0.00$0.00OSS
12Alibaba Qwen logoQwen3.6 Plus (free)$0.00$0.00Closed
13Alibaba Qwen logoQwen3.6 Plus Preview (free)$0.00$0.00OSS
14stepfun logoStep 3.5 Flash (free)$0.00$0.00OSS
15OpenAI logoGPT-5 Nano$0.05$0.40Closed
16NVIDIA logoNemotron 3 Nano 30B A3B$0.05$0.20OSS
17Alibaba Qwen logoQwen3.5-9B$0.05$0.15OSS
18z-ai logoGLM 4.7 Flash$0.06$0.40OSS
19Amazon logoNova Lite 1.0$0.06$0.24Closed
20Alibaba Qwen logoQwen3.5-Flash$0.07$0.26OSS
21Alibaba Qwen logoQwen3 235B A22B Instruct 2507$0.07$0.10OSS
22Google DeepMind logoGemini 2.0 Flash Lite$0.07$0.30Closed
23ByteDance logoSeed 1.6 Flash$0.07$0.30Closed
24Google DeepMind logoGemma 4 26B A4B $0.08$0.35OSS
25Meta logoLlama 4 Scout$0.08$0.30OSS
26xiaomi logoMiMo-V2-Flash$0.09$0.29OSS
27Alibaba Qwen logoQwen3 30B A3B Instruct 2507$0.09$0.30OSS
28Alibaba Qwen logoQwen3 Next 80B A3B Instruct$0.09$1.10OSS
29Google DeepMind logoGemini 2.0 Flash$0.10$0.40Closed
30Google DeepMind logoGemini 2.5 Flash Lite$0.10$0.40Closed
31Google DeepMind logoGemini 2.5 Flash Lite Preview 09-2025$0.10$0.40Closed
32OpenAI logoGPT-4.1 Nano$0.10$0.40Closed
33NVIDIA logoNemotron 3 Super$0.10$0.50OSS
34ByteDance logoSeed-2.0-Mini$0.10$0.40Closed
35stepfun logoStep 3.5 Flash$0.10$0.30OSS
36Google DeepMind logoGemma 4 31B$0.13$0.38OSS
37Meta logoLlama 4 Maverick$0.15$0.60OSS
38Mistral AI logoMinistral 3 8B 2512$0.15$0.15OSS
39Mistral AI logoMistral Small 4$0.15$0.60OSS
40Alibaba Qwen logoQwen3 Coder Next$0.15$0.80OSS
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
Llama 4 Maverick
$0.15/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.