为什么是这20个
The context window is how many tokens (pieces of words) a model takes in one request: a whole codebase, a contract or a book. Each row also shows the input and output price per million tokens so you can weigh size against cost.
-
1
S
SpaceXAI: Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct...
2,000,000 tokens 2,000,000 context$/M in 1.25$/M out 2.5x-ai
-
2
S
SpaceXAI: Grok 4.20
Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on...
2,000,000 tokens 2,000,000 context$/M in 1.25$/M out 2.5x-ai
-
3
M
Meta: Llama 4 Scout
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It...
1,310,720 tokens 1,310,720 context$/M in 0.1$/M out 0.3meta-llama
-
4
O
OpenAI: GPT-6.1 Sol Pro
GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for...
1,050,000 tokens 1,050,000 context$/M in 2$/M out 10openai
-
5
O
OpenAI: GPT-6.1 Sol Pro (batch)
GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for...
1,050,000 tokens 1,050,000 context$/M in 1$/M out 5openai
-
6
O
OpenAI: GPT-6.1 Sol
GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer...
1,050,000 tokens 1,050,000 context$/M in 2$/M out 10openai
-
7
O
OpenAI: GPT-6.1 Sol (batch)
GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer...
1,050,000 tokens 1,050,000 context$/M in 1$/M out 5openai
-
8
O
OpenAI: GPT-6 Luna Pro
GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for...
1,050,000 tokens 1,050,000 context$/M in 0.1$/M out 0.5openai
-
9
O
OpenAI: GPT-6 Luna Pro (batch)
GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for...
1,050,000 tokens 1,050,000 context$/M in 0.05$/M out 0.25openai
-
10
O
OpenAI: GPT-6 Luna
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive...
1,050,000 tokens 1,050,000 context$/M in 0.1$/M out 0.5openai
-
11
O
OpenAI: GPT-6 Luna (batch)
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive...
1,050,000 tokens 1,050,000 context$/M in 0.05$/M out 0.25openai
-
12
O
OpenAI: GPT-6 Sol Pro
GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for...
1,050,000 tokens 1,050,000 context$/M in 2$/M out 10openai
-
13
O
OpenAI: GPT-6 Sol Pro (batch)
GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for...
1,050,000 tokens 1,050,000 context$/M in 1$/M out 5openai
-
14
O
OpenAI: GPT-6 Sol
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is...
1,050,000 tokens 1,050,000 context$/M in 2$/M out 10openai
-
15
O
OpenAI: GPT-6 Sol (batch)
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is...
1,050,000 tokens 1,050,000 context$/M in 1$/M out 5openai
-
16
X
Xiaomi: MiMo-V2.6-Flash
MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B...
1,050,000 tokens 1,050,000 context$/M in 0.14$/M out 0.28xiaomi
-
17
X
Xiaomi: MiMo-V2.6-Pro
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability...
1,050,000 tokens 1,050,000 context$/M in 0.435$/M out 0.87xiaomi
-
18
O
OpenAI: GPT Astra Latest
This model always redirects to the latest model in the GPT Astra family.
1,050,000 tokens 1,050,000 context$/M in 10$/M out 50~openai
-
19
O
OpenAI: GPT Sol Latest
This model always redirects to the latest model in the GPT Sol family.
1,050,000 tokens 1,050,000 context$/M in 2$/M out 10~openai
-
20
O
OpenAI: GPT Terra Latest
This model always redirects to the latest model in the GPT Terra family.
1,050,000 tokens 1,050,000 context$/M in 2$/M out 12~openai
如何衡量
Public model catalogue of OpenRouter (models sold through its API), paid models only, sorted by context length.
参考资料
- OpenRouter models API, OpenRouter (public API). Checked 2026-10-19 22:52 UTC.
也在
图片: Long Room Interior, Trinity College Dublin, Ireland - Diliff by Diliff, CC BY-SA 4.0 via Wikimedia Commons. Pictures in rows: Wikimedia Commons, GitHub and the linked pages.