OpenRouter API Pricing Report: 2026-11-11
Por ahora este informe solo está disponible en inglés.
OpenRouter tracks 467 models as of 2026-11-11, with 15 models available free and 177 open-weight models in the catalog.
Free models
Fifteen models are free today. Google offers Lyria 3 Pro Preview and Lyria 3 Clip Preview, each with 1048576 context tokens, plus Gemma 4 26B A4B and Gemma 4 31B, each with 262144 context tokens. NVIDIA offers Nemotron 3.5 Super VL, Nemotron 3.5 Lightning, and Nemotron 3 Ultra, each with 1000000 context tokens, and Nemotron 3 Nano Omni with 256000 context tokens. Thinking Machines offers Inkling 2 Small with 1048576 context tokens. Dots Studio offers Dots3-Note Preview with 512000 context tokens. LiquidAI offers LFM3-1.7B with 262144 context tokens and LFM2.5-2.6B with 65536 context tokens. Recursive offers Flint with 262144 context tokens. Cohere offers North Mini Code with 256000 context tokens. OpenRouter offers Free Models Router with 200000 context tokens.
Changes since 2026-11-10
No models became free or stopped being free today. Two models were removed: Qwen: Qwen2.5 7B Instruct and XingChen: Xing4.0 29B A4B (free). Five new models were added: Baidu: ERNIE-5.5-Flash-Preview at $0.28 input and $1.13 output per million tokens, Baidu: ERNIE-Light-DT-1.0 at $1.13 input and $3.94 output per million tokens, Google: Gemini 4 Carbon at $2.0 input and $10.0 output per million tokens, Google: Gemini 4 Carbon (batch) at $1.0 input and $5.0 output per million tokens, and Nex AGI: Nex-N2.6 at $0.12 input and $0.4 output per million tokens.
Cheapest paid options
The cheapest paid models by input price are DeepSeek: DeepSeek Flash Latest and DeepSeek: DeepSeek V4.1 Flash 1017, both at $0.006 input per million tokens with 1048576 context tokens; the former is not open weights, the latter is open weights. Z.ai: GLM 5.2 is $0.007 input per million tokens with $6.8 output and 1048576 context tokens. DeepSeek: DeepSeek V4.1 Flash 1017 (batch) is $0.011 input and $0.2 output per million tokens. inclusionAI: Ling 3.0 Tiny is $0.015 input and $0.045 output per million tokens with 262144 context tokens. Meta: Llama 3.1 8B Instruct is $0.02 input and $0.04 output per million tokens with 131072 context tokens. inclusionAI: Ling 3.0 Flash is $0.021 input and $0.063 output per million tokens. OpenAI: gpt-oss-20b (batch) is $0.024 input and $0.112 output per million tokens with 131072 context tokens.
Largest context windows
Five models share the largest context window at 2000000 tokens: SpaceXAI: Grok 4.20 Multi-Agent, SpaceXAI: Grok 4.20, Auto Router, Auto Code, and Auto Router (Beta). Among free models, Google: Lyria 3 Pro Preview and Google: Lyria 3 Clip Preview offer 1048576 context tokens, as do Thinking Machines: Inkling 2 Small and the paid DeepSeek Flash Latest and DeepSeek V4.1 Flash 1017.
Puntos clave
- Fifteen models are free on OpenRouter as of 2026-11-11, with no changes to the free list from the previous day.
- Twelve models changed prices, including increases for DeepSeek: DeepSeek V4.1 Flash and Google: Gemma 3 27B, and decreases for Z.ai: GLM 5.3 Flash and Qwen: Qwen3 14B.
- Five new models launched, led by Baidu: ERNIE-5.5-Flash-Preview at $0.28 input per million tokens and Google: Gemini 4 Carbon at $2.0 input per million tokens.
- Two models were removed, including the free XingChen: Xing4.0 29B A4B (free).
- The cheapest paid input price is $0.006 per million tokens, offered by two DeepSeek models with 1048576 context tokens.