OpenRouter API Pricing Update: 2026-10-18
Por ahora este informe solo está disponible en inglés.
On 2026-10-18, OpenRouter tracks 471 models with 19 free models and 180 open-weight models.
Free Models
There are 19 free models available today, including Google: Lyria 3 Pro Preview and Google: Lyria 3 Clip Preview, each with 1,048,576 context tokens. Thinking Machines offers two free models: Inkling Small and Inkling, both with 1,048,576 context tokens. NVIDIA provides three free models: Nemotron 3.5 Super VL, Nemotron 3.5 Lightning, and Nemotron 3 Ultra, each with 1,000,000 context tokens.
New Models
Four new models were added today. DeepSeek: DeepSeek V4.1 Flash 1017 is priced at $0.15 per million input tokens and $0.6 per million output tokens with 1,048,576 context tokens and open weights. Elorian: Glimpse costs $0.6 per million input and $3.0 per million output tokens with 262,144 context tokens and no open weights. Qwen: Qwen3.7 Plus (batch) is priced at $0.23 per million input and $0.92 per million output tokens with 262,144 context tokens and no open weights. Pareto 26.10 costs $0.8 per million input and $3.2 per million output tokens with 1,048,576 context tokens and no open weights.
Price Changes
Several models had price updates. NVIDIA: Nemotron 3.5 Super VL increased input price from $0.1 to $0.15 per million tokens and output price from $0.4 to $0.5 per million tokens. Z.ai: GLM 5.3 Flash raised input price from $0.0109 to $0.048 per million tokens while lowering output price from $0.4455 to $0.2 per million tokens. DeepSeek: DeepSeek Pro Latest reduced input price from $0.2495 to $0.12 per million tokens but increased output price from $0.7484 to $8.0 per million tokens. DeepSeek: DeepSeek Flash Latest increased input price from $0.028 to $0.08 per million tokens and output price from $0.405 to $0.5 per million tokens. Z.ai: GLM 5.3 kept input price steady at $0.079 per million tokens but reduced output price from $4.8 to $3.2 per million tokens.
Cheapest Paid Options
The lowest input-priced paid model is DeepSeek: DeepSeek V4 Flash Latest at $0.0121 per million input tokens and $0.1436 per million output tokens with 1,048,576 context tokens and no open weights. Next is DeepSeek: DeepSeek V4 Flash 0731 at $0.0151 per million input and $1.28 per million output tokens with the same context length and open weights. IBM: Granite 4.0 Micro follows at $0.017 per million input and $0.112 per million output tokens with 131,000 context tokens and open weights. OpenAI: gpt-oss-20b is priced at $0.018 per million input and $0.09 per million output tokens with 131,072 context tokens and open weights.
Puntos clave
- Free models remain available from Google, Thinking Machines, NVIDIA, and others with context windows up to 1,048,576 tokens.
- DeepSeek: DeepSeek V4 Flash Latest is the cheapest paid model by input price at $0.0121 per million tokens.
- Price changes show mixed trends, with some models lowering costs and others increasing output prices significantly.
- Four new models entered the tracker today, including options from DeepSeek, Elorian, Qwen, and Pareto.