OpenRouter API Pricing Update: 20 Free Models, DeepSeek V4 Flash Input Price Rises Sharply

Two new models were added: Inception: Mercury 3 at $0.10 input and $0.35 output per million tokens with 1,000,000 context tokens, and MiniMax: MiniMax M3.1 Flash (free) at $0.00 input and output per million tokens with 1,000,000 context tokens. Three models were removed: DeepSeek: R1, WizardLM-2 8x22B, and Sao10K: Llama 3.3 Euryale 70B.

Several models saw price changes: NVIDIA: Nemotron 3.5 Super VL increased input from $0.10 to $0.15 and output from $0.40 to $0.50 per million tokens; Qwen: Qwen3.5-27B increased input from $0.26 to $0.27 and decreased output from $2.60 to $2.16 per million tokens; Z.ai: GLM 4.6 increased input from $0.50 to $0.55 and output from $2.00 to $2.20 per million tokens; Z.ai: GLM 5.3 Flash decreased output from $0.20 to $0.16 per million tokens with input unchanged at $0.048; DeepSeek: DeepSeek Pro Latest increased input from $0.2081 to $0.225 per million tokens with output steady at $8.00; DeepSeek: DeepSeek Flash Latest decreased input from $0.05 to $0.049 per million tokens with output steady at $0.60; Z.ai: GLM Flash Latest decreased output from $0.20 to $0.16 per million tokens with input unchanged at $0.048; DeepSeek: DeepSeek V4 Flash 0731 increased input from $0.0199 to $0.44 and output from $0.45 to $1.32 per million tokens; Reflection: Beam 1.0 501B A23B decreased input from $1.00 to $0.30 and output from $3.00 to $1.00 per million tokens; MoonshotAI: Kimi Latest decreased input from $0.249 to $0.238 and increased output from $11.936 to $16.00 per million tokens; MoonshotAI: Kimi K3 decreased input from $0.249 to $0.239 per million tokens with output steady at $11.936; DeepSeek: DeepSeek V4 Pro 0423 increased input from $0.2088 to $0.9553 and output from $0.4176 to $1.9105 per million tokens.

The cheapest paid models by input price are: DeepSeek: DeepSeek V4 Flash Latest at $0.0151 input and $0.45 output per million tokens with 1,048,576 context tokens; IBM: Granite 4.0 Micro at $0.017 input and $0.112 output per million tokens with 131,000 context tokens and open weights; OpenAI: gpt-oss-20b at $0.018 input and $0.09 output per million tokens with 131,072 context tokens and open weights; inclusionAI: Ling 3.0 Flash at $0.021 input and $0.063 output per million tokens with 262,144 context tokens and open weights.