OpenRouter API Pricing Snapshot: 16 Free Models, DeepSeek Flash Leads Cheapest Paid Tier

Sixteen models are listed as free on OpenRouter today. NVIDIA contributes five free variants: Nemotron 3.5 Super VL, Nemotron 3.5 Lightning, Nemotron 3 Ultra, Nemotron 3 Nano Omni, and Nemotron 3.5 Content Safety, with context windows ranging from 128,000 to 1,000,000 tokens. Google provides four free models: Lyria 3 Pro Preview, Lyria 3 Clip Preview, Gemma 4 26B A4B, and Gemma 4 31B, each offering 262,144 or 1,048,576 tokens of context. Other free entries include Crouton Alpha from stealth (1,048,576 tokens), Dots Studio Dots3-Note Preview (512,000 tokens), Recursive Flint (262,144 tokens), XingChen Xing4.0 29B A4B (262,144 tokens), Cohere North Mini Code (256,000 tokens), LiquidAI LFM2.5-2.6B (65,536 tokens), and the OpenRouter Free Models Router (200,000 tokens).

Two models were added to the catalog: ricursiveAI/Ripple-65B-Preview from ricursiveai priced at $0.20 per million input tokens and $0.60 per million output tokens with a 1,048,576-token context, and Tencent Hy4 from tencent priced at $0.417 per million input tokens and $1.2505 per million output tokens with a 1,048,576-token context and open weights. Two models were removed: Thinking Machines Inkling Small and Thinking Machines Inkling, both previously free. No models transitioned to or from free status between 2026-11-04 and 2026-11-05.

Eleven models recorded price changes. DeepSeek Flash Latest saw the steepest input price drop, falling from $0.0333 to $0.006 per million tokens, while output rose from $0.475 to $0.50. OpenAI gpt-oss-120b input price fell from $0.15 to $0.023 and output from $0.60 to $0.083. Meta Llama 3.3 70B Instruct input halved from $0.20 to $0.10 and output dropped from $0.52 to $0.32. Google Gemma 4 26B A4B input fell from $0.064 to $0.031 and output from $0.191 to $0.092. Z.ai GLM 5.3 input decreased from $0.08 to $0.0699 and output from $3.60 to $1.40. MoonshotAI Kimi K3 input dropped from $0.276 to $0.192 while output climbed from $9.60 to $16.00. MoonshotAI Kimi Latest input fell from $0.2128 to $0.1558 and output from $10.5572 to $9.3388. Z.ai GLM 5.3 Flash input rose from $0.0313 to $0.15 and output from $0.0846 to $0.50. IBM Granite 4.2 8B held input at $0.06 while output increased from $0.15 to $0.25. Z.ai GLM Flash Latest input edged down from $0.0313 to $0.0285 and output rose from $0.0846 to $0.0923.

The lowest input prices among paid models start at $0.006 per million tokens, shared by DeepSeek Flash Latest and Z.ai GLM 5.2. DeepSeek Flash Latest pairs that input price with $0.50 per million output tokens and a 1,048,576-token context. Z.ai GLM 5.2 carries a $6.80 per million output price with the same context length and open weights. The next tier includes inclusionAI Ling 3.0 Flash at $0.021 input and $0.063 output with 262,144-token context and open weights, OpenAI gpt-oss-120b at $0.023 input and $0.083 output with 131,072-token context and open weights, OpenAI gpt-oss-20b batch at $0.024 input and $0.112 output with 131,072-token context and open weights, Nex AGI Nex-N2.5-Mini at $0.025 input and $0.10 output with 262,144-token context and open weights, OpenAI GPT-5 Nano batch at $0.025 input and $0.20 output with 400,000-token context, and Meta Llama 3.2 1B Instruct at $0.027 input and $0.201 output with 60,000-token context and open weights.

Five models or routers offer a 2,000,000-token context window: SpaceXAI Grok 4.20 Multi-Agent, SpaceXAI Grok 4.20, Auto Router Beta, Pareto Code Router, and Auto Router, all provided by x-ai or openrouter.