Compare API pricing before you build.
Auto-updated OpenRouter API list prices, context limits and output limits. This is a cost-and-capacity comparison, not a quality ranking or subscription price guide.
| Price/capacity index | Model | Index | Tokens/$ | Input $/1M | Output $/1M | Blended $/1M | Context | Max output | Price move | Index move | Source |
|---|---|---|---|---|---|---|---|---|---|---|---|
| #1 | DeepSeek: DeepSeek V4.1 Flash 1017 (batch)Deepseek | 100 | 17.2M | $0.011 | $0.2 | $0.0583 | 1.0M | 944k | • | • | OpenRouter |
| #2 | Anthropic: Claude Haiku 5.5 (batch)Anthropic | 55.4 | 10.0M | $0.05 | $0.25 | $0.1 | 1.0M | 128k | • | • | OpenRouter |
| #3 | NVIDIA: Nemotron 3.5 LightningNvidia | 51.2 | 9.8M | $0.07 | $0.2 | $0.1025 | 262k | 236k | • | • | OpenRouter |
| #4 | DeepSeek: DeepSeek V4.1 Flash 1017Deepseek | 45 | 7.7M | $0.006 | $0.5 | $0.1295 | 1.0M | 944k | • | • | OpenRouter |
| #5 | DeepSeek: DeepSeek V4.1 FlashDeepseek | 32.4 | 5.6M | $0.051 | $0.567 | $0.18 | 1.0M | 944k | ↑ | ↑ | OpenRouter |
| #6 | Anthropic: Claude Haiku 5.5Anthropic | 27.7 | 5.0M | $0.1 | $0.5 | $0.2 | 1.0M | 128k | • | ↓ | OpenRouter |
| #7 | NVIDIA: Nemotron 3.5 Super VLNvidia | 25.3 | 4.3M | $0.15 | $0.47 | $0.23 | 1.0M | 944k | • | ↓ | OpenRouter |
| #8 | Qwen: Qwen3.8 Omni FlashQwen | 24.1 | 4.3M | $0.15 | $0.47 | $0.23 | 1.0M | 131k | • | ↓ | OpenRouter |
| #9 | Z.ai: GLM 5.3 FlashX LegalZ Ai | 9.4 | 1.7M | $0.37 | $1.25 | $0.59 | 1.0M | 131k | • | • | OpenRouter |
| #10 | Cohere: Command A+Cohere | 8.3 | 1.7M | $0.3 | $1.5 | $0.6 | 192k | 64k | • | • | OpenRouter |
| #11 | OpenAI: GPT-6.1 Terra Pro (batch)Openai | 5.5 | 1.0M | $0.5 | $2.5 | $1 | 1.1M | 128k | • | • | OpenRouter |
| #12 | OpenAI: GPT-6.1 Terra (batch)Openai | 5.5 | 1.0M | $0.5 | $2.5 | $1 | 1.1M | 128k | • | • | OpenRouter |
| #13 | Mistral: Mistral Large 4Mistralai | 5.4 | 952k | $0.7 | $2.1 | $1.05 | 1.0M | 262k | • | • | OpenRouter |
| #14 | Google: Gemini 4 Carbon (batch)Google | 2.9 | 500k | $1 | $5 | $2 | 1.0M | 944k | NEW | NEW | OpenRouter |
| #15 | OpenAI: GPT-6.1 Terra ProOpenai | 2.8 | 500k | $1 | $5 | $2 | 1.1M | 128k | • | • | OpenRouter |
| #16 | OpenAI: GPT-6.1 TerraOpenai | 2.8 | 500k | $1 | $5 | $2 | 1.1M | 128k | • | • | OpenRouter |
| #17 | SpaceXAI: Grok 4.7 (batch)X Ai | 2.3 | 417k | $1.6 | $4.8 | $2.4 | 500k | 450k | • | • | OpenRouter |
| #18 | SpaceXAI: Grok 4.7X Ai | 1.8 | 333k | $2 | $6 | $3 | 500k | 450k | • | • | OpenRouter |
| #19 | Qwen: Qwen3.8 Max (0902)Qwen | 1.8 | 333k | $2 | $6 | $3 | 1.0M | 131k | • | • | OpenRouter |
| #20 | SpaceXAI: Grok 4.6X Ai | 1.8 | 333k | $2 | $6 | $3 | 500k | 450k | • | • | OpenRouter |
| #21 | Google: Gemini 4 CarbonGoogle | 1.5 | 250k | $2 | $10 | $4 | 1.0M | 944k | NEW | NEW | OpenRouter |
| #22 | MoonshotAI: Kimi K3.1 ProMoonshotai | 1.5 | 250k | $2 | $10 | $4 | 1.0M | 944k | • | ↓ | OpenRouter |
| #23 | Google: Gemini Omni 1.2 FlashGoogle | 1.4 | 296k | $1.5 | $9 | $3.375 | 131k | 66k | • | • | OpenRouter |
| #24 | Google: Gemini Omni 1.1 FlashGoogle | 1.4 | 296k | $1.5 | $9 | $3.375 | 131k | 66k | • | • | OpenRouter |
| #25 | Z.ai: GLM 5.3 PrimeZ Ai | 1.3 | 233k | $2.8 | $8.8 | $4.3 | 1.0M | 131k | • | • | OpenRouter |
| #26 | Qwen: Qwen3.8 Max PrimeQwen | 0.9 | 167k | $4 | $12 | $6 | 1.0M | 131k | • | • | OpenRouter |
| #27 | Anthropic: Claude Fable 5.2 (batch)Anthropic | 0.7 | 125k | $4 | $20 | $8 | 1.0M | 128k | • | • | OpenRouter |
| #28 | Anthropic: Claude Fable 5.2Anthropic | 0.3 | 63k | $8 | $40 | $16 | 1.0M | 128k | • | • | OpenRouter |
Dynamic flagship selection picks the newest paid text models from major providers on OpenRouter. Blended price uses a 3:1 input-to-output token mix in USD per million tokens. Tokens per dollar is 1,000,000 divided by that blended price. Value score (0-100) combines tokens-per-dollar with a capability factor from context window and max output tokens (log-scaled). It ranks list-price efficiency, not benchmark quality. The price/capacity index compares list-price efficiency from OpenRouter Models API; it does not measure answer quality, latency, safety or app-subscription value. Check the provider and route terms before production use.