# LLMCost — Live LLM API pricing
> Verified 2026-08-23 from OpenRouter's public API. Prices are USD per 1M tokens.

## Models

- [OpenAI: GPT-5.6 Terra Pro](https://llmcost.example.com/model/openai--gpt-5.6-terra-pro/): input $2.00, output $12.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-terra-pro
- [Anthropic: Claude Fable 5](https://llmcost.example.com/model/anthropic--claude-fable-5/): input $10.00, output $50.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-fable-5
- [Claude Opus 5](https://llmcost.example.com/model/anthropic--claude-opus-5/): input $5.00, output $25.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-5
- [OpenAI: GPT-5.6 Sol](https://llmcost.example.com/model/openai--gpt-5.6-sol/): input $2.00, output $10.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-sol
- [Google: Gemini 3.7 Flash](https://llmcost.example.com/model/google--gemini-3.7-flash/): input $0.375, output $1.88 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.7-flash
- [Anthropic: Claude Sonnet 5](https://llmcost.example.com/model/anthropic--claude-sonnet-5/): input $2.00, output $10.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-5
- [OpenAI: GPT-5.5](https://llmcost.example.com/model/openai--gpt-5.5/): input $5.00, output $30.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.5
- [OpenAI: GPT-5.5 Pro](https://llmcost.example.com/model/openai--gpt-5.5-pro/): input $30.00, output $180.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.5-pro
- [Google: Gemini 3.6 Flash](https://llmcost.example.com/model/google--gemini-3.6-flash/): input $0.750, output $3.75 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.6-flash
- [Claude Opus 5 (Fast)](https://llmcost.example.com/model/anthropic--claude-opus-5-fast/): input $10.00, output $50.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-5-fast
- [OpenAI: GPT-5.6 Luna](https://llmcost.example.com/model/openai--gpt-5.6-luna/): input $0.200, output $1.20 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-luna
- [OpenAI: GPT-5.4](https://llmcost.example.com/model/openai--gpt-5.4/): input $2.50, output $15.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.4
- [Google: Gemini 3.5 Flash](https://llmcost.example.com/model/google--gemini-3.5-flash/): input $1.50, output $9.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.5-flash
- [OpenAI: GPT-5.4 Mini](https://llmcost.example.com/model/openai--gpt-5.4-mini/): input $0.750, output $4.50 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-mini
- [Google: Gemini 3.5 Flash Lite](https://llmcost.example.com/model/google--gemini-3.5-flash-lite/): input $0.300, output $2.50 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.5-flash-lite
- [OpenAI: GPT-5.4 Nano](https://llmcost.example.com/model/openai--gpt-5.4-nano/): input $0.200, output $1.25 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-nano
- [OpenAI: GPT-5](https://llmcost.example.com/model/openai--gpt-5/): input $1.25, output $10.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5
- [Anthropic: Claude Opus 4.1](https://llmcost.example.com/model/anthropic--claude-opus-4.1/): input $15.00, output $75.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.1
- [Google: Gemini 2.5 Pro](https://llmcost.example.com/model/google--gemini-2.5-pro/): input $1.25, output $10.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-pro
- [Anthropic: Claude Sonnet 4.5](https://llmcost.example.com/model/anthropic--claude-sonnet-4.5/): input $3.00, output $15.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-4.5
- [DeepSeek: R1](https://llmcost.example.com/model/deepseek--deepseek-r1/): input $0.700, output $2.50 per 1M tokens, context 64000 tokens. Source: https://openrouter.ai/deepseek/deepseek-r1
- [OpenAI: o3](https://llmcost.example.com/model/openai--o3/): input $2.00, output $8.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3
- [DeepSeek: DeepSeek V3.1](https://llmcost.example.com/model/deepseek--deepseek-chat-v3.1/): input $0.550, output $1.65 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-chat-v3.1
- [Google: Gemini 2.5 Flash](https://llmcost.example.com/model/google--gemini-2.5-flash/): input $0.300, output $2.50 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-flash
- [OpenAI: o4 Mini](https://llmcost.example.com/model/openai--o4-mini/): input $1.10, output $4.40 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o4-mini
- [Qwen: Qwen3 235B A22B](https://llmcost.example.com/model/qwen--qwen3-235b-a22b/): input $0.455, output $1.82 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-235b-a22b
- [Meta: Llama 4 Maverick](https://llmcost.example.com/model/meta-llama--llama-4-maverick/): input $0.200, output $0.800 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/meta-llama/llama-4-maverick
- [Amazon: Nova Pro 1.0](https://llmcost.example.com/model/amazon--nova-pro-v1/): input $0.800, output $3.20 per 1M tokens, context 300000 tokens. Source: https://openrouter.ai/amazon/nova-pro-v1
- [OpenAI: GPT-5 Pro](https://llmcost.example.com/model/openai--gpt-5-pro/): input $15.00, output $120.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-pro
- [OpenAI: GPT-5 Mini](https://llmcost.example.com/model/openai--gpt-5-mini/): input $0.250, output $2.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-mini
- [Google: Gemini 2.5 Flash Lite](https://llmcost.example.com/model/google--gemini-2.5-flash-lite/): input $0.100, output $0.400 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-flash-lite
- [OpenAI: GPT-5 Nano](https://llmcost.example.com/model/openai--gpt-5-nano/): input $0.050, output $0.400 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-nano
- [Meta: Muse Spark 1.2 Contributor](https://llmcost.example.com/model/meta--muse-spark-1.2-contributor/): input $0.100, output $0.200 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/meta/muse-spark-1.2-contributor
- [DeepSeek: DeepSeek V4 Flash Vision Exp](https://llmcost.example.com/model/deepseek--deepseek-v4-flash-vision-exp/): input $0.220, output $0.660 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/deepseek/deepseek-v4-flash-vision-exp
- [Tencent: Hy-MT2-1.8B](https://llmcost.example.com/model/tencent--hy-mt2-1.8b/): input $0.044, output $0.177 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/tencent/hy-mt2-1.8b
- [Tencent: Hy-MT2-30B-A3B](https://llmcost.example.com/model/tencent--hy-mt2-30b-a3b/): input $0.074, output $0.295 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/tencent/hy-mt2-30b-a3b
- [Z.ai: GLM Latest](https://llmcost.example.com/model/-z-ai--glm-latest/): input $1.40, output $4.40 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/~z-ai/glm-latest
- [Tencent: Hy-MT2-7B](https://llmcost.example.com/model/tencent--hy-mt2-7b/): input $0.074, output $0.295 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/tencent/hy-mt2-7b
- [Z.ai: GLM 5.3](https://llmcost.example.com/model/z-ai--glm-5.3/): input $1.40, output $4.40 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/z-ai/glm-5.3
- [Qwen: Qwen3.8 27B](https://llmcost.example.com/model/qwen--qwen3.8-27b/): input $0.400, output $3.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.8-27b
- [Dots Studio: Dots3-Note Preview (free)](https://llmcost.example.com/model/dots-studio--dots-3-note-preview-free/): input Free, output Free per 1M tokens, context 512000 tokens. Source: https://openrouter.ai/dots-studio/dots-3-note-preview:free
- [Google: Gemini 3.7 Flash (batch)](https://llmcost.example.com/model/google--gemini-3.7-flash-batch/): input $0.188, output $0.938 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.7-flash:batch
- [ByteDance Seed: Seed 2.1 Turbo](https://llmcost.example.com/model/bytedance-seed--seed-2-1-turbo/): input $0.500, output $2.50 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/bytedance-seed/seed-2-1-turbo
- [Qwen: Qwen3.8 2.4T A95B](https://llmcost.example.com/model/qwen--qwen3.8-2.4t-a95b/): input $2.00, output $6.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/qwen/qwen3.8-2.4t-a95b
- [ByteDance Seed: Seed-2.0-Code](https://llmcost.example.com/model/bytedance-seed--seed-2.0-code/): input $0.500, output $3.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/bytedance-seed/seed-2.0-code
- [DeepSeek: DeepSeek V4 Pro 0813](https://llmcost.example.com/model/deepseek--deepseek-v4-pro-0813/): input $1.12, output $3.37 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/deepseek/deepseek-v4-pro-0813
- [SpaceXAI: Grok 4.6](https://llmcost.example.com/model/x-ai--grok-4.6/): input $2.00, output $6.00 per 1M tokens, context 500000 tokens. Source: https://openrouter.ai/x-ai/grok-4.6
- [LiquidAI: LFM2.5-2.6B (free)](https://llmcost.example.com/model/liquid--lfm-2.5-2.6b-free/): input Free, output Free per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/liquid/lfm-2.5-2.6b:free
- [NVIDIA: Nemotron 3.5 Lightning](https://llmcost.example.com/model/nvidia--nemotron-3.5-lightning/): input $0.080, output $0.200 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/nvidia/nemotron-3.5-lightning
- [NVIDIA: Nemotron 3.5 Lightning (free)](https://llmcost.example.com/model/nvidia--nemotron-3.5-lightning-free/): input Free, output Free per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/nvidia/nemotron-3.5-lightning:free
- [Sakana: Sakana Namazu](https://llmcost.example.com/model/sakana--sakana-namazu/): input $0.950, output $4.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/sakana/sakana-namazu
- [Upstage: Solar Pro 4](https://llmcost.example.com/model/upstage--solar-pro4/): input $0.030, output $0.120 per 1M tokens, context 524288 tokens. Source: https://openrouter.ai/upstage/solar-pro4
- [Meta: Muse Glimmer 30B](https://llmcost.example.com/model/meta--muse-glimmer-30b/): input $0.350, output $1.50 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/meta/muse-glimmer-30b
- [Meta: Muse Spark 1.2](https://llmcost.example.com/model/meta--muse-spark-1.2/): input $1.25, output $4.25 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/meta/muse-spark-1.2
- [Qwen: Qwen3.8 Max](https://llmcost.example.com/model/qwen--qwen3.8-max/): input $2.00, output $6.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.8-max
- [DeepSeek V4 Flash Latest](https://llmcost.example.com/model/-deepseek--deepseek-v4-flash-latest/): input $0.040, output $0.130 per 1M tokens, context 1310720 tokens. Source: https://openrouter.ai/~deepseek/deepseek-v4-flash-latest
- [DeepSeek: DeepSeek V4 Flash 0731](https://llmcost.example.com/model/deepseek--deepseek-v4-flash-0731/): input $0.080, output $0.180 per 1M tokens, context 1310720 tokens. Source: https://openrouter.ai/deepseek/deepseek-v4-flash-0731
- [Thinking Machines: Inkling Small](https://llmcost.example.com/model/thinkingmachines--inkling-small/): input $0.450, output $1.20 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/thinkingmachines/inkling-small
- [Thinking Machines: Inkling Small (free)](https://llmcost.example.com/model/thinkingmachines--inkling-small-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/thinkingmachines/inkling-small:free
- [Qwen: Qwen3.7 Flash](https://llmcost.example.com/model/qwen--qwen3.7-flash/): input $0.030, output $0.130 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.7-flash
- [Claude Opus 5 (batch)](https://llmcost.example.com/model/anthropic--claude-opus-5-batch/): input $2.50, output $12.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-5:batch
- [Ling-3.0-flash](https://llmcost.example.com/model/inclusionai--ling-3.0-flash/): input $0.021, output $0.063 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/inclusionai/ling-3.0-flash
- [Poolside: Laguna S 2.1](https://llmcost.example.com/model/poolside--laguna-s-2.1/): input $0.090, output $0.180 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/poolside/laguna-s-2.1
- [Poolside: Laguna S 2.1 (free)](https://llmcost.example.com/model/poolside--laguna-s-2.1-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/poolside/laguna-s-2.1:free
- [Google: Gemini 3.6 Flash (batch)](https://llmcost.example.com/model/google--gemini-3.6-flash-batch/): input $0.375, output $1.88 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.6-flash:batch
- [Google: Gemini 3.5 Flash Lite (batch)](https://llmcost.example.com/model/google--gemini-3.5-flash-lite-batch/): input $0.150, output $1.25 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.5-flash-lite:batch
- [Meituan: LongCat 2.0](https://llmcost.example.com/model/meituan--longcat-2.0/): input $0.300, output $1.20 per 1M tokens, context 1048756 tokens. Source: https://openrouter.ai/meituan/longcat-2.0
- [Thinking Machines: Inkling](https://llmcost.example.com/model/thinkingmachines--inkling/): input $1.00, output $4.05 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/thinkingmachines/inkling
- [Thinking Machines: Inkling (batch)](https://llmcost.example.com/model/thinkingmachines--inkling-batch/): input $1.00, output $4.05 per 1M tokens, context 524288 tokens. Source: https://openrouter.ai/thinkingmachines/inkling:batch
- [Thinking Machines: Inkling (free)](https://llmcost.example.com/model/thinkingmachines--inkling-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/thinkingmachines/inkling:free
- [MoonshotAI: Kimi K3](https://llmcost.example.com/model/moonshotai--kimi-k3/): input $3.00, output $15.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/moonshotai/kimi-k3
- [Meta: Muse Spark 1.1](https://llmcost.example.com/model/meta--muse-spark-1.1/): input $1.25, output $4.25 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/meta/muse-spark-1.1
- [Kwaipilot: KAT-Coder-Air V2.5](https://llmcost.example.com/model/kwaipilot--kat-coder-air-v2.5/): input $0.150, output $0.600 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/kwaipilot/kat-coder-air-v2.5
- [Kwaipilot: KAT-Coder-Pro V2.5](https://llmcost.example.com/model/kwaipilot--kat-coder-pro-v2.5/): input $0.740, output $2.96 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/kwaipilot/kat-coder-pro-v2.5
- [OpenAI: GPT-5.6 Luna Pro](https://llmcost.example.com/model/openai--gpt-5.6-luna-pro/): input $0.200, output $1.20 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-luna-pro
- [OpenAI: GPT-5.6 Luna Pro (batch)](https://llmcost.example.com/model/openai--gpt-5.6-luna-pro-batch/): input $0.100, output $0.600 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-luna-pro:batch
- [OpenAI: GPT-5.6 Luna (batch)](https://llmcost.example.com/model/openai--gpt-5.6-luna-batch/): input $0.100, output $0.600 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-luna:batch
- [OpenAI: GPT-5.6 Terra Pro (batch)](https://llmcost.example.com/model/openai--gpt-5.6-terra-pro-batch/): input $1.00, output $6.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-terra-pro:batch
- [OpenAI: GPT-5.6 Terra](https://llmcost.example.com/model/openai--gpt-5.6-terra/): input $2.00, output $12.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-terra
- [OpenAI: GPT-5.6 Terra (batch)](https://llmcost.example.com/model/openai--gpt-5.6-terra-batch/): input $1.00, output $6.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-terra:batch
- [OpenAI: GPT-5.6 Sol Pro](https://llmcost.example.com/model/openai--gpt-5.6-sol-pro/): input $2.00, output $10.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-sol-pro
- [OpenAI: GPT-5.6 Sol Pro (batch)](https://llmcost.example.com/model/openai--gpt-5.6-sol-pro-batch/): input $1.00, output $5.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-sol-pro:batch
- [OpenAI: GPT-5.6 Sol (batch)](https://llmcost.example.com/model/openai--gpt-5.6-sol-batch/): input $1.00, output $5.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.6-sol:batch
- [SpaceXAI: Grok 4.5](https://llmcost.example.com/model/x-ai--grok-4.5/): input $2.00, output $6.00 per 1M tokens, context 500000 tokens. Source: https://openrouter.ai/x-ai/grok-4.5
- [xAI: Grok Latest](https://llmcost.example.com/model/-x-ai--grok-latest/): input $2.00, output $6.00 per 1M tokens, context 500000 tokens. Source: https://openrouter.ai/~x-ai/grok-latest
- [AionLabs: Aion-3.0-Mini](https://llmcost.example.com/model/aion-labs--aion-3.0-mini/): input $0.700, output $1.40 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/aion-labs/aion-3.0-mini
- [AionLabs: Aion-3.0](https://llmcost.example.com/model/aion-labs--aion-3.0/): input $3.00, output $6.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/aion-labs/aion-3.0
- [Tencent: Hy3](https://llmcost.example.com/model/tencent--hy3/): input $0.132, output $0.528 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/tencent/hy3
- [Poolside: Laguna XS 2.1](https://llmcost.example.com/model/poolside--laguna-xs-2.1/): input $0.060, output $0.120 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/poolside/laguna-xs-2.1
- [Poolside: Laguna XS 2.1 (free)](https://llmcost.example.com/model/poolside--laguna-xs-2.1-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/poolside/laguna-xs-2.1:free
- [Anthropic: Claude Sonnet 5 (batch)](https://llmcost.example.com/model/anthropic--claude-sonnet-5-batch/): input $1.00, output $5.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-5:batch
- [Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)](https://llmcost.example.com/model/google--gemini-3.1-flash-lite-image/): input $0.250, output $1.50 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/google/gemini-3.1-flash-lite-image
- [Nex AGI: Nex-N2-Mini](https://llmcost.example.com/model/nex-agi--nex-n2-mini/): input $0.025, output $0.100 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/nex-agi/nex-n2-mini
- [Sakana: Fugu Ultra](https://llmcost.example.com/model/sakana--fugu-ultra/): input $5.00, output $30.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/sakana/fugu-ultra
- [Google: Nano Banana 2 (Gemini 3.1 Flash Image)](https://llmcost.example.com/model/google--gemini-3.1-flash-image/): input $0.500, output $3.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/google/gemini-3.1-flash-image
- [Google: Nano Banana Pro (Gemini 3 Pro Image)](https://llmcost.example.com/model/google--gemini-3-pro-image/): input $2.00, output $12.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/google/gemini-3-pro-image
- [Cohere: North Mini Code (free)](https://llmcost.example.com/model/cohere--north-mini-code-free/): input Free, output Free per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/cohere/north-mini-code:free
- [Z.ai: GLM 5.2](https://llmcost.example.com/model/z-ai--glm-5.2/): input $0.966, output $3.04 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/z-ai/glm-5.2
- [Z.ai: GLM 5.2 (batch)](https://llmcost.example.com/model/z-ai--glm-5.2-batch/): input $1.40, output $4.40 per 1M tokens, context 1048575 tokens. Source: https://openrouter.ai/z-ai/glm-5.2:batch
- [Z.ai: GLM 5.2 (free)](https://llmcost.example.com/model/z-ai--glm-5.2-free/): input Free, output Free per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/z-ai/glm-5.2:free
- [MoonshotAI: Kimi K2.7 Code](https://llmcost.example.com/model/moonshotai--kimi-k2.7-code/): input $0.670, output $3.40 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2.7-code
- [MoonshotAI: Kimi K2.7 Code (batch)](https://llmcost.example.com/model/moonshotai--kimi-k2.7-code-batch/): input $0.950, output $4.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2.7-code:batch
- [Anthropic: Claude Fable Latest](https://llmcost.example.com/model/-anthropic--claude-fable-latest/): input $10.00, output $50.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/~anthropic/claude-fable-latest
- [Anthropic: Claude Fable 5 (batch)](https://llmcost.example.com/model/anthropic--claude-fable-5-batch/): input $5.00, output $25.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-fable-5:batch
- [Nex AGI: Nex-N2-Pro](https://llmcost.example.com/model/nex-agi--nex-n2-pro/): input $0.250, output $1.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/nex-agi/nex-n2-pro
- [NVIDIA: Nemotron 3.5 Content Safety (free)](https://llmcost.example.com/model/nvidia--nemotron-3.5-content-safety-free/): input Free, output Free per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/nvidia/nemotron-3.5-content-safety:free
- [NVIDIA: Nemotron 3 Ultra](https://llmcost.example.com/model/nvidia--nemotron-3-ultra-550b-a55b/): input $0.600, output $3.60 per 1M tokens, context 512288 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b
- [NVIDIA: Nemotron 3 Ultra (batch)](https://llmcost.example.com/model/nvidia--nemotron-3-ultra-550b-a55b-batch/): input $0.600, output $3.60 per 1M tokens, context 512288 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:batch
- [NVIDIA: Nemotron 3 Ultra (free)](https://llmcost.example.com/model/nvidia--nemotron-3-ultra-550b-a55b-free/): input Free, output Free per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b:free
- [Qwen: Qwen3.7 Plus](https://llmcost.example.com/model/qwen--qwen3.7-plus/): input $0.320, output $1.28 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.7-plus
- [MiniMax: MiniMax M3](https://llmcost.example.com/model/minimax--minimax-m3/): input $0.300, output $1.20 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/minimax/minimax-m3
- [MiniMax: MiniMax M3 (batch)](https://llmcost.example.com/model/minimax--minimax-m3-batch/): input $0.300, output $1.20 per 1M tokens, context 524288 tokens. Source: https://openrouter.ai/minimax/minimax-m3:batch
- [StepFun: Step 3.7 Flash](https://llmcost.example.com/model/stepfun--step-3.7-flash/): input $0.200, output $1.15 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/stepfun/step-3.7-flash
- [Anthropic: Claude Opus 4.8 (Fast)](https://llmcost.example.com/model/anthropic--claude-opus-4.8-fast/): input $10.00, output $50.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.8-fast
- [Anthropic: Claude Opus 4.8](https://llmcost.example.com/model/anthropic--claude-opus-4.8/): input $5.00, output $25.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.8
- [Anthropic: Claude Opus 4.8 (batch)](https://llmcost.example.com/model/anthropic--claude-opus-4.8-batch/): input $2.50, output $12.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.8:batch
- [Qwen: Qwen3.7 Max](https://llmcost.example.com/model/qwen--qwen3.7-max/): input $1.48, output $4.42 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.7-max
- [SpaceXAI: Grok Build 0.1](https://llmcost.example.com/model/x-ai--grok-build-0.1/): input $1.00, output $2.00 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/x-ai/grok-build-0.1
- [Google: Gemini 3.5 Flash (batch)](https://llmcost.example.com/model/google--gemini-3.5-flash-batch/): input $0.750, output $4.50 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.5-flash:batch
- [Anthropic: Claude Opus 4.7 (Fast)](https://llmcost.example.com/model/anthropic--claude-opus-4.7-fast/): input $30.00, output $150.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.7-fast
- [Perceptron: Perceptron Mk1](https://llmcost.example.com/model/perceptron--perceptron-mk1/): input $0.150, output $1.50 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/perceptron/perceptron-mk1
- [inclusionAI: Ring-2.6-1T](https://llmcost.example.com/model/inclusionai--ring-2.6-1t/): input $0.075, output $0.625 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/inclusionai/ring-2.6-1t
- [Google: Gemini 3.1 Flash Lite](https://llmcost.example.com/model/google--gemini-3.1-flash-lite/): input $0.250, output $1.50 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.1-flash-lite
- [Google: Gemini 3.1 Flash Lite (batch)](https://llmcost.example.com/model/google--gemini-3.1-flash-lite-batch/): input $0.125, output $0.750 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.1-flash-lite:batch
- [OpenAI: GPT Chat Latest](https://llmcost.example.com/model/openai--gpt-chat-latest/): input $5.00, output $30.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-chat-latest
- [SpaceXAI: Grok 4.3](https://llmcost.example.com/model/x-ai--grok-4.3/): input $1.25, output $2.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/x-ai/grok-4.3
- [IBM: Granite 4.1 8B](https://llmcost.example.com/model/ibm-granite--granite-4.1-8b/): input $0.050, output $0.100 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/ibm-granite/granite-4.1-8b
- [Mistral: Mistral Medium 3.5](https://llmcost.example.com/model/mistralai--mistral-medium-3-5/): input $1.50, output $7.50 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/mistralai/mistral-medium-3-5
- [NVIDIA: Nemotron 3 Nano Omni (free)](https://llmcost.example.com/model/nvidia--nemotron-3-nano-omni-30b-a3b-reasoning-free/): input Free, output Free per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
- [Anthropic Claude Haiku Latest](https://llmcost.example.com/model/-anthropic--claude-haiku-latest/): input $1.00, output $5.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/~anthropic/claude-haiku-latest
- [OpenAI GPT Mini Latest](https://llmcost.example.com/model/-openai--gpt-mini-latest/): input $0.750, output $4.50 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/~openai/gpt-mini-latest
- [Google Gemini Pro Latest](https://llmcost.example.com/model/-google--gemini-pro-latest/): input $2.00, output $12.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/~google/gemini-pro-latest
- [MoonshotAI Kimi Latest](https://llmcost.example.com/model/-moonshotai--kimi-latest/): input $2.60, output $13.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/~moonshotai/kimi-latest
- [Google Gemini Flash Latest](https://llmcost.example.com/model/-google--gemini-flash-latest/): input $0.375, output $1.88 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/~google/gemini-flash-latest
- [Anthropic Claude Sonnet Latest](https://llmcost.example.com/model/-anthropic--claude-sonnet-latest/): input $2.00, output $10.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/~anthropic/claude-sonnet-latest
- [OpenAI GPT Latest](https://llmcost.example.com/model/-openai--gpt-latest/): input $2.00, output $10.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/~openai/gpt-latest
- [Qwen: Qwen3.5 Plus 2026-04-20](https://llmcost.example.com/model/qwen--qwen3.5-plus-20260420/): input $0.300, output $1.80 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.5-plus-20260420
- [Qwen: Qwen3.6 Flash](https://llmcost.example.com/model/qwen--qwen3.6-flash/): input $0.188, output $1.13 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.6-flash
- [Qwen: Qwen3.6 35B A3B](https://llmcost.example.com/model/qwen--qwen3.6-35b-a3b/): input $0.140, output $1.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.6-35b-a3b
- [Qwen: Qwen3.6 Max Preview](https://llmcost.example.com/model/qwen--qwen3.6-max-preview/): input $1.03, output $6.16 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.6-max-preview
- [Qwen: Qwen3.6 27B](https://llmcost.example.com/model/qwen--qwen3.6-27b/): input $0.600, output $3.60 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.6-27b
- [OpenAI: GPT-5.5 Pro (batch)](https://llmcost.example.com/model/openai--gpt-5.5-pro-batch/): input $15.00, output $90.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.5-pro:batch
- [OpenAI: GPT-5.5 (batch)](https://llmcost.example.com/model/openai--gpt-5.5-batch/): input $2.50, output $15.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.5:batch
- [DeepSeek: DeepSeek V4 Pro 0423](https://llmcost.example.com/model/deepseek--deepseek-v4-pro/): input $0.397, output $0.794 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/deepseek/deepseek-v4-pro
- [DeepSeek: DeepSeek V4 Flash 0423](https://llmcost.example.com/model/deepseek--deepseek-v4-flash/): input $0.050, output $0.101 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/deepseek/deepseek-v4-flash
- [inclusionAI: Ling-2.6-1T](https://llmcost.example.com/model/inclusionai--ling-2.6-1t/): input $0.075, output $0.625 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/inclusionai/ling-2.6-1t
- [Tencent: Hy3 preview](https://llmcost.example.com/model/tencent--hy3-preview/): input $0.180, output $0.600 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/tencent/hy3-preview
- [Xiaomi: MiMo-V2.5-Pro](https://llmcost.example.com/model/xiaomi--mimo-v2.5-pro/): input $0.435, output $0.870 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/xiaomi/mimo-v2.5-pro
- [Xiaomi: MiMo-V2.5](https://llmcost.example.com/model/xiaomi--mimo-v2.5/): input $0.140, output $0.280 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/xiaomi/mimo-v2.5
- [OpenAI: GPT-5.4 Image 2](https://llmcost.example.com/model/openai--gpt-5.4-image-2/): input $8.00, output $15.00 per 1M tokens, context 272000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-image-2
- [inclusionAI: Ling-2.6-flash](https://llmcost.example.com/model/inclusionai--ling-2.6-flash/): input $0.010, output $0.030 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/inclusionai/ling-2.6-flash
- [Anthropic: Claude Opus Latest](https://llmcost.example.com/model/-anthropic--claude-opus-latest/): input $5.00, output $25.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/~anthropic/claude-opus-latest
- [MoonshotAI: Kimi K2.6](https://llmcost.example.com/model/moonshotai--kimi-k2.6/): input $0.950, output $4.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2.6
- [Anthropic: Claude Opus 4.7](https://llmcost.example.com/model/anthropic--claude-opus-4.7/): input $5.00, output $25.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.7
- [Anthropic: Claude Opus 4.7 (batch)](https://llmcost.example.com/model/anthropic--claude-opus-4.7-batch/): input $2.50, output $12.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.7:batch
- [Z.ai: GLM 5.1](https://llmcost.example.com/model/z-ai--glm-5.1/): input $0.966, output $3.04 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/z-ai/glm-5.1
- [Google: Gemma 4 26B A4B ](https://llmcost.example.com/model/google--gemma-4-26b-a4b-it/): input $0.070, output $0.340 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/google/gemma-4-26b-a4b-it
- [Google: Gemma 4 26B A4B  (free)](https://llmcost.example.com/model/google--gemma-4-26b-a4b-it-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/google/gemma-4-26b-a4b-it:free
- [Google: Gemma 4 31B](https://llmcost.example.com/model/google--gemma-4-31b-it/): input $0.100, output $0.340 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/google/gemma-4-31b-it
- [Google: Gemma 4 31B (free)](https://llmcost.example.com/model/google--gemma-4-31b-it-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/google/gemma-4-31b-it:free
- [Qwen: Qwen3.6 Plus](https://llmcost.example.com/model/qwen--qwen3.6-plus/): input $0.325, output $1.95 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.6-plus
- [Z.ai: GLM 5V Turbo](https://llmcost.example.com/model/z-ai--glm-5v-turbo/): input $1.20, output $4.00 per 1M tokens, context 202752 tokens. Source: https://openrouter.ai/z-ai/glm-5v-turbo
- [Arcee AI: Trinity Large Thinking](https://llmcost.example.com/model/arcee-ai--trinity-large-thinking/): input $0.220, output $0.850 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/arcee-ai/trinity-large-thinking
- [SpaceXAI: Grok 4.20 Multi-Agent](https://llmcost.example.com/model/x-ai--grok-4.20-multi-agent/): input $1.25, output $2.50 per 1M tokens, context 2000000 tokens. Source: https://openrouter.ai/x-ai/grok-4.20-multi-agent
- [SpaceXAI: Grok 4.20](https://llmcost.example.com/model/x-ai--grok-4.20/): input $1.25, output $2.50 per 1M tokens, context 2000000 tokens. Source: https://openrouter.ai/x-ai/grok-4.20
- [Kwaipilot: KAT-Coder-Pro V2](https://llmcost.example.com/model/kwaipilot--kat-coder-pro-v2/): input $0.300, output $1.20 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/kwaipilot/kat-coder-pro-v2
- [Reka Edge](https://llmcost.example.com/model/rekaai--reka-edge/): input $0.100, output $0.100 per 1M tokens, context 16384 tokens. Source: https://openrouter.ai/rekaai/reka-edge
- [MiniMax: MiniMax M2.7](https://llmcost.example.com/model/minimax--minimax-m2.7/): input $0.300, output $1.20 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/minimax/minimax-m2.7
- [OpenAI: GPT-5.4 Nano (batch)](https://llmcost.example.com/model/openai--gpt-5.4-nano-batch/): input $0.100, output $0.625 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-nano:batch
- [OpenAI: GPT-5.4 Mini (batch)](https://llmcost.example.com/model/openai--gpt-5.4-mini-batch/): input $0.375, output $2.25 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-mini:batch
- [Mistral: Mistral Small 4](https://llmcost.example.com/model/mistralai--mistral-small-2603/): input $0.150, output $0.600 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/mistralai/mistral-small-2603
- [Z.ai: GLM 5 Turbo](https://llmcost.example.com/model/z-ai--glm-5-turbo/): input $1.20, output $4.00 per 1M tokens, context 202752 tokens. Source: https://openrouter.ai/z-ai/glm-5-turbo
- [NVIDIA: Nemotron 3 Super](https://llmcost.example.com/model/nvidia--nemotron-3-super-120b-a12b/): input $0.085, output $0.400 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b
- [NVIDIA: Nemotron 3 Super (free)](https://llmcost.example.com/model/nvidia--nemotron-3-super-120b-a12b-free/): input Free, output Free per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-super-120b-a12b:free
- [ByteDance Seed: Seed-2.0-Lite](https://llmcost.example.com/model/bytedance-seed--seed-2.0-lite/): input $0.250, output $2.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/bytedance-seed/seed-2.0-lite
- [Qwen: Qwen3.5-9B](https://llmcost.example.com/model/qwen--qwen3.5-9b/): input $0.100, output $0.150 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.5-9b
- [OpenAI: GPT-5.4 Pro](https://llmcost.example.com/model/openai--gpt-5.4-pro/): input $30.00, output $180.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-pro
- [OpenAI: GPT-5.4 Pro (batch)](https://llmcost.example.com/model/openai--gpt-5.4-pro-batch/): input $15.00, output $90.00 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.4-pro:batch
- [OpenAI: GPT-5.4 (batch)](https://llmcost.example.com/model/openai--gpt-5.4-batch/): input $1.25, output $7.50 per 1M tokens, context 1050000 tokens. Source: https://openrouter.ai/openai/gpt-5.4:batch
- [Inception: Mercury 2](https://llmcost.example.com/model/inception--mercury-2/): input $0.250, output $0.750 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/inception/mercury-2
- [Google: Gemini 3.1 Flash Lite Preview](https://llmcost.example.com/model/google--gemini-3.1-flash-lite-preview/): input $0.250, output $1.50 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.1-flash-lite-preview
- [ByteDance Seed: Seed-2.0-Mini](https://llmcost.example.com/model/bytedance-seed--seed-2.0-mini/): input $0.100, output $0.400 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/bytedance-seed/seed-2.0-mini
- [Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)](https://llmcost.example.com/model/google--gemini-3.1-flash-image-preview/): input $0.500, output $3.00 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/google/gemini-3.1-flash-image-preview
- [Qwen: Qwen3.5-35B-A3B](https://llmcost.example.com/model/qwen--qwen3.5-35b-a3b/): input $0.250, output $1.25 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.5-35b-a3b
- [Qwen: Qwen3.5-27B](https://llmcost.example.com/model/qwen--qwen3.5-27b/): input $0.195, output $1.56 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.5-27b
- [Qwen: Qwen3.5-122B-A10B](https://llmcost.example.com/model/qwen--qwen3.5-122b-a10b/): input $0.260, output $2.08 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.5-122b-a10b
- [Qwen: Qwen3.5-Flash](https://llmcost.example.com/model/qwen--qwen3.5-flash-02-23/): input $0.065, output $0.260 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.5-flash-02-23
- [Google: Gemini 3.1 Pro Preview Custom Tools](https://llmcost.example.com/model/google--gemini-3.1-pro-preview-customtools/): input $2.00, output $12.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.1-pro-preview-customtools
- [OpenAI: GPT-5.3-Codex](https://llmcost.example.com/model/openai--gpt-5.3-codex/): input $1.75, output $14.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.3-codex
- [AionLabs: Aion-2.0](https://llmcost.example.com/model/aion-labs--aion-2.0/): input $0.800, output $1.60 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/aion-labs/aion-2.0
- [Google: Gemini 3.1 Pro Preview](https://llmcost.example.com/model/google--gemini-3.1-pro-preview/): input $2.00, output $12.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.1-pro-preview
- [Google: Gemini 3.1 Pro Preview (batch)](https://llmcost.example.com/model/google--gemini-3.1-pro-preview-batch/): input $1.00, output $6.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3.1-pro-preview:batch
- [Anthropic: Claude Sonnet 4.6](https://llmcost.example.com/model/anthropic--claude-sonnet-4.6/): input $3.00, output $15.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-4.6
- [Anthropic: Claude Sonnet 4.6 (batch)](https://llmcost.example.com/model/anthropic--claude-sonnet-4.6-batch/): input $1.50, output $7.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-4.6:batch
- [Qwen: Qwen3.5 Plus 2026-02-15](https://llmcost.example.com/model/qwen--qwen3.5-plus-02-15/): input $0.260, output $1.56 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3.5-plus-02-15
- [Qwen: Qwen3.5 397B A17B](https://llmcost.example.com/model/qwen--qwen3.5-397b-a17b/): input $0.390, output $2.34 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3.5-397b-a17b
- [MiniMax: MiniMax M2.5](https://llmcost.example.com/model/minimax--minimax-m2.5/): input $0.270, output $1.08 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/minimax/minimax-m2.5
- [Z.ai: GLM 5](https://llmcost.example.com/model/z-ai--glm-5/): input $0.600, output $1.92 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/z-ai/glm-5
- [Qwen: Qwen3 Max Thinking](https://llmcost.example.com/model/qwen--qwen3-max-thinking/): input $0.780, output $3.90 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-max-thinking
- [Anthropic: Claude Opus 4.6](https://llmcost.example.com/model/anthropic--claude-opus-4.6/): input $5.00, output $25.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.6
- [Anthropic: Claude Opus 4.6 (batch)](https://llmcost.example.com/model/anthropic--claude-opus-4.6-batch/): input $2.50, output $12.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.6:batch
- [Qwen: Qwen3 Coder Next](https://llmcost.example.com/model/qwen--qwen3-coder-next/): input $0.120, output $0.800 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-coder-next
- [StepFun: Step 3.5 Flash](https://llmcost.example.com/model/stepfun--step-3.5-flash/): input $0.100, output $0.300 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/stepfun/step-3.5-flash
- [MoonshotAI: Kimi K2.5](https://llmcost.example.com/model/moonshotai--kimi-k2.5/): input $0.450, output $2.25 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2.5
- [Upstage: Solar Pro 3](https://llmcost.example.com/model/upstage--solar-pro-3/): input $0.150, output $0.600 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/upstage/solar-pro-3
- [MiniMax: MiniMax M2-her](https://llmcost.example.com/model/minimax--minimax-m2-her/): input $0.300, output $1.20 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/minimax/minimax-m2-her
- [Writer: Palmyra X5](https://llmcost.example.com/model/writer--palmyra-x5/): input $0.600, output $6.00 per 1M tokens, context 1040000 tokens. Source: https://openrouter.ai/writer/palmyra-x5
- [OpenAI: GPT Audio](https://llmcost.example.com/model/openai--gpt-audio/): input $2.50, output $10.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-audio
- [OpenAI: GPT Audio Mini](https://llmcost.example.com/model/openai--gpt-audio-mini/): input $0.600, output $2.40 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-audio-mini
- [Z.ai: GLM 4.7 Flash](https://llmcost.example.com/model/z-ai--glm-4.7-flash/): input $0.060, output $0.400 per 1M tokens, context 202752 tokens. Source: https://openrouter.ai/z-ai/glm-4.7-flash
- [OpenAI: GPT-5.2-Codex](https://llmcost.example.com/model/openai--gpt-5.2-codex/): input $1.75, output $14.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.2-codex
- [ByteDance Seed: Seed 1.6 Flash](https://llmcost.example.com/model/bytedance-seed--seed-1.6-flash/): input $0.075, output $0.300 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/bytedance-seed/seed-1.6-flash
- [ByteDance Seed: Seed 1.6](https://llmcost.example.com/model/bytedance-seed--seed-1.6/): input $0.250, output $2.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/bytedance-seed/seed-1.6
- [MiniMax: MiniMax M2.1](https://llmcost.example.com/model/minimax--minimax-m2.1/): input $0.300, output $1.20 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/minimax/minimax-m2.1
- [Z.ai: GLM 4.7](https://llmcost.example.com/model/z-ai--glm-4.7/): input $0.400, output $1.75 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/z-ai/glm-4.7
- [Google: Gemini 3 Flash Preview](https://llmcost.example.com/model/google--gemini-3-flash-preview/): input $0.500, output $3.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3-flash-preview
- [Google: Gemini 3 Flash Preview (batch)](https://llmcost.example.com/model/google--gemini-3-flash-preview-batch/): input $0.250, output $1.50 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-3-flash-preview:batch
- [NVIDIA: Nemotron 3 Nano 30B A3B](https://llmcost.example.com/model/nvidia--nemotron-3-nano-30b-a3b/): input $0.050, output $0.200 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b
- [NVIDIA: Nemotron 3 Nano 30B A3B (free)](https://llmcost.example.com/model/nvidia--nemotron-3-nano-30b-a3b-free/): input Free, output Free per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/nvidia/nemotron-3-nano-30b-a3b:free
- [OpenAI: GPT-5.2 Chat](https://llmcost.example.com/model/openai--gpt-5.2-chat/): input $1.75, output $14.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-5.2-chat
- [OpenAI: GPT-5.2 Pro](https://llmcost.example.com/model/openai--gpt-5.2-pro/): input $21.00, output $168.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.2-pro
- [OpenAI: GPT-5.2 Pro (batch)](https://llmcost.example.com/model/openai--gpt-5.2-pro-batch/): input $10.50, output $84.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.2-pro:batch
- [OpenAI: GPT-5.2](https://llmcost.example.com/model/openai--gpt-5.2/): input $1.75, output $14.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.2
- [OpenAI: GPT-5.2 (batch)](https://llmcost.example.com/model/openai--gpt-5.2-batch/): input $0.875, output $7.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.2:batch
- [Relace: Relace Search](https://llmcost.example.com/model/relace--relace-search/): input $1.00, output $3.00 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/relace/relace-search
- [Z.ai: GLM 4.6V](https://llmcost.example.com/model/z-ai--glm-4.6v/): input $0.300, output $0.900 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/z-ai/glm-4.6v
- [OpenAI: GPT-5.1-Codex-Max](https://llmcost.example.com/model/openai--gpt-5.1-codex-max/): input $1.25, output $10.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.1-codex-max
- [Amazon: Nova 2 Lite](https://llmcost.example.com/model/amazon--nova-2-lite-v1/): input $0.300, output $2.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/amazon/nova-2-lite-v1
- [Mistral: Ministral 3 14B 2512](https://llmcost.example.com/model/mistralai--ministral-14b-2512/): input $0.200, output $0.200 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/mistralai/ministral-14b-2512
- [Mistral: Ministral 3 8B 2512](https://llmcost.example.com/model/mistralai--ministral-8b-2512/): input $0.150, output $0.150 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/mistralai/ministral-8b-2512
- [Mistral: Ministral 3 3B 2512](https://llmcost.example.com/model/mistralai--ministral-3b-2512/): input $0.100, output $0.100 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/mistralai/ministral-3b-2512
- [Mistral: Mistral Large 3 2512](https://llmcost.example.com/model/mistralai--mistral-large-2512/): input $0.500, output $1.50 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/mistralai/mistral-large-2512
- [DeepSeek: DeepSeek V3.2](https://llmcost.example.com/model/deepseek--deepseek-v3.2/): input $0.260, output $0.380 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-v3.2
- [Anthropic: Claude Opus 4.5](https://llmcost.example.com/model/anthropic--claude-opus-4.5/): input $5.00, output $25.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.5
- [Anthropic: Claude Opus 4.5 (batch)](https://llmcost.example.com/model/anthropic--claude-opus-4.5-batch/): input $2.50, output $12.50 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.5:batch
- [AllenAI: Olmo 3 32B Think](https://llmcost.example.com/model/allenai--olmo-3-32b-think/): input $0.150, output $0.500 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/allenai/olmo-3-32b-think
- [Google: Nano Banana Pro (Gemini 3 Pro Image Preview)](https://llmcost.example.com/model/google--gemini-3-pro-image-preview/): input $2.00, output $12.00 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/google/gemini-3-pro-image-preview
- [OpenAI: GPT-5.1](https://llmcost.example.com/model/openai--gpt-5.1/): input $1.25, output $10.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.1
- [OpenAI: GPT-5.1 (batch)](https://llmcost.example.com/model/openai--gpt-5.1-batch/): input $0.625, output $5.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.1:batch
- [OpenAI: GPT-5.1-Codex](https://llmcost.example.com/model/openai--gpt-5.1-codex/): input $1.25, output $10.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.1-codex
- [OpenAI: GPT-5.1-Codex-Mini](https://llmcost.example.com/model/openai--gpt-5.1-codex-mini/): input $0.250, output $2.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5.1-codex-mini
- [MoonshotAI: Kimi K2 Thinking](https://llmcost.example.com/model/moonshotai--kimi-k2-thinking/): input $0.600, output $2.50 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2-thinking
- [Amazon: Nova Premier 1.0](https://llmcost.example.com/model/amazon--nova-premier-v1/): input $2.50, output $12.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/amazon/nova-premier-v1
- [Perplexity: Sonar Pro Search](https://llmcost.example.com/model/perplexity--sonar-pro-search/): input $3.00, output $15.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/perplexity/sonar-pro-search
- [Mistral: Voxtral Small 24B 2507](https://llmcost.example.com/model/mistralai--voxtral-small-24b-2507/): input $0.100, output $0.300 per 1M tokens, context 32000 tokens. Source: https://openrouter.ai/mistralai/voxtral-small-24b-2507
- [OpenAI: gpt-oss-safeguard-20b](https://llmcost.example.com/model/openai--gpt-oss-safeguard-20b/): input $0.075, output $0.300 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/openai/gpt-oss-safeguard-20b
- [NVIDIA: Nemotron Nano 12B 2 VL (free)](https://llmcost.example.com/model/nvidia--nemotron-nano-12b-v2-vl-free/): input Free, output Free per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/nvidia/nemotron-nano-12b-v2-vl:free
- [MiniMax: MiniMax M2](https://llmcost.example.com/model/minimax--minimax-m2/): input $0.255, output $1.02 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/minimax/minimax-m2
- [Qwen: Qwen3 VL 32B Instruct](https://llmcost.example.com/model/qwen--qwen3-vl-32b-instruct/): input $0.104, output $0.416 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-32b-instruct
- [IBM: Granite 4.0 Micro](https://llmcost.example.com/model/ibm-granite--granite-4.0-h-micro/): input $0.017, output $0.112 per 1M tokens, context 131000 tokens. Source: https://openrouter.ai/ibm-granite/granite-4.0-h-micro
- [OpenAI: GPT-5 Image Mini](https://llmcost.example.com/model/openai--gpt-5-image-mini/): input $2.50, output $2.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-image-mini
- [Anthropic: Claude Haiku 4.5](https://llmcost.example.com/model/anthropic--claude-haiku-4.5/): input $1.00, output $5.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-haiku-4.5
- [Anthropic: Claude Haiku 4.5 (batch)](https://llmcost.example.com/model/anthropic--claude-haiku-4.5-batch/): input $0.500, output $2.50 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-haiku-4.5:batch
- [Qwen: Qwen3 VL 8B Thinking](https://llmcost.example.com/model/qwen--qwen3-vl-8b-thinking/): input $0.180, output $2.10 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-8b-thinking
- [Qwen: Qwen3 VL 8B Instruct](https://llmcost.example.com/model/qwen--qwen3-vl-8b-instruct/): input $0.117, output $0.455 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-8b-instruct
- [OpenAI: GPT-5 Image](https://llmcost.example.com/model/openai--gpt-5-image/): input $10.00, output $10.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-image
- [Google: Nano Banana (Gemini 2.5 Flash Image)](https://llmcost.example.com/model/google--gemini-2.5-flash-image/): input $0.300, output $2.50 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/google/gemini-2.5-flash-image
- [Qwen: Qwen3 VL 30B A3B Thinking](https://llmcost.example.com/model/qwen--qwen3-vl-30b-a3b-thinking/): input $0.200, output $2.40 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-30b-a3b-thinking
- [Qwen: Qwen3 VL 30B A3B Instruct](https://llmcost.example.com/model/qwen--qwen3-vl-30b-a3b-instruct/): input $0.130, output $0.520 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-30b-a3b-instruct
- [OpenAI: GPT-5 Pro (batch)](https://llmcost.example.com/model/openai--gpt-5-pro-batch/): input $7.50, output $60.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-pro:batch
- [Z.ai: GLM 4.6](https://llmcost.example.com/model/z-ai--glm-4.6/): input $0.500, output $2.00 per 1M tokens, context 204800 tokens. Source: https://openrouter.ai/z-ai/glm-4.6
- [Anthropic: Claude Sonnet 4.5 (batch)](https://llmcost.example.com/model/anthropic--claude-sonnet-4.5-batch/): input $1.50, output $7.50 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-4.5:batch
- [DeepSeek: DeepSeek V3.2 Exp](https://llmcost.example.com/model/deepseek--deepseek-v3.2-exp/): input $0.270, output $0.410 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-v3.2-exp
- [TheDrummer: Cydonia 24B V4.1](https://llmcost.example.com/model/thedrummer--cydonia-24b-v4.1/): input $0.300, output $0.500 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/thedrummer/cydonia-24b-v4.1
- [Relace: Relace Apply 3](https://llmcost.example.com/model/relace--relace-apply-3/): input $0.850, output $1.25 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/relace/relace-apply-3
- [Qwen: Qwen3 VL 235B A22B Thinking](https://llmcost.example.com/model/qwen--qwen3-vl-235b-a22b-thinking/): input $0.400, output $4.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-235b-a22b-thinking
- [Qwen: Qwen3 VL 235B A22B Instruct](https://llmcost.example.com/model/qwen--qwen3-vl-235b-a22b-instruct/): input $0.210, output $1.90 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-vl-235b-a22b-instruct
- [Qwen: Qwen3 Max](https://llmcost.example.com/model/qwen--qwen3-max/): input $0.780, output $3.90 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-max
- [Qwen: Qwen3 Coder Plus](https://llmcost.example.com/model/qwen--qwen3-coder-plus/): input $0.650, output $3.25 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3-coder-plus
- [OpenAI: GPT-5 Codex (batch)](https://llmcost.example.com/model/openai--gpt-5-codex-batch/): input $0.625, output $5.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-codex:batch
- [DeepSeek: DeepSeek V3.1 Terminus](https://llmcost.example.com/model/deepseek--deepseek-v3.1-terminus/): input $0.270, output $1.00 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-v3.1-terminus
- [Qwen: Qwen3 Coder Flash](https://llmcost.example.com/model/qwen--qwen3-coder-flash/): input $0.195, output $0.975 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen3-coder-flash
- [Qwen: Qwen3 Next 80B A3B Thinking](https://llmcost.example.com/model/qwen--qwen3-next-80b-a3b-thinking/): input $0.150, output $1.20 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-next-80b-a3b-thinking
- [Qwen: Qwen3 Next 80B A3B Instruct](https://llmcost.example.com/model/qwen--qwen3-next-80b-a3b-instruct/): input $0.100, output $1.10 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-next-80b-a3b-instruct
- [Qwen: Qwen Plus 0728](https://llmcost.example.com/model/qwen--qwen-plus-2025-07-28/): input $0.260, output $0.780 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen-plus-2025-07-28
- [Qwen: Qwen Plus 0728 (thinking)](https://llmcost.example.com/model/qwen--qwen-plus-2025-07-28-thinking/): input $0.260, output $0.780 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen-plus-2025-07-28:thinking
- [NVIDIA: Nemotron Nano 9B V2 (free)](https://llmcost.example.com/model/nvidia--nemotron-nano-9b-v2-free/): input Free, output Free per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/nvidia/nemotron-nano-9b-v2:free
- [MoonshotAI: Kimi K2 0905](https://llmcost.example.com/model/moonshotai--kimi-k2-0905/): input $0.600, output $2.50 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2-0905
- [Qwen: Qwen3 30B A3B Thinking 2507](https://llmcost.example.com/model/qwen--qwen3-30b-a3b-thinking-2507/): input $0.200, output $2.40 per 1M tokens, context 81920 tokens. Source: https://openrouter.ai/qwen/qwen3-30b-a3b-thinking-2507
- [Nous: Hermes 4 70B](https://llmcost.example.com/model/nousresearch--hermes-4-70b/): input $0.130, output $0.400 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/nousresearch/hermes-4-70b
- [Nous: Hermes 4 405B](https://llmcost.example.com/model/nousresearch--hermes-4-405b/): input $1.00, output $3.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/nousresearch/hermes-4-405b
- [Mistral: Mistral Medium 3.1](https://llmcost.example.com/model/mistralai--mistral-medium-3.1/): input $0.400, output $2.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/mistralai/mistral-medium-3.1
- [Z.ai: GLM 4.5V](https://llmcost.example.com/model/z-ai--glm-4.5v/): input $0.600, output $1.80 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/z-ai/glm-4.5v
- [OpenAI: GPT-5 (batch)](https://llmcost.example.com/model/openai--gpt-5-batch/): input $0.625, output $5.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5:batch
- [OpenAI: GPT-5 Mini (batch)](https://llmcost.example.com/model/openai--gpt-5-mini-batch/): input $0.125, output $1.00 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-mini:batch
- [OpenAI: GPT-5 Nano (batch)](https://llmcost.example.com/model/openai--gpt-5-nano-batch/): input $0.025, output $0.200 per 1M tokens, context 400000 tokens. Source: https://openrouter.ai/openai/gpt-5-nano:batch
- [OpenAI: gpt-oss-120b](https://llmcost.example.com/model/openai--gpt-oss-120b/): input $0.037, output $0.170 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/openai/gpt-oss-120b
- [OpenAI: gpt-oss-20b](https://llmcost.example.com/model/openai--gpt-oss-20b/): input $0.030, output $0.130 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/openai/gpt-oss-20b
- [Anthropic: Claude Opus 4.1 (batch)](https://llmcost.example.com/model/anthropic--claude-opus-4.1-batch/): input $7.50, output $37.50 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4.1:batch
- [Mistral: Codestral 2508](https://llmcost.example.com/model/mistralai--codestral-2508/): input $0.300, output $0.900 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/mistralai/codestral-2508
- [Qwen: Qwen3 Coder 30B A3B Instruct](https://llmcost.example.com/model/qwen--qwen3-coder-30b-a3b-instruct/): input $0.070, output $0.280 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct
- [Qwen: Qwen3 30B A3B Instruct 2507](https://llmcost.example.com/model/qwen--qwen3-30b-a3b-instruct-2507/): input $0.048, output $0.193 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-30b-a3b-instruct-2507
- [Z.ai: GLM 4.5](https://llmcost.example.com/model/z-ai--glm-4.5/): input $0.600, output $2.20 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/z-ai/glm-4.5
- [Z.ai: GLM 4.5 Air](https://llmcost.example.com/model/z-ai--glm-4.5-air/): input $0.130, output $0.850 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/z-ai/glm-4.5-air
- [Qwen: Qwen3 235B A22B Thinking 2507](https://llmcost.example.com/model/qwen--qwen3-235b-a22b-thinking-2507/): input $0.230, output $2.30 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507
- [Qwen: Qwen3 Coder 480B A35B](https://llmcost.example.com/model/qwen--qwen3-coder/): input $0.300, output $1.00 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-coder
- [ByteDance: UI-TARS 7B ](https://llmcost.example.com/model/bytedance--ui-tars-1.5-7b/): input $0.100, output $0.200 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/bytedance/ui-tars-1.5-7b
- [Google: Gemini 2.5 Flash Lite (batch)](https://llmcost.example.com/model/google--gemini-2.5-flash-lite-batch/): input $0.050, output $0.200 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-flash-lite:batch
- [Qwen: Qwen3 235B A22B Instruct 2507](https://llmcost.example.com/model/qwen--qwen3-235b-a22b-2507/): input $0.090, output $0.550 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/qwen/qwen3-235b-a22b-2507
- [MoonshotAI: Kimi K2 0711](https://llmcost.example.com/model/moonshotai--kimi-k2/): input $0.570, output $2.30 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/moonshotai/kimi-k2
- [Venice: Uncensored](https://llmcost.example.com/model/cognitivecomputations--dolphin-mistral-24b-venice-edition/): input $0.200, output $0.900 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition
- [Tencent: Hunyuan A13B Instruct](https://llmcost.example.com/model/tencent--hunyuan-a13b-instruct/): input $0.140, output $0.570 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/tencent/hunyuan-a13b-instruct
- [Morph: Morph V3 Large](https://llmcost.example.com/model/morph--morph-v3-large/): input $0.900, output $1.90 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/morph/morph-v3-large
- [Morph: Morph V3 Fast](https://llmcost.example.com/model/morph--morph-v3-fast/): input $0.800, output $1.20 per 1M tokens, context 81920 tokens. Source: https://openrouter.ai/morph/morph-v3-fast
- [Baidu: ERNIE 4.5 VL 424B A47B ](https://llmcost.example.com/model/baidu--ernie-4.5-vl-424b-a47b/): input $0.420, output $1.25 per 1M tokens, context 123000 tokens. Source: https://openrouter.ai/baidu/ernie-4.5-vl-424b-a47b
- [Mistral: Mistral Small 3.2 24B](https://llmcost.example.com/model/mistralai--mistral-small-3.2-24b-instruct/): input $0.075, output $0.200 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/mistralai/mistral-small-3.2-24b-instruct
- [MiniMax: MiniMax M1](https://llmcost.example.com/model/minimax--minimax-m1/): input $0.550, output $2.20 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/minimax/minimax-m1
- [Google: Gemini 2.5 Flash (batch)](https://llmcost.example.com/model/google--gemini-2.5-flash-batch/): input $0.150, output $1.25 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-flash:batch
- [Google: Gemini 2.5 Pro (batch)](https://llmcost.example.com/model/google--gemini-2.5-pro-batch/): input $0.625, output $5.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-pro:batch
- [OpenAI: o3 Pro](https://llmcost.example.com/model/openai--o3-pro/): input $20.00, output $80.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3-pro
- [OpenAI: o3 Pro (batch)](https://llmcost.example.com/model/openai--o3-pro-batch/): input $10.00, output $40.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3-pro:batch
- [Google: Gemini 2.5 Pro Preview 06-05](https://llmcost.example.com/model/google--gemini-2.5-pro-preview/): input $1.25, output $10.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-pro-preview
- [DeepSeek: R1 0528](https://llmcost.example.com/model/deepseek--deepseek-r1-0528/): input $0.500, output $2.15 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-r1-0528
- [Anthropic: Claude Opus 4](https://llmcost.example.com/model/anthropic--claude-opus-4/): input $15.00, output $75.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-opus-4
- [Anthropic: Claude Sonnet 4](https://llmcost.example.com/model/anthropic--claude-sonnet-4/): input $3.00, output $15.00 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/anthropic/claude-sonnet-4
- [Google: Gemma 3n 4B](https://llmcost.example.com/model/google--gemma-3n-e4b-it/): input $0.060, output $0.120 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/google/gemma-3n-e4b-it
- [Mistral: Mistral Medium 3](https://llmcost.example.com/model/mistralai--mistral-medium-3/): input $0.400, output $2.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/mistralai/mistral-medium-3
- [Google: Gemini 2.5 Pro Preview 05-06](https://llmcost.example.com/model/google--gemini-2.5-pro-preview-05-06/): input $1.25, output $10.00 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/google/gemini-2.5-pro-preview-05-06
- [Arcee AI: Virtuoso Large](https://llmcost.example.com/model/arcee-ai--virtuoso-large/): input $0.750, output $1.20 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/arcee-ai/virtuoso-large
- [Meta: Llama Guard 4 12B](https://llmcost.example.com/model/meta-llama--llama-guard-4-12b/): input $0.180, output $0.180 per 1M tokens, context 1048576 tokens. Source: https://openrouter.ai/meta-llama/llama-guard-4-12b
- [Qwen: Qwen3 30B A3B](https://llmcost.example.com/model/qwen--qwen3-30b-a3b/): input $0.120, output $0.500 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-30b-a3b
- [Qwen: Qwen3 8B](https://llmcost.example.com/model/qwen--qwen3-8b/): input $0.117, output $0.455 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-8b
- [Qwen: Qwen3 14B](https://llmcost.example.com/model/qwen--qwen3-14b/): input $0.120, output $0.240 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-14b
- [Qwen: Qwen3 32B](https://llmcost.example.com/model/qwen--qwen3-32b/): input $0.080, output $0.280 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/qwen/qwen3-32b
- [OpenAI: o4 Mini High](https://llmcost.example.com/model/openai--o4-mini-high/): input $1.10, output $4.40 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o4-mini-high
- [OpenAI: o4 Mini High (batch)](https://llmcost.example.com/model/openai--o4-mini-high-batch/): input $0.550, output $2.20 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o4-mini-high:batch
- [OpenAI: o3 (batch)](https://llmcost.example.com/model/openai--o3-batch/): input $1.00, output $4.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3:batch
- [OpenAI: o4 Mini (batch)](https://llmcost.example.com/model/openai--o4-mini-batch/): input $0.550, output $2.20 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o4-mini:batch
- [OpenAI: GPT-4.1](https://llmcost.example.com/model/openai--gpt-4.1/): input $2.00, output $8.00 per 1M tokens, context 1047576 tokens. Source: https://openrouter.ai/openai/gpt-4.1
- [OpenAI: GPT-4.1 (batch)](https://llmcost.example.com/model/openai--gpt-4.1-batch/): input $1.00, output $4.00 per 1M tokens, context 1047576 tokens. Source: https://openrouter.ai/openai/gpt-4.1:batch
- [OpenAI: GPT-4.1 Mini](https://llmcost.example.com/model/openai--gpt-4.1-mini/): input $0.400, output $1.60 per 1M tokens, context 1047576 tokens. Source: https://openrouter.ai/openai/gpt-4.1-mini
- [OpenAI: GPT-4.1 Mini (batch)](https://llmcost.example.com/model/openai--gpt-4.1-mini-batch/): input $0.200, output $0.800 per 1M tokens, context 1047576 tokens. Source: https://openrouter.ai/openai/gpt-4.1-mini:batch
- [OpenAI: GPT-4.1 Nano](https://llmcost.example.com/model/openai--gpt-4.1-nano/): input $0.100, output $0.400 per 1M tokens, context 1047576 tokens. Source: https://openrouter.ai/openai/gpt-4.1-nano
- [OpenAI: GPT-4.1 Nano (batch)](https://llmcost.example.com/model/openai--gpt-4.1-nano-batch/): input $0.050, output $0.200 per 1M tokens, context 1047576 tokens. Source: https://openrouter.ai/openai/gpt-4.1-nano:batch
- [Meta: Llama 4 Scout](https://llmcost.example.com/model/meta-llama--llama-4-scout/): input $0.100, output $0.300 per 1M tokens, context 1310720 tokens. Source: https://openrouter.ai/meta-llama/llama-4-scout
- [DeepSeek: DeepSeek V3 0324](https://llmcost.example.com/model/deepseek--deepseek-chat-v3-0324/): input $0.250, output $1.00 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-chat-v3-0324
- [OpenAI: o1-pro](https://llmcost.example.com/model/openai--o1-pro/): input $150.00, output $600.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o1-pro
- [OpenAI: o1-pro (batch)](https://llmcost.example.com/model/openai--o1-pro-batch/): input $75.00, output $300.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o1-pro:batch
- [Mistral: Mistral Small 3.1 24B](https://llmcost.example.com/model/mistralai--mistral-small-3.1-24b-instruct/): input $0.351, output $0.555 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/mistralai/mistral-small-3.1-24b-instruct
- [Google: Gemma 3 4B](https://llmcost.example.com/model/google--gemma-3-4b-it/): input $0.050, output $0.100 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/google/gemma-3-4b-it
- [Google: Gemma 3 12B](https://llmcost.example.com/model/google--gemma-3-12b-it/): input $0.050, output $0.150 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/google/gemma-3-12b-it
- [Cohere: Command A](https://llmcost.example.com/model/cohere--command-a/): input $2.50, output $10.00 per 1M tokens, context 256000 tokens. Source: https://openrouter.ai/cohere/command-a
- [Reka Flash 3](https://llmcost.example.com/model/rekaai--reka-flash-3/): input $0.100, output $0.200 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/rekaai/reka-flash-3
- [Google: Gemma 3 27B](https://llmcost.example.com/model/google--gemma-3-27b-it/): input $0.080, output $0.450 per 1M tokens, context 262144 tokens. Source: https://openrouter.ai/google/gemma-3-27b-it
- [TheDrummer: Skyfall 36B V2](https://llmcost.example.com/model/thedrummer--skyfall-36b-v2/): input $0.550, output $0.800 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/thedrummer/skyfall-36b-v2
- [Perplexity: Sonar Reasoning Pro](https://llmcost.example.com/model/perplexity--sonar-reasoning-pro/): input $2.00, output $8.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/perplexity/sonar-reasoning-pro
- [Perplexity: Sonar Pro](https://llmcost.example.com/model/perplexity--sonar-pro/): input $3.00, output $15.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/perplexity/sonar-pro
- [Perplexity: Sonar Deep Research](https://llmcost.example.com/model/perplexity--sonar-deep-research/): input $2.00, output $8.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/perplexity/sonar-deep-research
- [Mistral: Saba](https://llmcost.example.com/model/mistralai--mistral-saba/): input $0.200, output $0.600 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/mistralai/mistral-saba
- [OpenAI: o3 Mini High](https://llmcost.example.com/model/openai--o3-mini-high/): input $1.10, output $4.40 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3-mini-high
- [OpenAI: o3 Mini High (batch)](https://llmcost.example.com/model/openai--o3-mini-high-batch/): input $0.550, output $2.20 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3-mini-high:batch
- [AionLabs: Aion-RP 1.0 (8B)](https://llmcost.example.com/model/aion-labs--aion-rp-llama-3.1-8b/): input $0.800, output $1.60 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/aion-labs/aion-rp-llama-3.1-8b
- [Qwen: Qwen2.5 VL 72B Instruct](https://llmcost.example.com/model/qwen--qwen2.5-vl-72b-instruct/): input $0.800, output $1.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/qwen/qwen2.5-vl-72b-instruct
- [Qwen: Qwen-Plus](https://llmcost.example.com/model/qwen--qwen-plus/): input $0.260, output $0.780 per 1M tokens, context 1000000 tokens. Source: https://openrouter.ai/qwen/qwen-plus
- [OpenAI: o3 Mini](https://llmcost.example.com/model/openai--o3-mini/): input $1.10, output $4.40 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3-mini
- [OpenAI: o3 Mini (batch)](https://llmcost.example.com/model/openai--o3-mini-batch/): input $0.550, output $2.20 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o3-mini:batch
- [Mistral: Mistral Small 3](https://llmcost.example.com/model/mistralai--mistral-small-24b-instruct-2501/): input $0.050, output $0.080 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/mistralai/mistral-small-24b-instruct-2501
- [Perplexity: Sonar](https://llmcost.example.com/model/perplexity--sonar/): input $1.00, output $1.00 per 1M tokens, context 127072 tokens. Source: https://openrouter.ai/perplexity/sonar
- [DeepSeek: R1 Distill Llama 70B](https://llmcost.example.com/model/deepseek--deepseek-r1-distill-llama-70b/): input $0.800, output $0.800 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b
- [MiniMax: MiniMax-01](https://llmcost.example.com/model/minimax--minimax-01/): input $0.200, output $1.10 per 1M tokens, context 1000192 tokens. Source: https://openrouter.ai/minimax/minimax-01
- [Microsoft: Phi 4](https://llmcost.example.com/model/microsoft--phi-4/): input $0.070, output $0.140 per 1M tokens, context 16384 tokens. Source: https://openrouter.ai/microsoft/phi-4
- [DeepSeek: DeepSeek V3](https://llmcost.example.com/model/deepseek--deepseek-chat/): input $0.257, output $1.03 per 1M tokens, context 163840 tokens. Source: https://openrouter.ai/deepseek/deepseek-chat
- [Sao10K: Llama 3.3 Euryale 70B](https://llmcost.example.com/model/sao10k--l3.3-euryale-70b/): input $0.650, output $0.750 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/sao10k/l3.3-euryale-70b
- [OpenAI: o1](https://llmcost.example.com/model/openai--o1/): input $15.00, output $60.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o1
- [OpenAI: o1 (batch)](https://llmcost.example.com/model/openai--o1-batch/): input $7.50, output $30.00 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/openai/o1:batch
- [Cohere: Command R7B (12-2024)](https://llmcost.example.com/model/cohere--command-r7b-12-2024/): input $0.037, output $0.150 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/cohere/command-r7b-12-2024
- [Meta: Llama 3.3 70B Instruct](https://llmcost.example.com/model/meta-llama--llama-3.3-70b-instruct/): input $0.100, output $0.320 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/meta-llama/llama-3.3-70b-instruct
- [Amazon: Nova Lite 1.0](https://llmcost.example.com/model/amazon--nova-lite-v1/): input $0.060, output $0.240 per 1M tokens, context 300000 tokens. Source: https://openrouter.ai/amazon/nova-lite-v1
- [Amazon: Nova Micro 1.0](https://llmcost.example.com/model/amazon--nova-micro-v1/): input $0.035, output $0.140 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/amazon/nova-micro-v1
- [OpenAI: GPT-4o (2024-11-20)](https://llmcost.example.com/model/openai--gpt-4o-2024-11-20/): input $2.50, output $10.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o-2024-11-20
- [Mistral Large 2407](https://llmcost.example.com/model/mistralai--mistral-large-2407/): input $2.00, output $6.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/mistralai/mistral-large-2407
- [Qwen2.5 Coder 32B Instruct](https://llmcost.example.com/model/qwen--qwen-2.5-coder-32b-instruct/): input $0.660, output $1.00 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/qwen/qwen-2.5-coder-32b-instruct
- [TheDrummer: UnslopNemo 12B](https://llmcost.example.com/model/thedrummer--unslopnemo-12b/): input $0.400, output $0.400 per 1M tokens, context 1024000 tokens. Source: https://openrouter.ai/thedrummer/unslopnemo-12b
- [Magnum v4 72B](https://llmcost.example.com/model/anthracite-org--magnum-v4-72b/): input $3.00, output $5.00 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/anthracite-org/magnum-v4-72b
- [Mistral: Ministral 8B](https://llmcost.example.com/model/mistralai--ministral-8b/): input $0.110, output $0.110 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/mistralai/ministral-8b
- [Qwen: Qwen2.5 7B Instruct](https://llmcost.example.com/model/qwen--qwen-2.5-7b-instruct/): input $0.100, output $0.200 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/qwen/qwen-2.5-7b-instruct
- [TheDrummer: Rocinante 12B](https://llmcost.example.com/model/thedrummer--rocinante-12b/): input $0.250, output $0.500 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/thedrummer/rocinante-12b
- [Meta: Llama 3.2 1B Instruct](https://llmcost.example.com/model/meta-llama--llama-3.2-1b-instruct/): input $0.027, output $0.201 per 1M tokens, context 60000 tokens. Source: https://openrouter.ai/meta-llama/llama-3.2-1b-instruct
- [Meta: Llama 3.2 3B Instruct](https://llmcost.example.com/model/meta-llama--llama-3.2-3b-instruct/): input $0.050, output $0.330 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/meta-llama/llama-3.2-3b-instruct
- [Qwen2.5 72B Instruct](https://llmcost.example.com/model/qwen--qwen-2.5-72b-instruct/): input $0.360, output $0.400 per 1M tokens, context 32768 tokens. Source: https://openrouter.ai/qwen/qwen-2.5-72b-instruct
- [Cohere: Command R (08-2024)](https://llmcost.example.com/model/cohere--command-r-08-2024/): input $0.150, output $0.600 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/cohere/command-r-08-2024
- [Cohere: Command R+ (08-2024)](https://llmcost.example.com/model/cohere--command-r-plus-08-2024/): input $2.50, output $10.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/cohere/command-r-plus-08-2024
- [Sao10K: Llama 3.1 Euryale 70B v2.2](https://llmcost.example.com/model/sao10k--l3.1-euryale-70b/): input $0.850, output $0.850 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/sao10k/l3.1-euryale-70b
- [Nous: Hermes 3 70B Instruct](https://llmcost.example.com/model/nousresearch--hermes-3-llama-3.1-70b/): input $0.700, output $0.700 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/nousresearch/hermes-3-llama-3.1-70b
- [Nous: Hermes 3 405B Instruct](https://llmcost.example.com/model/nousresearch--hermes-3-llama-3.1-405b/): input $1.00, output $1.00 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/nousresearch/hermes-3-llama-3.1-405b
- [Sao10K: Llama 3 8B Lunaris](https://llmcost.example.com/model/sao10k--l3-lunaris-8b/): input $0.040, output $0.050 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/sao10k/l3-lunaris-8b
- [OpenAI: GPT-4o (2024-08-06)](https://llmcost.example.com/model/openai--gpt-4o-2024-08-06/): input $2.50, output $10.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o-2024-08-06
- [Meta: Llama 3.1 70B Instruct](https://llmcost.example.com/model/meta-llama--llama-3.1-70b-instruct/): input $0.400, output $0.400 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/meta-llama/llama-3.1-70b-instruct
- [Meta: Llama 3.1 8B Instruct](https://llmcost.example.com/model/meta-llama--llama-3.1-8b-instruct/): input $0.050, output $0.080 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/meta-llama/llama-3.1-8b-instruct
- [Mistral: Mistral Nemo](https://llmcost.example.com/model/mistralai--mistral-nemo/): input $0.019, output $0.030 per 1M tokens, context 131072 tokens. Source: https://openrouter.ai/mistralai/mistral-nemo
- [OpenAI: GPT-4o-mini](https://llmcost.example.com/model/openai--gpt-4o-mini/): input $0.150, output $0.600 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o-mini
- [OpenAI: GPT-4o-mini (2024-07-18)](https://llmcost.example.com/model/openai--gpt-4o-mini-2024-07-18/): input $0.150, output $0.600 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o-mini-2024-07-18
- [OpenAI: GPT-4o-mini (batch)](https://llmcost.example.com/model/openai--gpt-4o-mini-batch/): input $0.075, output $0.300 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o-mini:batch
- [Google: Gemma 2 27B](https://llmcost.example.com/model/google--gemma-2-27b-it/): input $0.650, output $0.650 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/google/gemma-2-27b-it
- [OpenAI: GPT-4o](https://llmcost.example.com/model/openai--gpt-4o/): input $2.50, output $10.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o
- [OpenAI: GPT-4o (2024-05-13)](https://llmcost.example.com/model/openai--gpt-4o-2024-05-13/): input $5.00, output $15.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o-2024-05-13
- [OpenAI: GPT-4o (batch)](https://llmcost.example.com/model/openai--gpt-4o-batch/): input $1.25, output $5.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4o:batch
- [Mistral: Mixtral 8x22B Instruct](https://llmcost.example.com/model/mistralai--mixtral-8x22b-instruct/): input $2.00, output $6.00 per 1M tokens, context 65536 tokens. Source: https://openrouter.ai/mistralai/mixtral-8x22b-instruct
- [WizardLM-2 8x22B](https://llmcost.example.com/model/microsoft--wizardlm-2-8x22b/): input $0.620, output $0.620 per 1M tokens, context 65535 tokens. Source: https://openrouter.ai/microsoft/wizardlm-2-8x22b
- [OpenAI: GPT-4 Turbo](https://llmcost.example.com/model/openai--gpt-4-turbo/): input $10.00, output $30.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4-turbo
- [OpenAI: GPT-4 Turbo (batch)](https://llmcost.example.com/model/openai--gpt-4-turbo-batch/): input $5.00, output $15.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4-turbo:batch
- [Anthropic: Claude 3 Haiku](https://llmcost.example.com/model/anthropic--claude-3-haiku/): input $0.250, output $1.25 per 1M tokens, context 200000 tokens. Source: https://openrouter.ai/anthropic/claude-3-haiku
- [Mistral Large](https://llmcost.example.com/model/mistralai--mistral-large/): input $2.00, output $6.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/mistralai/mistral-large
- [OpenAI: GPT-3.5 Turbo (older v0613)](https://llmcost.example.com/model/openai--gpt-3.5-turbo-0613/): input $1.00, output $2.00 per 1M tokens, context 4095 tokens. Source: https://openrouter.ai/openai/gpt-3.5-turbo-0613
- [OpenAI: GPT-4 Turbo Preview](https://llmcost.example.com/model/openai--gpt-4-turbo-preview/): input $10.00, output $30.00 per 1M tokens, context 128000 tokens. Source: https://openrouter.ai/openai/gpt-4-turbo-preview
- [OpenAI: GPT-3.5 Turbo Instruct](https://llmcost.example.com/model/openai--gpt-3.5-turbo-instruct/): input $1.50, output $2.00 per 1M tokens, context 4095 tokens. Source: https://openrouter.ai/openai/gpt-3.5-turbo-instruct
- [OpenAI: GPT-3.5 Turbo 16k](https://llmcost.example.com/model/openai--gpt-3.5-turbo-16k/): input $3.00, output $4.00 per 1M tokens, context 16385 tokens. Source: https://openrouter.ai/openai/gpt-3.5-turbo-16k
- [Mancer: Weaver (alpha)](https://llmcost.example.com/model/mancer--weaver/): input $0.500, output $0.750 per 1M tokens, context 8000 tokens. Source: https://openrouter.ai/mancer/weaver
- [ReMM SLERP 13B](https://llmcost.example.com/model/undi95--remm-slerp-l2-13b/): input $0.450, output $0.650 per 1M tokens, context 6144 tokens. Source: https://openrouter.ai/undi95/remm-slerp-l2-13b
- [MythoMax 13B](https://llmcost.example.com/model/gryphe--mythomax-l2-13b/): input $0.060, output $0.060 per 1M tokens, context 8192 tokens. Source: https://openrouter.ai/gryphe/mythomax-l2-13b
- [OpenAI: GPT-3.5 Turbo](https://llmcost.example.com/model/openai--gpt-3.5-turbo/): input $0.500, output $1.50 per 1M tokens, context 16385 tokens. Source: https://openrouter.ai/openai/gpt-3.5-turbo
- [OpenAI: GPT-3.5 Turbo (batch)](https://llmcost.example.com/model/openai--gpt-3.5-turbo-batch/): input $0.250, output $0.750 per 1M tokens, context 16385 tokens. Source: https://openrouter.ai/openai/gpt-3.5-turbo:batch
- [OpenAI: GPT-4](https://llmcost.example.com/model/openai--gpt-4/): input $30.00, output $60.00 per 1M tokens, context 8191 tokens. Source: https://openrouter.ai/openai/gpt-4

## JSON API

Full machine-readable dataset: https://llmcost.example.com/api/models.json