LLM Gateway serves 138 of the models we track. We do not support bring-your-own-key for this provider yet.
| Model | Made by | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| Llama 3.2 3B Instruct | NVIDIA | $0.03 | $0.05 | 33K |
| GPT-OSS 120B | OpenAI | $0.032 | $0.14 | 131K |
| GPT-OSS 20B | OpenAI | $0.04 | $0.19 | 66K |
| GPT-5 Nano | OpenAI | $0.05 | $0.4 | 400K |
| Qwen Flash | Alibaba | $0.05 | $0.4 | 1.0M |
| GLM-4.7-Flash | Zhipu AI | $0.06 | $0.4 | 200K |
| Qwen3-Coder 30B-A3B Instruct | Alibaba | $0.07 | $0.27 | 160K |
| GLM-4.7-FlashX | Zhipu AI | $0.07 | $0.4 | 200K |
| Gemma 4 26B A4B IT | $0.07 | $0.34 | 262K | |
| DeepSeek V4 Flash | DeepSeek | $0.076 | $0.153 | 1.0M |
| Ministral 3B (latest) | Mistral | $0.1 | $0.1 | 131K |
| Muse Spark 1.2 Contributor | Meta | $0.1 | $0.2 | 1.0M |
| Mistral Small 3.2 | Mistral | $0.1 | $0.3 | 128K |
| Gemini 2.5 Flash Lite | $0.1 | $0.4 | 1.0M | |
| GPT-4.1 Nano | OpenAI | $0.1 | $0.4 | 1.0M |
| Muse Spark 1.3 Contributor | Meta | $0.1 | $0.2 | 1.0M |
| Gemma 4 31B IT | $0.102 | $0.297 | 262K | |
| Qwen3 Coder Next | Amazon Bedrock | $0.108 | $0.675 | 262K |
| GPT-4o Mini | OpenAI | $0.15 | $0.6 | 128K |
| Ministral 8B (latest) | Mistral | $0.15 | $0.15 | 262K |
| Qwen3.8 Flash | Alibaba | $0.15 | $0.47 | 1.0M |
| GLM-5.3-Flash | Zhipu AI | $0.15 | $0.5 | 1.0M |
| Qwen3-Next 80B-A3B Instruct | Alibaba | $0.15 | $1.5 | 131K |
| Llama 4 Scout 17B Instruct (US) | Amazon Bedrock | $0.18 | $0.59 | 131K |
| GPT-5.4 nano | OpenAI | $0.2 | $1.25 | 400K |
| Qwen3-VL Plus | Alibaba | $0.2 | $1.6 | 262K |
| Qwen3 VL 235B A22B Instruct | Amazon Bedrock | $0.2 | $0.88 | 262K |
| GLM-4.5-Air | Zhipu AI | $0.2 | $1.1 | 128K |
| MiniMax-M2 | MiniMax | $0.2 | $1 | 197K |
| Qwen-Omni Turbo | Alibaba | $0.2 | $0.8 | 33K |
| GPT-5.6 Luna | OpenAI | $0.2 | $1.2 | 1.1M |
| DeepSeek V4.1 Flash | DeepSeek | $0.22 | $0.66 | 1.0M |
| Qwen3.6 35B-A3B | Alibaba | $0.248 | $1.485 | 262K |
| GPT-5.1 Codex Mini | OpenAI | $0.25 | $2 | 400K |
| Qwen3.6 Flash | Alibaba | $0.25 | $1.5 | 1.0M |
| GPT-5 Mini | OpenAI | $0.25 | $2 | 400K |
| Gemini 3.1 Flash Lite | $0.25 | $1.5 | 1.0M | |
| DeepSeek V3.2 | DeepSeek | $0.26 | $0.38 | 160K |
| Llama 4 Maverick 17B Instruct (US) | Amazon Bedrock | $0.27 | $0.85 | 1.0M |
| Codestral | Mistral | $0.3 | $0.9 | 256K |
| MiniMax-M2.7 | MiniMax | $0.3 | $1.2 | 200K |
| Gemini 2.5 Flash | $0.3 | $2.5 | 1.0M | |
| MiniMax-M3 | MiniMax | $0.3 | $1.2 | 1.0M |
| MiniMax-M2.1 | MiniMax | $0.3 | $1.2 | 205K |
| Gemini 3.5 Flash Lite | $0.3 | $2.5 | 1.0M | |
| GLM-4.6V | Zhipu AI | $0.3 | $0.9 | 128K |
| MiniMax M2.5 | MiniMax | $0.3 | $1.2 | 205K |
| Qwen3 Coder Flash | Alibaba | $0.3 | $1.5 | 1.0M |
| Qwen3-Coder 480B-A35B Instruct | Alibaba | $0.38 | $1.55 | 262K |
| GPT-4.1 Mini | OpenAI | $0.4 | $1.6 | 1.0M |
| Qwen Plus | Alibaba | $0.4 | $1.2 | 1.0M |
| Devstral 2 | Mistral | $0.4 | $2 | 262K |
| Qwen3.7 Plus | Alibaba | $0.4 | $1.6 | 1.0M |
| Qwen3.6 Plus | Alibaba | $0.5 | $3 | 1.0M |
| GPT-3.5-turbo | OpenAI | $0.5 | $1.5 | 16K |
| Gemini 3 Flash | $0.5 | $3 | 1.0M | |
| Mistral Large 3 | Mistral | $0.5 | $1.5 | 262K |
| Qwen3.5 397B-A17B | Alibaba | $0.6 | $3.6 | 262K |
| Qwen3 235B-A22B Instruct 2507 | Amazon Bedrock | $0.6 | $1.2 | 262K |
| Kimi K2.5 | Moonshot AI | $0.6 | $3 | 262K |
| Kimi K2 Thinking | Vertex | $0.6 | $2.5 | 262K |
| MiniMax-M2.5-highspeed | MiniMax | $0.6 | $2.4 | 205K |
| MiniMax-M2.7-highspeed | MiniMax | $0.6 | $2.4 | 205K |
| Kimi K2.6 | Moonshot AI | $0.6 | $3.05 | 262K |
| GLM-4.6 | Zhipu AI | $0.6 | $2.2 | 200K |
| GLM-4.5 | Zhipu AI | $0.6 | $2.2 | 128K |
| GLM-4.5V | Zhipu AI | $0.6 | $1.8 | 128K |
| Llama 3.1 70b Instruct | NVIDIA | $0.72 | $0.72 | 128K |
| Gemini 3.7 Flash | $0.75 | $3.75 | 1.0M | |
| Gemini 3.8 Flash | $0.75 | $3.75 | 1.0M | |
| Gemini 3.6 Flash | $0.75 | $3.75 | 1.0M | |
| GPT-5.4 mini | OpenAI | $0.75 | $4.5 | 400K |
| GLM-5.2 | Mistral | $0.8 | $2.55 | 1.0M |
| Llama 3.3 70b Instruct | NVIDIA | $0.85 | $1.2 | 128K |
| Kimi K2.7 Code | Moonshot AI | $0.95 | $4 | 262K |
| DeepSeek V4 Pro | DeepSeek | $0.961 | $1.922 | 1.0M |
| Qwen3 Coder Plus | Alibaba | $1 | $5 | 1.0M |
| Claude Haiku 4.5 | Anthropic | $1 | $5 | 200K |
| Sonar | Perplexity | $1 | $1 | 130K |
| GLM-5 | Zhipu AI | $1 | $3.2 | 203K |
| Grok Build 0.1 | xAI | $1 | $2 | 256K |
| o3 Mini | OpenAI | $1.1 | $4.4 | 200K |
| o4 Mini | OpenAI | $1.1 | $4.4 | 200K |
| GLM-5.3 | Zhipu AI | $1.2 | $4 | 1.0M |
| GLM-5V-Turbo | Zhipu AI | $1.2 | $4 | 200K |
| Grok 4.3 | xAI | $1.25 | $2.5 | 1.0M |
| Qwen3.7 Max | Alibaba | $1.25 | $3.75 | 1.0M |
| Muse Spark 1.2 | Meta | $1.25 | $4.25 | 1.0M |
| Muse Spark 1.1 | Meta | $1.25 | $4.25 | 1.0M |
| GPT-5 | OpenAI | $1.25 | $10 | 400K |
| Gemini 2.5 Pro | $1.25 | $10 | 1.0M | |
| Muse Spark 1.3 | Meta | $1.25 | $4.25 | 1.0M |
| GPT-5.1 | OpenAI | $1.25 | $10 | 400K |
| GPT-5.1 Codex | OpenAI | $1.25 | $10 | 400K |
| Qwen3.6 Max Preview | Alibaba | $1.3 | $7.8 | 262K |
| GLM-5.1 | Zhipu AI | $1.4 | $4.4 | 200K |
| Gemini 3.5 Flash | $1.5 | $9 | 1.0M | |
| Qwen Max | Alibaba | $1.6 | $6.4 | 33K |
| GPT-5.2 Codex | Azure | $1.75 | $14 | 400K |
| GPT-5.3 Codex | OpenAI | $1.75 | $14 | 400K |
| GPT-5.2 | OpenAI | $1.75 | $14 | 400K |
| Kimi K2.7 Code HighSpeed | Moonshot AI | $1.9 | $8 | 262K |
| Claude Sonnet 5 | Anthropic | $2 | $10 | 1.0M |
| Gemini 3.1 Pro | $2 | $12 | 1.0M | |
| Grok 4.6 | xAI | $2 | $6 | 500K |
| Grok 4.5 | xAI | $2 | $6 | 500K |
| o3 | OpenAI | $2 | $8 | 200K |
| Sonar Reasoning Pro | Perplexity | $2 | $8 | 128K |
| GPT-4.1 | OpenAI | $2 | $8 | 1.0M |
| GPT-5.6 Terra | OpenAI | $2 | $12 | 1.1M |
| Qwen3.8 Max | Alibaba | $2 | $6 | 1.0M |
| GLM-4.7 | Zhipu AI | $2.25 | $2.75 | 200K |
| GPT-4o | OpenAI | $2.5 | $10 | 128K |
| GPT-5.4 | OpenAI | $2.5 | $15 | 1.1M |
| Claude Sonnet 4.6 | Anthropic | $3 | $15 | 1.0M |
| Grok 4 | xAI | $3 | $15 | 256K |
| Sonar Pro | Perplexity | $3 | $15 | 200K |
| Kimi K3 | Moonshot AI | $3 | $15 | 1.0M |
| Claude Sonnet 4.5 | Anthropic | $3 | $15 | 200K |
| Mistral Large (latest) | Mistral | $4 | $12 | 128K |
| Claude Opus 4.6 | Anthropic | $5 | $25 | 1.0M |
| Claude Opus 5 | Anthropic | $5 | $25 | 1.0M |
| GPT-5.5 | OpenAI | $5 | $30 | 1.1M |
| GPT-5.6 Sol | OpenAI | $5 | $30 | 1.1M |
| Claude Opus 4.8 | Anthropic | $5 | $25 | 1.0M |
| Claude Opus 4.5 | Anthropic | $5 | $25 | 200K |
| Claude Opus 4.7 | Anthropic | $5 | $25 | 1.0M |
| Claude Fable 5.1 | Anthropic | $10 | $50 | 1.0M |
| GPT-6 Astra | OpenAI | $10 | $50 | 1.1M |
| Claude Fable 5 | Anthropic | $10 | $50 | 1.0M |
| GPT-4 Turbo | OpenAI | $10 | $30 | 128K |
| Claude Opus 4.1 | Vertex | $15 | $75 | 200K |
| o1 | OpenAI | $15 | $60 | 200K |
| GPT-5 Pro | OpenAI | $15 | $120 | 400K |
| GPT-5.2 Pro | OpenAI | $21 | $168 | 400K |
| GPT-5.4 Pro | OpenAI | $30 | $180 | 1.1M |
| GPT-5.5 Pro | OpenAI | $30 | $180 | 1.1M |
| GPT-4 | OpenAI | $30 | $60 | 8K |
LLM Gateway serves 138 of the models we track, across 1 model type.
Llama 3.2 3B Instruct at $0.03 per million input tokens.
Not yet — LLM Gateway is not currently one of the providers Serenities supports for bring-your-own-key.
