Merge Gateway is a third-party gateway that routes to many upstream models through one API. Gateway quotes are often among the lowest on the site, but availability, rate limits and routing can vary between models, so a low headline price is worth verifying against your own workload.
It lists 195 models on this page. 194 of them have a public price. 1 is offered at $0. Coverage spans text and chat (189), image generation (3), classification and safety (2), and embeddings (1). The lowest-priced model hosted here is DeepSeek V4 Flash.
Merge Gateway is the lowest paid channel for 20 models that have at least two competing paid hosts, which is where its pricing genuinely leads rather than being the only option.
| Cheapest here? | |||||
|---|---|---|---|---|---|
| Nemotron 3.5 Lightning 30B A3Bnvidia/nemotron-3.5-lightning-30b-a3b | Free | — | 1,000,000 | — | |
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | $0.035 | $0.07 | $0.007 | 1,048,576 | Lowest anywhere |
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | $0.035 | $0.07 | $0.007 | 1,048,576 | Lowest anywhere |
| Gemma 3 4B ITgoogle/gemma-3-4b-it | $0.04 | $0.08 | — | 128,000 | 1.0× pricier |
| Command R7Bcohere/command-r7b-12-2024 | $0.038 | $0.15 | — | 128,000 | 1.0× pricier |
| GPT OSS 20Bopenai/gpt-oss-20b | $0.04 | $0.15 | $0.02 | 128,000 | 1.9× pricier |
| Qwen Flashqwen/qwen-flash | $0.022 | $0.22 | $0.0044 | 1,000,000 | Lowest anywhere |
| Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b | $0.05 | $0.20 | — | 256,000 | 1.0× pricier |
| Qwen3.5 Flashqwen/qwen3.5-flash | $0.029 | $0.29 | $0.0058 | 1,000,000 | 1.0× pricier |
| GPT OSS 120Bopenai/gpt-oss-120b | $0.05 | $0.25 | — | 128,000 | 1.7× pricier |
| Qwen3.5 9Bqwen/qwen3.5-9b | $0.09 | $0.13 | — | 262,144 | 1.5× pricier |
| GPT OSS Safeguard 20BClassify / Safetyopenai/gpt-oss-safeguard-20b | $0.07 | $0.20 | $0 | 4,096 | 1.0× pricier |
| Nvidia Nemotron Nano 9B V2nvidia/nemotron-nano-9b-v2 | $0.06 | $0.23 | — | 128,000 | 1.0× pricier |
| Gemini Embedding 001Embeddinggoogle/gemini-embedding-001 | $0.15 | $0 | — | 2,048 | 1.0× pricier |
| GLM-5.3-Flashzai/glm-5.3-flash | $0.075 | $0.25 | $0.015 | 1,000,000 | 2.5× pricier |
| GPT-5 Nanoopenai/gpt-5-nano | $0.05 | $0.40 | $0.005 | 400,000 | 1.3× pricier |
| Gemma 3 12B ITgoogle/gemma-3-12b-it | $0.09 | $0.29 | — | 128,000 | 2.2× pricier |
| Devstral Smallmistral/devstral-small-2507 | $0.10 | $0.30 | — | 128,000 | Lowest anywhere |
| GLM-4.7-Flashzai/glm-4.7-flash | $0.07 | $0.40 | — | 200,000 | 1.1× pricier |
| GLM-4.7-FlashXzai/glm-4.7-flashx | $0.07 | $0.40 | $0.01 | 200,000 | 1.1× pricier |
| Qwen3.5 35B-A3Bqwen/qwen3.5-35b-a3b | $0.057 | $0.46 | $0.02 | 131,072 | 1.0× pricier |
| Qwen Plusqwen/qwen-plus | $0.12 | $0.29 | $0.023 | 1,000,000 | Lowest anywhere |
| Gemma 3 27B ITgoogle/gemma-3-27b-it | $0.08 | $0.45 | $0.04 | 131,072 | 1.7× pricier |
| DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash-0423 | $0.14 | $0.28 | — | 131,072 | 1.0× pricier |
| Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite | $0.10 | $0.40 | $0.01 | 1,000,000 | 1.8× pricier |
| GPT-4.1 nanoopenai/gpt-4.1-nano | $0.10 | $0.40 | $0.025 | 1,047,576 | 1.4× pricier |
| Seed 2.0 Minibytedance/dola-seed-2.0-mini | $0.10 | $0.40 | — | 131,072 | 1.8× pricier |
| Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it | $0.13 | $0.40 | — | 262,144 | 2.3× pricier |
| GPT-6 Lunaopenai/gpt-6-luna | $0.10 | $0.50 | $0.01 | 1,050,000 | 1.3× pricier |
| Gemma 4 31B ITgoogle/gemma-4-31b-it | $0.14 | $0.40 | — | 262,144 | 1.5× pricier |
| Llama 3.1 8Bmeta/llama-3.1-8b-instruct | $0.22 | $0.22 | — | 128,000 | 3.8× pricier |
| Qwen3 235B-A22B Instruct 2507qwen/qwen3-235b-a22b-instruct-2507 | $0.10 | $0.60 | $0.057 | 131,072 | 1.5× pricier |
| Qwen3.8 Flashqwen/qwen3.8-flash | $0.15 | $0.47 | $0.016 | 977,000 | 1.3× pricier |
| Qwen3.5 27Bqwen/qwen3.5-27b | $0.086 | $0.69 | $0.017 | 131,072 | 1.0× pricier |
| Qwen3-Next 80B-A3B Instructqwen/qwen3-next-80b-a3b-instruct | $0.14 | $0.57 | $0.029 | 131,072 | Lowest anywhere |
| Qwen3 Coder Flashqwen/qwen3-coder-flash | $0.14 | $0.57 | $0.029 | 1,000,000 | Lowest anywhere |
| Qwen3.5 Plusqwen/qwen3.5-plus | $0.12 | $0.69 | $0.023 | 1,000,000 | 1.0× pricier |
| DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | $0.15 | $0.60 | $0.003 | 1,000,000 | 5.2× pricier |
| GPT-4o miniopenai/gpt-4o-mini | $0.15 | $0.60 | $0.075 | 128,000 | 2.0× pricier |
| Qwen3 32Bqwen/qwen3-32b | $0.15 | $0.60 | — | 131,072 | 2.0× pricier |
| Command Rcohere/command-r-08-2024 | $0.15 | $0.60 | — | 128,000 | 1.0× pricier |
| GPT OSS Safeguard 120BClassify / Safetyopenai/gpt-oss-safeguard-120b | $0.15 | $0.60 | — | 4,096 | 1.0× pricier |
| Mistral Small (latest)mistral/mistral-small-latest | $0.15 | $0.60 | — | 256,000 | 1.0× pricier |
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | $0.22 | $0.50 | $0.11 | 131,072 | 3.1× pricier |
| DeepSeek V3.2deepseek/deepseek-v3.2 | $0.28 | $0.40 | $0.13 | 128,000 | 1.4× pricier |
| Qwen3 Coder Nextqwen/qwen3-coder-next | $0.15 | $0.80 | $0.075 | 262,144 | 1.3× pricier |
| Qwen3.5 122B-A10Bqwen/qwen3.5-122b-a10b | $0.12 | $0.92 | $0.023 | 131,072 | 1.0× pricier |
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731-fast | $0.28 | $0.56 | $0.07 | 1,000,000 | Lowest anywhere |
| Qwen3 30B A3Bqwen/qwen3-30b-a3b | $0.11 | $1.08 | $0.022 | 131,072 | 2.6× pricier |
| Qwen3.6 Flashqwen/qwen3.6-flash | $0.17 | $0.99 | $0.033 | 1,000,000 | Lowest anywhere |
| Qwen3.5 397B-A17Bqwen/qwen3.5-397b-a17b | $0.17 | $1.03 | $0.034 | 131,072 | 1.0× pricier |
| Qwen3-Next 80B-A3B (Thinking)qwen/qwen3-next-80b-a3b-thinking | $0.15 | $1.20 | — | 131,072 | 1.5× pricier |
| GLM-4.5-Airzai/glm-4.5-air | $0.20 | $1.10 | $0.03 | 128,000 | 2.7× pricier |
| Codestral (latest)mistral/codestral-latest | $0.30 | $0.90 | — | 256,000 | 1.0× pricier |
| GPT-5.6 Lunaopenai/gpt-5.6-luna | $0.20 | $1.20 | $0.02 | 1,050,000 | 3.3× pricier |
| GPT-5.4 nanoopenai/gpt-5.4-nano | $0.20 | $1.25 | $0.02 | 400,000 | 1.3× pricier |
| Qwen3-VL Plusqwen/qwen3-vl-plus | $0.14 | $1.43 | $0.029 | 262,144 | 1.0× pricier |
| DeepSeek-V3deepseek/deepseek-v3 | $0.27 | $1.10 | — | 163,840 | 1.1× pricier |
| Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct | $0.29 | $1.15 | $0.16 | 131,072 | 1.4× pricier |
| Qwen3 235B-A22Bqwen/qwen3-235b-a22b | $0.29 | $1.15 | $0.057 | 131,072 | 1.4× pricier |
| MiniMax-M3minimax/minimax-m3 | $0.30 | $1.20 | $0.06 | 1,000,000 | 1.4× pricier |
| MiniMax-M2.7minimax/minimax-m2.7 | $0.30 | $1.20 | $0.06 | 204,800 | 3.7× pricier |
| MiniMax-M2.5minimax/minimax-m2.5 | $0.30 | $1.20 | $0.03 | 204,800 | 1.4× pricier |
| MiniMax-M2.1minimax/minimax-m2.1 | $0.30 | $1.20 | $0.03 | 204,800 | 1.1× pricier |
| MiniMax-M2minimax/minimax-m2 | $0.30 | $1.20 | $0.03 | 204,800 | 1.3× pricier |
| Qwen3.6 35B-A3Bqwen/qwen3.6-35b-a3b | $0.25 | $1.49 | $0.05 | 262,144 | 5.1× pricier |
| Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite | $0.25 | $1.50 | $0.025 | 1,048,576 | 2.0× pricier |
| Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview | $0.25 | $1.50 | $0.025 | 1,048,576 | 2.0× pricier |
| Gemini Flash-Lite Latestgoogle/gemini-flash-lite-latest | $0.25 | $1.50 | $0.025 | 1,048,576 | 1.0× pricier |
| Qwen3-Coder 480B-A35B Instructqwen/qwen3-coder-480b-a35b-instruct | $0.22 | $1.80 | — | 131,072 | 1.8× pricier |
| Qwen3.6 Plusqwen/qwen3.6-plus | $0.28 | $1.65 | $0.055 | 1,000,000 | 1.1× pricier |
| Qwen3 Maxqwen/qwen3-max | $0.36 | $1.43 | $0.072 | 262,144 | 1.0× pricier |
| GPT-5 Miniopenai/gpt-5-mini | $0.25 | $2.00 | $0.025 | 400,000 | 6.7× pricier |
| Seed 2.0 Litebytedance/dola-seed-2.0-lite | $0.25 | $2.00 | — | 131,072 | 3.4× pricier |
| Qwen3.7 Plusqwen/qwen3.7-plus | $0.40 | $1.60 | — | 1,000,000 | 1.4× pricier |
| GPT-4.1 miniopenai/gpt-4.1-mini | $0.40 | $1.60 | $0.10 | 1,047,576 | 1.3× pricier |
| DeepSeek-V3.1deepseek/deepseek-v3.1 | $0.50 | $1.50 | — | 164,000 | 2.3× pricier |
| Mistral Large 3mistral/mistral-large-2512 | $0.50 | $1.50 | $0.05 | 256,000 | 1.0× pricier |
| GPT-3.5-turboopenai/gpt-3.5-turbo | $0.50 | $1.50 | — | 16,385 | 1.1× pricier |
| Mistral Large (latest)mistral/mistral-large-latest | $0.50 | $1.50 | — | 262,144 | Lowest anywhere |
| Devstral 2mistral/devstral-2512 | $0.40 | $2.00 | $0.04 | 256,000 | 1.0× pricier |
| Mistral Medium 3mistral/mistral-medium-2505 | $0.40 | $2.00 | $0.04 | 128,000 | 1.0× pricier |
| Mistral Medium (latest)mistral/mistral-medium-latest | $0.40 | $2.00 | — | 262,144 | Lowest anywhere |
| Devstral 2 (latest)mistral/devstral-medium-latest | $0.40 | $2.00 | — | 262,144 | Lowest anywhere |
| Devstral Mediummistral/devstral-medium-2507 | $0.40 | $2.00 | — | 128,000 | Lowest anywhere |
| Qwen3.6 27Bqwen/qwen3.6-27b | $0.29 | $2.40 | — | 131,072 | 1.6× pricier |
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | $0.30 | $2.50 | $0.03 | 1,048,576 | 3.5× pricier |
| Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite | $0.30 | $2.50 | $0.03 | 1,048,576 | 2.0× pricier |
| Nano BananaImage gengoogle/gemini-2.5-flash-image | $0.30 | $2.50 | — | 32,768 | 1.4× pricier |
| GLM-4.5Vzai/glm-4.5v | $0.60 | $1.80 | $0.11 | 128,000 | 2.1× pricier |
| Seed 2.0 Codebytedance/dola-seed-2.0-code | $0.40 | $2.40 | — | 256,000 | 1.0× pricier |
| Qwen3 VL 235B A22B Thinkingqwen/qwen3-vl-235b-a22b-thinking | $0.29 | $2.87 | $0.057 | 131,072 | Lowest anywhere |
| Llama-3.1-70B-Instructmeta/llama-3.1-70b-instruct | $0.99 | $0.99 | — | 128,000 | 2.5× pricier |
| GLM-4.7zai/glm-4.7 | $0.60 | $2.20 | $0.11 | 200,000 | 2.9× pricier |
| GLM-4.6zai/glm-4.6 | $0.60 | $2.20 | $0.11 | 200,000 | 2.1× pricier |
| GLM-4.5zai/glm-4.5 | $0.60 | $2.20 | $0.11 | 128,000 | 2.0× pricier |
| Qwen3 Coder Plusqwen/qwen3-coder-plus | $0.57 | $2.29 | $0.11 | 1,000,000 | Lowest anywhere |
| MiniMax-M2.7-highspeedminimax/minimax-m2.7-highspeed | $0.60 | $2.40 | $0.06 | 204,800 | 2.0× pricier |
| MiniMax-M2.5-highspeedminimax/minimax-m2.5-highspeed | $0.60 | $2.40 | $0.06 | 204,800 | 1.0× pricier |
| GLM-5.3zai/glm-5.3 | $0.70 | $2.20 | $0.13 | 1,000,000 | 1.7× pricier |
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | $0.60 | $2.50 | — | 262,144 | 1.3× pricier |
| Gemini 3 Flash Previewgoogle/gemini-3-flash-preview | $0.50 | $3.00 | $0.05 | 1,048,576 | 7.0× pricier |
| Nano Banana 2Image gengoogle/gemini-3.1-flash-image | $0.50 | $3.00 | — | 32,768 | 1.3× pricier |
| Seed 2.0 Probytedance/dola-seed-2.0-pro | $0.50 | $3.00 | — | 131,072 | 1.2× pricier |
| Dola Seed 2.0 Code (preview)bytedance/dola-seed-2.0-code-preview | $0.50 | $3.00 | — | 131,072 | Only channel |
| Kimi K2.5moonshot/kimi-k2.5 | $0.60 | $3.00 | $0.10 | 262,144 | 1.7× pricier |
| Qwen3.7 Maxqwen/qwen3.7-max | $0.83 | $2.48 | $0.17 | 1,000,000 | Lowest anywhere |
| Grok Build 0.1xai/grok-build-0.1 | $1.00 | $2.00 | $0.20 | 256,000 | 1.0× pricier |
| Gemini 3.7 Flashgoogle/gemini-3.7-flash | $0.75 | $3.75 | $0.075 | 1,048,576 | 1.0× pricier |
| Gemini 3.8 Flashgoogle/gemini-3.8-flash | $0.75 | $3.75 | $0.075 | 1,048,576 | 1.0× pricier |
| GLM-5zai/glm-5 | $1.00 | $3.20 | $0.20 | 200,000 | 2.1× pricier |
| Grok 4.3xai/grok-4.3 | $1.25 | $2.50 | $0.20 | 1,000,000 | 1.0× pricier |
| Grok 4.20 (Non-Reasoning)xai/grok-4.20-0309-non-reasoning | $1.25 | $2.50 | $0.20 | 1,000,000 | 1.0× pricier |
| Grok 4.20xai/grok-4.20-0309-reasoning | $1.25 | $2.50 | $0.20 | 1,000,000 | 1.0× pricier |
| GLM-5.2zai/glm-5.2 | $1.05 | $3.30 | $0.20 | 1,000,000 | 3.3× pricier |
| GPT-5.4 miniopenai/gpt-5.4-mini | $0.75 | $4.50 | $0.075 | 400,000 | 1.3× pricier |
| Kimi K2.6moonshot/kimi-k2.6 | $0.95 | $4.00 | $0.16 | 262,144 | 3.6× pricier |
| Kimi K2.7 Codemoonshot/kimi-k2.7-code | $0.95 | $4.00 | $0.19 | 262,144 | 3.6× pricier |
| Sakana Namazusakana/sakana-namazu | $0.95 | $4.00 | $0.15 | 262,144 | 1.0× pricier |
| Inklingthinkingmachines/inkling | $1.00 | $4.05 | $0.17 | 1,048,000 | 1.0× pricier |