Merge Gateway model pricing.

prices as of · 149 models · 151 prices

Sells many makers' models through one API and one bill.

Merge Gateway is a router selling 149 models, from $0.10 per million tokens for GLM-5.3-Flash, read on 16 Sept 2026.

Kind of provider

Router

home country not stated

Where it runs

not stated

no regions published

How you pay

not stated

no payment terms published

Free tier

none published

nothing given away

Where Merge Gateway's prices land, and why

Merge Gateway publishes 151 prices we can compare, and 40 of them are below the list price for that model. 25 of those have a published reason behind them, so they rank like any other price. The other 13 sit below list on models whose weights are closed, with nothing published to account for the gap, so they are listed here in full and ranked nowhere on the site. Nobody here has read its terms, legal entity and data policy yet, so treat what it says about itself as its own claim.

Merge Gateway does not say whether it trains on what you send it. It does not say how long it keeps requests.

not yet checked: terms, legal entity and data policy

Models to start with

all 151 prices ↓
  • DeepSeek V4 Flash 0731DeepSeek · 1M context · 97 providers sell it$0.14 / $0.2834% under list
  • GLM-5.2Z.ai · 1M context · 94 providers sell it$1.05 / $3.3025% under list
  • DeepSeek V4 ProDeepSeek · 1M context · 84 providers sell it$1.74 / $3.48300% above list
  • Kimi K2.6Moonshot AI · 262k context · 82 providers sell it$0.95 / $4same as list
  • Kimi K3Moonshot AI · 1M context · 81 providers sell it$2.90 / $145% under list

Everything Merge Gateway sells, against the list price

Cheapest first inside each group. The share is this row against the price the lab that trained the model charges.

Cheaper, and we know why

25 prices

Below list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.

  • GLM-5.3-Flash

    Z.ai · 1M context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.01 / $0.05in / out per M

    0.20×of list price

  • Gemma 3 4B

    Google · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.04 / $0.08in / out per M

    0.80×of list price

  • Qwen3.5-9B

    Alibaba Cloud · 262k context

    10% under the list price, an ordinary reseller margin.

    $0.09 / $0.13in / out per M

    0.89×of list price

  • gpt-oss-safeguard-20b

    OpenAI · 131k context

    7% under the list price, an ordinary reseller margin.

    $0.07 / $0.20in / out per M

    0.78×of list price

  • Qwen3.5 35B-A3B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.06 / $0.46in / out per M

    0.23×of list price

  • DeepSeek V4 Flash 0731

    DeepSeek · 1M context

    7% under the list price, an ordinary reseller margin.

    $0.14 / $0.28in / out per M

    0.66×of list price

  • Gemma 4 26B A4B IT

    Google · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.13 / $0.40in / out per M

    0.75×of list price

  • Qwen3.5 27B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.09 / $0.69in / out per M

    0.29×of list price

  • Qwen3-Next 80B-A3B Instruct

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.14 / $0.57in / out per M

    0.29×of list price

  • Qwen3 32B

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.15 / $0.60in / out per M

    0.21×of list price

  • Qwen3 Coder Next

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.15 / $0.80in / out per M

    0.52×of list price

  • Qwen3.5 122B-A10B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.12 / $0.92in / out per M

    0.29×of list price

  • Qwen3 30B A3B Instruct 2507

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.11 / $1.08in / out per M

    1.54×of list price

  • Qwen3.5 397B-A17B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.17 / $1.03in / out per M

    0.29×of list price

  • Qwen3-Next 80B-A3B (Thinking)

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.15 / $1.20in / out per M

    0.22×of list price

  • Qwen3 235B-A22B

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.29 / $1.15in / out per M

    0.41×of list price

  • Qwen3-VL 235B-A22B

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.29 / $1.15in / out per M

    0.41×of list price

  • Mistral Medium (latest)

    Mistral AI · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.40 / $2in / out per M

    0.27×of list price

  • Qwen3.6 27B

    Alibaba Cloud · 262k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.29 / $2.40in / out per M

    0.60×of list price

  • Qwen3 VL 235B A22B Thinking

    Alibaba Cloud · 131k context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.29 / $2.87in / out per M

    0.72×of list price

  • Qwen3 Coder Plus

    Alibaba Cloud · 1M context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.57 / $2.29in / out per M

    0.50×of list price

  • GLM-5.3

    Z.ai · 1M context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $0.70 / $2.20in / out per M

    0.50×of list price

  • GLM-5.2

    Z.ai · 1M context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $1.05 / $3.30in / out per M

    0.75×of list price

  • Inkling

    Thinking Machines · 1M context

    Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.

    $1 / $4.05in / out per M

    0.69×of list price

  • Kimi K3

    Moonshot AI · 1M context

    3% under the list price, an ordinary reseller margin.

    $2.90 / $14in / out per M

    0.95×of list price

Same price as the maker

113 prices

The same price the maker charges, sold by someone else.

  • Command R7B

    Cohere · 128k context

    The same price Cohere charges.

    $0.04 / $0.15in / out per M

    1.00×of list price

  • gpt-oss-20b

    OpenAI · 131k context

    33% above OpenRouter's price.

    $0.04 / $0.20in / out per M

    1.45×of list price

  • Gemini Embedding 001

    Google · 2k context

    The same price Google charges.

    $0.15 / $0in / out per M

    1.00×of list price

  • GPT-5 Nano

    OpenAI · 400k context

    The same price OpenAI charges.

    $0.05 / $0.40in / out per M

    1.00×of list price

  • Gemma 3 12B

    Google · 131k context

    80% above OpenRouter's price.

    $0.09 / $0.29in / out per M

    1.87×of list price

  • Devstral Small

    Mistral AI · 128k context

    The same price Mistral AI charges.

    $0.10 / $0.30in / out per M

    1.00×of list price

  • GLM-4.7-Flash

    Z.ai · 200k context

    16% above OpenRouter's price.

    $0.07 / $0.40in / out per M

    1.05×of list price

  • GLM-4.7-FlashX

    Z.ai · 200k context

    The same price Z.ai charges.

    $0.07 / $0.40in / out per M

    1.00×of list price

  • gpt-oss-120b

    OpenAI · 131k context

    143% above OpenRouter's price.

    $0.09 / $0.36in / out per M

    2.24×of list price

  • Gemma 3 27B

    Google · 131k context

    The same price OpenRouter charges.

    $0.08 / $0.45in / out per M

    1.00×of list price

  • Gemini 2.5 Flash-Lite

    Google · 1M context

    The same price Google charges.

    $0.10 / $0.40in / out per M

    1.00×of list price

  • GPT-4.1 nano

    OpenAI · 1M context

    The same price OpenAI charges.

    $0.10 / $0.40in / out per M

    1.00×of list price

  • Gemma 4 31B IT

    Google · 262k context

    56% above OpenRouter's price.

    $0.14 / $0.40in / out per M

    1.34×of list price

  • Llama 3.1 8B Instruct

    Meta · 131k context

    340% above OpenRouter's price.

    $0.22 / $0.22in / out per M

    3.83×of list price

  • Command R

    Cohere · 128k context

    The same price Cohere charges.

    $0.15 / $0.60in / out per M

    1.00×of list price

  • DeepSeek V4.1 Flash

    DeepSeek · 1M context

    The same price DeepSeek charges.

    $0.15 / $0.60in / out per M

    1.00×of list price

  • GPT-4o mini

    OpenAI · 128k context

    The same price OpenAI charges.

    $0.15 / $0.60in / out per M

    1.00×of list price

  • Mistral Small 3.2

    Mistral AI · 128k context

    50% above Mistral AI's price.

    $0.15 / $0.60in / out per M

    1.75×of list price

  • Llama-3.3-70B-Instruct

    Meta · 128k context

    120% above OpenRouter's price.

    $0.22 / $0.50in / out per M

    1.87×of list price

  • DeepSeek V3.2

    DeepSeek · 164k context

    The same price DeepSeek charges.

    $0.28 / $0.45in / out per M

    1.04×of list price

  • GLM-4.5-Air

    Z.ai · 131k context

    The same price Z.ai charges.

    $0.20 / $1.10in / out per M

    1.00×of list price

  • Codestral (latest)

    Mistral AI · 256k context

    The same price Mistral AI charges.

    $0.30 / $0.90in / out per M

    1.00×of list price

  • GPT-5.6 Luna

    OpenAI · 1.1M context

    The same price OpenAI charges.

    $0.20 / $1.20in / out per M

    1.00×of list price

  • GPT-5.4 nano

    OpenAI · 400k context

    The same price OpenAI charges.

    $0.20 / $1.25in / out per M

    1.00×of list price

  • MiniMax-M2

    MiniMax · 205k context

    The same price MiniMax charges.

    $0.30 / $1.20in / out per M

    1.00×of list price

  • MiniMax-M2.1

    MiniMax · 205k context

    The same price MiniMax charges.

    $0.30 / $1.20in / out per M

    1.00×of list price

  • MiniMax-M2.5

    MiniMax · 205k context

    The same price MiniMax charges.

    $0.30 / $1.20in / out per M

    1.00×of list price

  • MiniMax-M2.7

    MiniMax · 205k context

    The same price MiniMax charges.

    $0.30 / $1.20in / out per M

    1.00×of list price

  • MiniMax-M3

    MiniMax · 1M context

    The same price MiniMax charges.

    $0.30 / $1.20in / out per M

    1.00×of list price

  • Qwen3.6 35B-A3B

    Alibaba Cloud · 262k context

    The same price Alibaba Cloud charges.

    $0.25 / $1.49in / out per M

    1.00×of list price

showing the 30 cheapest of 113 · every row in the open dataset

Cheaper, and nobody says why

13 prices · never ranked

Below list on a closed model with nothing to account for it. Shown, never ranked, never a pick.

  • Qwen Flash

    Alibaba Cloud · 1M context

    0.44× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.02 / $0.22in / out per M

    0.51×of list price

  • Qwen Plus

    Alibaba Cloud · 1M context

    0.29× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.12 / $0.29in / out per M

    0.26×of list price

  • Qwen3 Coder Flash

    Alibaba Cloud · 1M context

    0.48× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.14 / $0.57in / out per M

    0.42×of list price

  • Qwen3.5 Plus

    Alibaba Cloud · 1M context

    0.29× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.12 / $0.69in / out per M

    0.29×of list price

  • Qwen3.6 Flash

    Alibaba Cloud · 1M context

    0.88× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.17 / $0.99in / out per M

    0.88×of list price

  • Qwen3-VL Plus

    Alibaba Cloud · 262k context

    0.71× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.14 / $1.43in / out per M

    0.85×of list price

  • Gemini Flash-Lite Latest

    Google · 1M context

    0.83× Google's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.25 / $1.50in / out per M

    0.66×of list price

  • Qwen3-Coder 480B-A35B Instruct

    Alibaba Cloud · 262k context

    0.15× the list price, from one source and far below what hosting the weights costs. Listed until a second source agrees.

    $0.22 / $1.80in / out per M

    0.20×of list price

  • Qwen3.6 Plus

    Alibaba Cloud · 1M context

    0.55× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.28 / $1.65in / out per M

    0.55×of list price

  • Qwen3 Max

    Alibaba Cloud · 262k context

    0.30× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.36 / $1.43in / out per M

    0.26×of list price

  • Qwen3.7 Plus

    Alibaba Cloud · 1M context

    0.80× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.40 / $1.60in / out per M

    0.62×of list price

  • Qwen3.7 Max

    Alibaba Cloud · 1M context

    0.33× Alibaba Cloud's list price on a closed model, and nobody says why. Listed, never ranked.

    $0.82 / $2.48in / out per M

    0.33×of list price

  • GPT-4 Turbo

    OpenAI · 128k context

    0.33× OpenAI's list price on a closed model, and nobody says why. Listed, never ranked.

    $10 / $30in / out per M

    0.40×of list price

Frequently asked

What is Merge Gateway?
Sells many makers' models through one API and one bill. It sells 149 of the models we track.
Is Merge Gateway cheaper than buying from the maker?
40 of its 151 prices sit below the list price for the model, and 25 of those have a published reason behind them, so they can lead a ranking. 13 are listed and never ranked.
Does Merge Gateway train on what you send it?
Merge Gateway does not say whether it trains on what you send it. It does not say how long it keeps requests.
How current are these Merge Gateway prices?
They come from the public catalogs we read, last read 16 Sept 2026. Prices exclude tax.