BroadRouter

GMI Cloud API pricing

Updated

GMI Cloud lists standard prices for 97 models. The cheapest is DeepSeek V4 Flash at USD 0.091 input and USD 0.182 output per 1M tokens; the dearest is GPT-6 Astra at USD 10 / USD 50. It publishes cached-input prices for 62 of them, and lists no per-model batch, flex or priority prices on the pages we read.

GMI Cloud hosts models it does not train. By maker: DeepSeek 21, Qwen 19, Google 11, Z.ai 10, OpenAI 8, MiniMax 6, and 8 more. 97 prices, each read from GMI Cloud's own pricing page or one of 96 linked model pages, checked 2026-11-15. BroadRouter is BroadNet's own site and does not sell GMI Cloud's services. Automated re-check 2026-11-16: 97 of 97 prices still matched the provider's page.

Models with a standard price
97
Median input / output
USD 0.417 / USD 1.92
Cached-input prices
62 of 97
Cheapest host for
23 of 91 shared models

Which models is GMI Cloud the cheapest provider for?

Of the 91 models that GMI Cloud and at least one other provider both price at the standard tier, GMI Cloud has the lowest price for 23, ranked on a blend of 3 input tokens to 1 output token (5 of them tied with another provider at the same price). It also ties the lowest price for 22 more, where another provider is listed first. It is the dearest for 21. Another 6 models have a standard price from GMI Cloud only.

Models where GMI Cloud is the cheapest provider
ModelGMI Cloud input / outputNext cheapestSaving on 3:1 blendProviders
GLM 5.3 Flash (promo)USD 0.075 / USD 0.25CoreWeave Forge USD 0.12 / USD 0.3836%20
DeepSeek V4 Pro (promo)USD 0.957 / USD 1.914DeepInfra USD 1.30 / USD 2.6026%11
DeepSeek V3.2 (promo)USD 0.2088 / USD 0.3096DeepInfra USD 0.26 / USD 0.3819%11
GLM 5 (promo)USD 0.60 / USD 1.92SiliconFlow USD 0.95 / USD 2.5531%10
Llama 4 Maverick 17B 128E Instruct FP8USD 0.25 / USD 0.80Novita AI USD 0.27 / USD 0.857%7
Kimi K2 ThinkingUSD 0.80 / USD 1.20Amazon Bedrock USD 0.60 / USD 2.5016%6
Qwen3 235B A22B Instruct 2507 FP8 (promo)USD 0.0875 / USD 0.35DeepInfra USD 0.09 / USD 0.5525%5
MiMo V2.6 Flash (promo)USD 0.112 / USD 0.224DeepInfra USD 0.14 / USD 0.2820%5
DeepSeek R1USD 0.50 / USD 2.18SiliconFlow USD 0.50 / USD 2.18tie4
DeepSeek R1 Distill Qwen 32BUSD 0.50 / USD 0.90Cloudflare Workers AI USD 0.497 / USD 4.88162%3
MiniMax M2.7 (promo)USD 0.21 / USD 0.84Featherless USD 0.30 / USD 1.2030%3
DeepSeek V3 0324USD 0.29 / USD 1.14Featherless USD 0.385 / USD 1.62528%3
Qwen3.8 Max (0902)USD 1.65 / USD 4.951Alibaba Cloud USD 2 / USD 617%3
MiMo V2.6 Pro (promo)USD 0.32625 / USD 0.6525DeepInfra USD 0.387 / USD 0.78316%3
DeepSeek-V3.1-TerminusUSD 0.27 / USD 1SiliconFlow USD 0.27 / USD 1tie3

Showing the 15 with the most competing providers; the full price list below marks every model page.

The 6 models GMI Cloud sells that the most other providers also sell, with GMI Cloud's rank among them on the 3:1 blend.

GMI Cloud on the most widely hosted models
ModelGMI CloudRankCheapest
GLM 5.3USD 0.70 / USD 2.202 of 24DeepInfra USD 0.5625 / USD 2.50
GLM 5.3 FlashUSD 0.075 / USD 0.251 of 20GMI Cloud (this page)
GLM 5.2USD 1.40 / USD 4.405 of 19DeepInfra USD 0.5625 / USD 1.80
Kimi K3USD 3 / USD 155 of 18Chutes USD 1.85 / USD 9.50
DeepSeek V4.1 Flash 1017USD 0.18 / USD 0.722 of 16DeepInfra USD 0.098 / USD 0.294
DeepSeek V4.1 FlashUSD 0.18 / USD 0.724 of 16DeepInfra USD 0.14 / USD 0.42

Which model makers does GMI Cloud sell?

GMI Cloud prices models from 14 makers. DeepSeek leads with 21 models. Standard prices, USD per 1M input / output tokens.

GMI Cloud models by maker
MakerModelsCheapest modelMedian input / output
DeepSeek21DeepSeek V4 Flash USD 0.091 / USD 0.182USD 0.27 / USD 0.858
Qwen19Qwen3 30B A3B (fp8) USD 0.08 / USD 0.25USD 0.35 / USD 3
Google11Gemma 4 26B A4B USD 0.13 / USD 0.40USD 0.75 / USD 3.75
Z.ai10GLM 5.3 Flash USD 0.075 / USD 0.25USD 0.60 / USD 2.10
OpenAI8GPT-6 Luna USD 0.10 / USD 0.50USD 2.25 / USD 12.50
MiniMax6MiniMax M3.1 Flash USD 0.15 / USD 0.60USD 0.27 / USD 1.08
Moonshot AI6Kimi K2 Thinking USD 0.80 / USD 1.20USD 1.425 / USD 6
Tencent4Hy3 USD 0.14 / USD 0.58USD 0.2985 / USD 0.92525
Meta3Llama 4 Scout 17B 16E Instruct USD 0.08 / USD 0.50USD 0.25 / USD 0.75
xAI3Grok 4.5 USD 2 / USD 6USD 2 / USD 6
StepFun2Step 3.7 Flash USD 0.20 / USD 1.15USD 0.60 / USD 1.925
Xiaomi2MiMo V2.6 Flash USD 0.112 / USD 0.224USD 0.219125 / USD 0.43825
NVIDIA1NVIDIA Nemotron 3 Ultra USD 0.80 / USD 2.60—
Ricursive AI1Ripple-65B Preview USD 0.20 / USD 0.60—

GMI Cloud price list

USD per 1M tokens: 97 prices for 97 models, one row per model with any other service tiers stacked under the standard price. Sources checked 2026-11-15 unless a row says otherwise. "vs maker" compares a standard price with the model maker's own API on the 3:1 blend; a minus means GMI Cloud is cheaper. Of 46 hosted model prices with a maker price to compare, 11 are below the maker's and 6 above.

GMI Cloud API prices by model
ModelTierInputCachedOutputContextvs makerSource
DeepSeek Prover V2 671BstandardUSD 0.50—USD 2.18131,072—source
DeepSeek R1standardUSD 0.50—USD 2.18131,072—source
DeepSeek R1 0528standardUSD 0.57USD 0.23USD 2.29131,072—source
DeepSeek R1 Distill Llama 70BstandardUSD 0.25—USD 0.75131,072—source
DeepSeek R1 Distill Llama 8BstandardUSD 0.14—USD 0.39131,072—source
DeepSeek R1 Distill Qwen 14BstandardUSD 0.20—USD 0.20131,072—source
DeepSeek R1 Distill Qwen 32BstandardUSD 0.50—USD 0.90131,072—source
DeepSeek R1 Distill Qwen 7BstandardUSD 0.10—USD 0.20131,072—source
DeepSeek V3 0324standardUSD 0.29USD 0.11USD 1.14128,000—source
DeepSeek V3.1standardUSD 0.27—USD 1163,840—source
DeepSeek V3.2promostandardUSD 0.2088USD 0.0216USD 0.3096163,840—source
DeepSeek V4 FlashpromostandardUSD 0.091USD 0.0182USD 0.1821,048,575—source
DeepSeek V4 Flash 0731promostandardUSD 0.286USD 0.0091USD 0.8581,048,575—source
DeepSeek V4 PropromostandardUSD 0.957USD 0.07975USD 1.9141,048,576−40%source
DeepSeek V4 Pro 0813promostandardUSD 1.056USD 0.0352USD 3.1681,048,575−20%source
DeepSeek V4.1 FlashpromostandardUSD 0.18USD 0.0036USD 0.721,048,575−40%source
DeepSeek V4.1 Flash 1017promostandardUSD 0.18USD 0.0036USD 0.721,048,575−40%source
DeepSeek-V3.1-TerminusstandardUSD 0.27—USD 1131,072—source
DeepSeek-V3.2-ExpstandardUSD 0.27—USD 0.41163,840—source
DeepSeek-V3.2-SpecialestandardUSD 0.28—USD 0.40163,840—source
DeepSeek-V4-Flash-Vision-ExpstandardUSD 0.44USD 0.014USD 1.321,048,575—source
Gemini 3.1 Flash-Lite (gemini-3.1-flash-lite-preview)standardUSD 0.25USD 0.025USD 1.501,048,576—source
Gemini 3.1 Pro PreviewstandardUSD 2—USD 121,048,576samesource
Gemini 3.5 FlashstandardUSD 1.50USD 0.15USD 91,048,576—source
Gemini 3.5 Flash-LitestandardUSD 0.30USD 0.03USD 2.501,048,576samesource
Gemini 3.6 FlashstandardUSD 1.50USD 0.15USD 7.501,048,576+100%source
Gemini 3.7 FlashstandardUSD 0.75USD 0.075USD 3.751,048,576—source
Gemini 3.8 FlashstandardUSD 0.75USD 0.075USD 3.751,048,576samesource
Gemini 4 ArgonpromostandardUSD 2USD 0.10USD 101,048,576samesource
Gemini 4 CarbonpromostandardUSD 2USD 0.10USD 101,048,576samesource
Gemma 4 26B A4BstandardUSD 0.13—USD 0.40256,000—source
Gemma 4 31BstandardUSD 0.14USD 0.10USD 0.40262,144—source
GLM 4.5 AirstandardUSD 0.20—USD 1.10131,076samesource
GLM 4.6standardUSD 0.60—USD 2204,800−5%source
GLM 4.7standardUSD 0.60USD 0.11USD 2.20202,752samesource
GLM 4.7 FlashstandardUSD 0.07—USD 0.40202,752—source
GLM 5promostandardUSD 0.60USD 0.12USD 1.92202,752−40%source
GLM 5.1standardUSD 1.40USD 0.26USD 4.40202,752samesource
GLM 5.2standardUSD 1.40USD 0.26USD 4.401,048,576samesource
GLM 5.3promostandardUSD 0.70USD 0.13USD 2.201,048,576−50%source
GLM 5.3 FlashpromostandardUSD 0.075USD 0.015USD 0.251,048,576−50%source
GLM-4.5-FP8standardUSD 0.60—USD 2.20131,072samesource
GPT-5.5standardUSD 5USD 0.50USD 301,050,000samesource
GPT-5.6 LunastandardUSD 1USD 0.10USD 61,050,000+400%source
GPT-5.6 SolstandardUSD 5USD 0.50USD 301,050,000+41%source
GPT-5.6 TerrastandardUSD 2.50USD 0.25USD 151,050,000+25%source
GPT-6 AstrastandardUSD 10USD 1USD 501,050,000samesource
GPT-6 LunastandardUSD 0.10USD 0.01USD 0.501,050,000samesource
GPT-6 SolstandardUSD 2USD 0.20USD 101,050,000samesource
GPT-6.1 SolstandardUSD 2USD 0.10USD 101,050,000samesource
Grok 4.5standardUSD 2USD 0.50USD 62,000,000samesource
Grok 4.6standardUSD 2USD 0.50USD 62,000,000samesource
Grok 4.7standardUSD 2USD 0.50USD 6500,000samesource
Hy3standardUSD 0.14USD 0.035USD 0.58262,144—source
Hy4promostandardUSD 0.417USD 0.021USD 1.25051,000,000—source
Hy4 PreviewstandardUSD 0.834USD 0.042USD 2.501262,144—source
Kimi K2 ThinkingstandardUSD 0.80—USD 1.20262,144—source
Kimi K2.5standardUSD 0.60—USD 3262,144—source
Kimi K2.7 CodestandardUSD 0.95USD 0.19USD 4262,144samesource
Kimi K3standardUSD 3USD 0.30USD 151,048,576samesource
Kimi K3.1 ProstandardUSD 2USD 0.20USD 101,048,576samesource
Llama 3.3 70BstandardUSD 0.25—USD 0.75131,072—source
Llama 4 Maverick 17B 128E Instruct FP8standardUSD 0.25—USD 0.801,048,576—source
Llama 4 Scout 17B 16E InstructstandardUSD 0.08—USD 0.501,048,576—source
MiMo V2.6 FlashpromostandardUSD 0.112USD 0.00224USD 0.2241,050,000—source
MiMo V2.6 PropromostandardUSD 0.32625USD 0.0027USD 0.65251,050,000—source
MiniMax M2standardUSD 0.30—USD 1.20196,608—source
Minimax M2.1standardUSD 0.30USD 0.03USD 1.20196,608—source
MiniMax M2.5standardUSD 0.30USD 0.03USD 1.20196,608—source
MiniMax M2.7promostandardUSD 0.21USD 0.042USD 0.84196,608—source
MiniMax M3promostandardUSD 0.24USD 0.048USD 0.961,048,576−20%source
MiniMax M3.1 FlashstandardUSD 0.15USD 0.015USD 0.601,048,576samesource
moonshotai/Kimi: K2.7-Code-HighspeedstandardUSD 1.90USD 0.38USD 8262,144—source
NVIDIA Nemotron 3 UltrastandardUSD 0.80USD 0.10USD 2.60262,144—source
Qwen3 235B A22B FP8standardUSD 0.17—USD 1.0932,768—source
Qwen3 235B A22B Instruct 2507 FP8promostandardUSD 0.0875USD 0.0175USD 0.35131,072—source
Qwen3 235B A22B Thinking 2507 FP8standardUSD 0.35—USD 4.20131,072—source
Qwen3 30B A3B (fp8)standardUSD 0.08—USD 0.2540,946—source
Qwen3 32B FP8standardUSD 0.10—USD 0.6032,768—source
Qwen3 Coder 480B A35BstandardUSD 0.90USD 0.18USD 4.50262,128—source
Qwen3 Next 80B A3B ThinkingstandardUSD 0.15—USD 1.50262,144—source
Qwen3.5 122B A10BstandardUSD 0.40—USD 3.20262,144samesource
Qwen3.5 27BstandardUSD 0.30—USD 2.40262,144samesource
Qwen3.5 35B A3BstandardUSD 0.25—USD 2262,144samesource
Qwen3.5 397B A17BstandardUSD 0.60—USD 3.60262,144samesource
Qwen3.6 35B A3BstandardUSD 0.248—USD 1.485262,144−34%source
Qwen3.6 PlusstandardUSD 0.50—USD 3262,144samesource
Qwen3.6 Plus 2026-04-02standardUSD 0.50—USD 3262,144—source
Qwen3.7 MaxstandardUSD 2.50USD 0.25USD 7.50262,144samesource
Qwen3.8 27BstandardUSD 0.45USD 0.25USD 3.20262,144+1%source
Qwen3.8 FlashstandardUSD 0.16USD 0.016USD 0.471,048,575+3%source
Qwen3.8 MaxstandardUSD 2USD 0.25USD 6262,144samesource
Qwen3.8 Max (0902)standardUSD 1.65USD 0.206USD 4.951262,144−17%source
Ripple-65B PreviewstandardUSD 0.20USD 0.05USD 0.601,000,000—source
Step 3.7 FlashstandardUSD 0.20USD 0.04USD 1.15256,000—source
Step 5 PreviewstandardUSD 1USD 0.10USD 2.701,048,576—source
Tencent/hy3-previewstandardUSD 0.18USD 0.06USD 0.60262,144—source
  • Cached "—" means GMI Cloud's page shows no cache price for that row; budget cached tokens at the input price.
  • Promo: GMI Cloud's page describes 18 prices as promotional or discounted; they can end without notice. Each model page has the list price where the source gives one.

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What service tiers does GMI Cloud publish?

Standard prices only: GMI Cloud publishes no per-model batch, flex, priority or fast price on the pages we read.

Cached input: 62 of 97 standard prices include a cache-read price, a median 10% of the input price. What cached input means.

What we recorded about GMI Cloud's pricing page: GMI Cloud MaaS (serverless) per-token prices from each model's public page in the GMI Cloud console model library (console.gmicloud.ai, no login needed). The same values are in GMI's public catalogue JSON behind that page (ie-api.gmicloud.ai/v1/artifact/get_public_artifacts, prices in millionths of a USD). www.gmicloud.ai/en/pricing covers GPU-hours only and points to the Models page for inference prices. Standard price is the price charged now; discounts shown as "x% off" are noted as promotional with the list price. Rows at the shortest prompt tier where GMI publishes prompt-length tiers. Duplicate hardware/dev deployments, OCR models and image, video and audio models excluded. GMI also resells proprietary models (OpenAI, Google, xAI); those are host rows.

Is GMI Cloud cheaper than the model makers' own APIs?

Mostly it charges the same as the maker. Of 46 standard prices for models whose maker sells its own API, 11 are below the maker's price, 6 above and 29 the same, on the 3:1 blend. The median difference is zero. The biggest saving is GLM 5.3 Flash, 50% below Z.ai. The biggest markup is GPT-5.6 Luna, 400% above OpenAI.

BroadNet Inference and GMI Cloud

BroadRouter is BroadNet's own site, so BroadNet is never ranked on this page. BroadNet Inference also serves 4 models that GMI Cloud prices: BroadNet Gemma 4 VL 26B at USD 0.10 / USD 0.22 against GMI Cloud's USD 0.13 / USD 0.40 (BroadNet is cheaper on the 3:1 blend); DeepSeek V4.1 Flash at USD 0.175 / USD 0.52 against GMI Cloud's USD 0.18 / USD 0.72 (BroadNet is cheaper on the 3:1 blend); GLM 5.3 at USD 0.78 / USD 3.46 against GMI Cloud's USD 0.70 / USD 2.20 (GMI Cloud is cheaper on the 3:1 blend); Qwen3.8 27B at USD 0.175 / USD 2.17 against GMI Cloud's USD 0.45 / USD 3.20 (BroadNet is cheaper on the 3:1 blend). BroadNet prices are from its rate card, synced 2026-11-14. BroadNet Inference pricing.

More on GMI Cloud

Questions

How much does the GMI Cloud API cost per token?

GMI Cloud's standard prices run from USD 0.091 input and USD 0.182 output per 1M tokens (DeepSeek V4 Flash) to USD 10 / USD 50 (GPT-6 Astra). The median across 97 standard prices is USD 0.417 input and USD 1.92 output per 1M, which is USD 0.000000417 per input token. Input, cached input and output are billed separately.

What is the cheapest model on GMI Cloud?

DeepSeek V4 Flash, at USD 0.091 input and USD 0.182 output per 1M tokens (USD 0.1138 on a 3:1 input-to-output blend), a promotional price. The cheapest from other makers: Qwen3 30B A3B (fp8) (Qwen) at USD 0.08 / USD 0.25; Gemma 4 26B A4B (Google) at USD 0.13 / USD 0.40; GLM 5.3 Flash (Z.ai) at USD 0.075 / USD 0.25.

Is GMI Cloud cheaper than other providers?

It depends on the model. Of 91 models that other providers also price, GMI Cloud is the cheapest standard price for 23 (5 of them tied with another provider), for example GLM 5.3 Flash, DeepSeek V4 Pro and DeepSeek V3.2; it ties the lowest price, without beating it, for 22 more; another provider is cheaper for 46; and it is the dearest for 21. Its median rank is 2 of a median 6 providers, on a 3:1 input-to-output blend.

Does GMI Cloud have batch, cached or priority pricing?

Cached input: yes, for 62 of 97 standard prices, at a median 10% of the input price. No batch, flex or priority prices are listed per model on the pages we read.

How much does a chatbot cost per month on GMI Cloud?

For 2,000 requests a day, 1,500 input tokens (60% cached), 300 output, over 30 days: USD 7.53 on DeepSeek V4 Flash, USD 62.64 on GLM 5 (the middle of GMI Cloud's list) and USD 1,314 on GPT-6 Astra. Try your own numbers.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity