Pricing
Updated
BroadNet Inference charges pay-as-you-go per token for chat, in USD per 1M input, cached input and output tokens, and per audio minute for transcription. DeepSeek V4.1 Flash is also sold as flat session plans from $60 a month, one request at a time per session. New accounts get $5 of starting credit for eligible models.
Prices on this page are from BroadNet's price feed snapshot dated , not checked live here. See official pricing for current rates.
official pricingWhat does each model cost?
Chat models are priced in USD per 1M tokens; speech to text in USD per minute of audio. Cached input applies only to prompt tokens the API reports as read from cache (usage.prompt_tokens_details.cached_tokens), usually the repeated start of recent requests. A model without a published cached rate has none, which is not the same as zero. More models are available on request.
| Chat model | Input, per 1M tokens | Cached input, per 1M tokens | Output, per 1M tokens | Context, tokens | Input types | Access |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash broadnet/deepseek-v4.1-flash | $0.175 | $0.0055 | $0.52 | 1,048,576 | text, image (vision) | Top-up required |
| GLM 5.3 broadnet/glm-5.3 | $0.78 | $0.173 | $3.46 | 1,048,576 | text | Top-up required |
| Qwen3.8 27B broadnet/qwen3.8-27b | $0.175 | $0.0435 | $2.17 | 262,144 | text, image (vision) | Top-up required |
| BroadNet Gemma 4 VL 26B broadnet/gemma-4-26b-a4b | $0.10 | Not published | $0.22 | 32,768 | text, image (vision) | Starting credit eligible |
| Speech to text | USD per audio minute | Languages | Access |
|---|---|---|---|
| BroadNet Transcribe Arabic broadnet/cohere-transcribe-arabic | $0.0042 | Arabic | Starting credit eligible |
| BroadNet Transcribe broadnet/cohere-transcribe | $0.002 | 14 languages | Starting credit eligible |
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
Estimate a pay-as-you-go charge
Enter your total input and output tokens for the period you want to price. The cache-hit share starts at 0%; raise it only if your traffic reuses a long prompt prefix.
Rates are the published USD prices per 1M tokens from the price feed snapshot dated 2026-11-14. The estimate excludes taxes, which depend on your location and are set at checkout, and extra usage such as retries, failed calls and re-sent context.
Reasoning tokens. DeepSeek V4.1 Flash, GLM 5.3 and Qwen3.8 27B reason before they answer. BroadNet's API reference says the reasoning counts toward max_tokens and is reported in usage.completion_tokens_details.reasoning_tokens, inside the completion (output) tokens. Include it in the output figure; BroadNet publishes no separate reasoning rate.
Images on a pay-as-you-go key are billed as input tokens. Arabic text is a different number of tokens on each model; measure it with the Arabic token counter instead of guessing from characters.
Estimate a transcription charge
Audio is billed per minute: the charge is minutes × the per-minute rate. For Arabic audio, BroadNet recommends its Arabic model.
USD per minute of audio, from the price feed snapshot dated 2026-11-14. Both transcription models can use the starting credit. BroadNet does not publish how partial minutes are rounded, so treat short clips as approximate. Files are WAV or MP3 up to 26,214,400 bytes each. Taxes and retries are not included.
Flat-price DeepSeek session plans
Prefer a fixed charge? DeepSeek V4.1 Flash is sold by the session, by the month, week or hour. Plan keys are separate from pay-as-you-go keys and do not draw on your balance. Work out how many sessions you need, and compare a plan with pay-as-you-go for the same period, on the plans page.
Full Moon
Billed per month
$60 a month per session
One request at a time per session
Founders offer: 25% off for the first 3 months, $45 a month per session, then the standard $60. BroadNet's feed says: “Enter a founders code at checkout.” No code is published here.
Start Full Moon on inference.broadnet.aiOrbit
Billed per week
$15 a week per session
One request at a time per session
Buy a week on inference.broadnet.aiMeteor
Billed per hour
$1 an hour per session
One request at a time per session
Start an hour on inference.broadnet.aiAll plans cover DeepSeek V4.1 Flash only, with no token meter for the purchased period. One session runs one request at a time, so parallel agents need one session each. Context limits and the Acceptable Use Policy still apply; images are included. Session pricing does not guarantee throughput or uptime. Prices in US dollars; BroadNet's plans page says tax is added at checkout where it applies.
Gemma hourly key
A separate product from the plans: $0.50 buys one hour of BroadNet Gemma 4 VL 26B with one concurrent stream, 120 requests a minute and 300,000 tokens a minute. The starting credit can pay for it. Revoking the key stops new requests but does not reverse the charge.
Open BroadNet's official rate cardOpen the BroadNet console
Questions
When is a session plan cheaper than paying per token?
When one agent would spend more than $60 a month on DeepSeek V4.1 Flash pay-as-you-go. At published standard rates that is about 343 million uncached input tokens, or 115 million output tokens, a month. A lower plan charge does not prove the work fits: one session runs one request at a time. Compare with your own workload.
What does the starting credit cover?
New accounts get $5 of starting credit. It covers pay-as-you-go use of BroadNet Gemma 4 VL 26B, BroadNet Transcribe Arabic and BroadNet Transcribe, and Gemma hourly keys. DeepSeek V4.1 Flash, GLM 5.3 and Qwen3.8 27B open after a qualifying top-up. Session plans are bought separately.
What is a Gemma hourly key?
A prepaid $0.50 key for one hour of BroadNet Gemma 4 VL 26B: one concurrent stream, 120 requests a minute and 300,000 tokens a minute. It is its own product, separate from the Meteor plan, which is an hour of DeepSeek V4.1 Flash.
How are reasoning tokens billed?
BroadNet publishes no separate reasoning rate. Its API reference says reasoning counts toward max_tokens and is reported in usage.completion_tokens_details.reasoning_tokens, part of the completion (output) tokens. Count it in your output estimate.
Are images extra?
On a pay-as-you-go key an image is billed as input tokens, and a larger image uses more tokens. On a session plan, images are part of the flat price.
Is tax included?
Prices are in US dollars. BroadNet's plans page says tax is added at checkout where it applies. The estimates on this page exclude tax.