Skip to content
InfratoApp
Layers / Inference / Serving / Inference APIs / Together AI

Together AI

UNCLAIMED

By Together

INFERENCE APISEDGE AND ON-DEVICE

Together AI — The official Python library for the together API. Listed under Inference APIs in the Inference / Serving layer. 1 of 15 comparison attributes are recorded, each with the page it was read from.

Build what's next on the AI Native Cloud. Full-stack AI platform for inference, fine-tuning, and GPU clusters — powered by cutting-edge research.

2 OF 4 SIGNALS HELD · MISSING LICENCE, REPOSITORY

WebsitePricing page

What it runs on, and what runs on it

4 cited edges
The differentiator

Computed from the stack graph, both directions. Every cited edge links the page it was read from; a vendor-added one links the vendor’s own source — this is the reason to be here rather than on the vendor’s own site.

RUNS ON / INTEGRATES WITH

  • nothing recorded

USED BY

Open-source signals

LICENCE
not measured
STARS
not measured
DOWNLOADS 30D
322,052
LAST COMMIT
not measured

A HOLLOW RING IS UNMEASURED, NOT ZERO · WE DO NOT SUBSTITUTE A PARENT COMPANY’S REPOSITORY FOR A PRODUCT THAT HAS NONE

Price

MODELIN /1MCACHED /1MOUT /1MMOVEDTERMSSOURCE
deepseek-ai/DeepSeek-V4-Flash-0731$0.14$0.03$0.28— 0.0%$0.14 → $0.14on demand2026-10-23Dispute
deepseek-ai/DeepSeek-V4-Pro-0813$1.32$0.13$3.96— 0.0%$1.32 → $1.32on demand2026-10-27Dispute
deepseek-ai/DeepSeek-V4.1-Flash$0.30$0.01$1.20— 0.0%$0.30 → $0.30on demand2026-10-22Dispute
deepseek-ai/DeepSeek-V4.1-Flash-1017$0.30$0.01$1.20— 0.0%$0.30 → $0.30on demand2026-10-27Dispute
google/gemma-4-31B-it$0.39○$0.97— 0.0%$0.39 → $0.39on demand2026-10-23Dispute
meta-models/Muse-Glimmer-30B$0.35$0.04$1.50First readingon demand2026-10-14Dispute
meta-models/Muse-Spark-Open-816B-A42B$1.25$0.15$4.25— 0.0%$1.25 → $1.25on demand2026-10-27Dispute
meta-models/Muse-Spark-Open-816B-A42B-promo$0.00○$0.00First readingon demand2026-10-18Dispute
MiniMaxAI/MiniMax-M3$0.30$0.06$1.20— 0.0%$0.30 → $0.30on demand2026-10-27Dispute
MiniMaxAI/MiniMax-M3.1-Flash$0.15$0.01$0.60— 0.0%$0.15 → $0.15on demand2026-10-27Dispute
moonshotai/Kimi-K3$3.00$0.30$15.00— 0.0%$3.00 → $3.00on demand2026-10-27Dispute
Prism-ML/Ternary-Bonsai-27B$0.00○$0.00First readingon demand2026-10-27Dispute
Qwen/Qwen3.7-Plus$0.32○$1.28— 0.0%$0.32 → $0.32on demand2026-10-27Dispute
Qwen/Qwen3.8-2.4T-A95B$2.00$0.25$6.00— 0.0%$2.00 → $2.00on demand2026-10-27Dispute
Qwen/Qwen3.8-Flash$0.15○$0.47— 0.0%$0.15 → $0.15on demand2026-10-27Dispute
reflection/Beam-1.0-501B-A23B$0.40$0.04$1.20— 0.0%$0.40 → $0.40on demand2026-10-27Dispute
thinkingmachines/Inkling$1.00$0.17$4.05— 0.0%$1.00 → $1.00on demand2026-10-27Dispute
zai-org/GLM-5.2$1.40$0.26$4.40— 0.0%$1.40 → $1.40on demand2026-10-27Dispute
zai-org/GLM-5.3$1.40$0.26$4.40— 0.0%$1.40 → $1.40on demand2026-10-27Dispute
zai-org/GLM-5.3-Flash$0.15$0.03$0.50— 0.0%$0.15 → $0.15on demand2026-10-27Dispute
SKURATEMOVEDTERMSSOURCE
B200-SXM-192GB$11.00 /hr— 0.0%$11.00 → $11.00not stated2026-10-26Dispute

READINGS OVER 21 DAYS OLD ARE HIDDEN RATHER THAN SHOWN STALE, SO THIS TABLE CAN EMPTY OUT BETWEEN READS · MOVED COMPARES THE CHEAPEST READING WE TOOK ON EACH DAY, WHICH ON A MARKETPLACE IS A DIFFERENT HOST FROM THE ONE PRICED BESIDE IT — BOTH ENDS ARE SHOWN SO NOTHING HAS TO BE INFERRED · A MOVE IS A CHANGE IN OUR READING, WHICH IS NOT ALWAYS A CHANGE IN THE MARKET: A CORRECTED EXTRACTOR MOVES THE SERIES WITHOUT THE PRICE MOVING

Configurations

CONFIGURATIONSWhat you can rent, and what it holds

Together AI publishes no machine-readable catalogue of its instance types, so no configurations are recorded. The prices above were read from its pricing page; a configuration read the same way would be a guess about how many GPUs a price covers, which is the mistake this section exists to avoid.

NONE ON RECORD

CONFIGURATIONS ARE TAKEN ONLY FROM A VENDOR’S OWN CATALOGUE API · IF YOU WORK HERE AND PUBLISH ONE, TELL US AND IT WILL BE READ

What its categories ask

1 answered · 14 unanswered

15 questions declared by Inference APIs and Edge and on-device. Most rows across the directory read like these.

ATTRIBUTEANSWEREVIDENCE · SOURCE
Pricing modelusage-based2026-09-23
Data residencyno answer on record
Free tierno answer on record
GDPR DPAno answer on record
Hardwareno answer on record
Licenceno answer on record
Model formatsno answer on record
On-deviceno answer on record
Open sourceno answer on record
OpenAI-compatible APIno answer on record
Quantizationno answer on record
Regionsno answer on record
SOC 2no answer on record
Streamingno answer on record
Structured outputno answer on record

A ROW WITH NO ANSWER IS NOT A ROW WITH A “NO” · A VENDOR MAY ANSWER A BLANK ONE, MARKED VENDOR CLAIMED WITH ITS SOURCE · A DOCUMENTED VALUE IS DISPUTED, NOT OVERWRITTEN, AND STAYS VISIBLE WHILE WE RE-READ THE SOURCE

Practitioner reviews

Nobody has written one yet.

A review here is structured, not a star: hardware, scale band, what broke in production, and whether you would choose it again.

NO PERCENTAGE IS SHOWN UNDER FIVE REVIEWS · NO STAR RATINGS, EVER

Also in this category

69 products in Inference APIs. Comparison defaults to within the category — pairing this with a GPU cloud would produce a page that means nothing.

GroqUSED BY 14COMPARE →
ModalUSED BY 14COMPARE →
ReplicateUSED BY 4COMPARE →
Cerebras InferenceUSED BY 3COMPARE →
Fireworks AIUSED BY 1COMPARE →
Alibaba Model StudioNO DEPENDENTS RECORDEDCOMPARE →
Amazon BedrockNO DEPENDENTS RECORDEDCOMPARE →
Arcee AINO DEPENDENTS RECORDEDCOMPARE →

USED BY = LISTED PRODUCTS DEPENDING ON IT, IN THIS DIRECTORY

Frequently asked

How much does Together AI charge for deepseek-ai/DeepSeek-V4.1-Flash?
$0.01 per token-1m-in-cached, read from Together AI's own pricing page on 2026-10-22. 52 rates are listed, each linking to the page it came from.
How current are Together AI's prices here?
These rates were read between 2026-10-14 and 2026-10-27. Nothing older than 21 days is shown: a stale rate is hidden rather than displayed with an old date, and every row links to the page its figure came from.
What does a blank mean on the Together AI page?
That nobody has told us, not that the answer is no. A hollow ring is "no answer on record", which is a different state from a recorded no — and the two look different on purpose. A blank is an absence of evidence, and this page shows how many of its questions are in that state rather than quietly leaving them out.
Where do the Together AI figures come from?
Each one is read from a public page — usually the vendor's own documentation or pricing page — and carries a link to it with the date it was read. Nothing here is estimated, averaged across sources, or inferred from a similar product. If a figure cannot be traced to a page, it is not published.
Can Together AI change what this page says?
They can claim the listing and supply or correct values, which are then labelled as theirs. They cannot remove the page, hide a comparison they are losing, or change a figure somebody else recorded with a source. Nothing on the page is for sale. How the site is paid for is set out under money and independence at /our-data#sec5.
Something here is wrong — how do I fix it?
Dispute the value. Every figure links to the page it was read from, so a dispute names the value and gives a source that contradicts it. That is the only lever anyone has over this page, and it is the same lever for the vendor, a competitor and a reader.
Is this listing run by Together?
No. It is built from public sources, and no value on it came from the company. Its website is on shared hosting, so an email address cannot prove who owns it and there is no claim by address. A correction with a source can be sent instead. A claim lets the company write the tagline, description and logo, and answer blank questions or add dependencies, each marked as theirs with a source. Prices, licence and OSS figures stay as the directory read them, category changes only through our review, and each can be disputed with a source.

Cite this page

A model that quotes us should quote us correctly. The reading and its date sit inside the citation rather than beside it, because a quotation carrying only a URL goes wrong the week the URL changes.

infratoapp, “Together AI — Inference APIs”, read 26 October 2026. Price $11.00/gpu-hour as published at together.ai. https://www.infratoapp.com/products/together-ai

What Together AI can and cannot change here

Claiming Together lets its admins and editors change the tagline, description, logo, docs link and deployment model of every product that org owns — live, labelled as theirs, and logged. Answers to blank questions and dependencies go live too, marked as the owner’s and sourced; a documented answer cannot be overwritten. Everything else on this page is a stated fact with a dispute route: price, licence and OSS figures. Those columns are ungranted at the database level, so they are not a feature we withheld — they are a write that cannot happen. Name, category, website, pricing page and package names can be changed by the owner only through our review. A dispute never deletes a value; it marks it and publishes the correction.

Together’s website is on shared hosting, so an email address cannot prove who owns it and there is no claim by address. If you maintain it, send a correction with a source.

Maintain Together? Ask us to verify you.