Together AI pricing
Kimi K3 (Together AI) pricing
Kimi K3 (Together AI) bills per million tokens, metered separately for input and output. The current rates are below, along with the parts of the bill a per-token estimate leaves out.
Kimi K3 (Together AI) rates in full
All figures are USD per million tokens, taken from Together AI’s own pricing documentation. The API model identifier is moonshotai/Kimi-K3.
| Per million tokens | Standard |
|---|---|
| Input | $3 |
| Cached input read | $0.30 |
| Output | $15 |
Context window: 1M tokens.
What the rate table does not tell you
Kimi K3 is Moonshot AI's flagship model, the first open model in the 3-trillion-parameter class, hosted here on Together AI's serverless tier.
2.8T total parameters, activating 16 of 896 experts per token, with a 1-million-token context window and native vision input.
The same model is also hosted by Fireworks AI at the same headline rate; see its own page for the full table.
A worked monthly example
Take 500,000 calls in a month at 3,000 input tokens and 400 output tokens each. That is 1.5 billion input tokens against 200 million output tokens, so input is 88% of the token volume.
| Line | Tokens | Rate | Cost |
|---|---|---|---|
| Input | 1,500M | $3 | $4,500 |
| Output | 200M | $15 | $3,000 |
| Total | 1,700M | $7,500 |
Output is 12% of the tokens and 40% of the bill. That inversion is why prompt trimming so often fails to move the invoice, and it is the single most common reason a forecast built on Kimi K3 (Together AI) comes in under the real number.
How this page stays current
Most third-party pricing tables are typed in once and quietly rot. This one is generated from a checked figure with the date and source recorded, and it is cross-checked on every deploy against the live model catalog Spendline uses to price real API traffic. If the two disagree, the site fails to build rather than publishing a stale number.
Frequently asked questions
How much does the Kimi K3 (Together AI) API cost?
Kimi K3 (Together AI) is billed per million tokens, metered separately for input and output. As of September 16, 2026 the rate is $3 per million input tokens and $15 per million output tokens, with cached input read at $0.30.
Why is my Kimi K3 (Together AI) bill higher than the per-token estimate?
Most estimates multiply expected tokens by the input rate and stop there. Output is priced at $15 against $3 for input, so responses usually dominate the bill even when prompts look larger. Reasoning tokens bill as output. Retries and agent fan-out pay full input cost for calls that produced nothing. And a cache that gets written but never read is pure overhead rather than a saving.
What is the cheapest way to run Kimi K3 (Together AI)?
Caching a stable prefix takes repeat input to $0.30, 10% of the standard rate, and pays for itself once the cached content is read more often than it is written. The larger lever is usually routing: sending the requests that do not need this tier to a cheaper model, and capping spend per customer before the call goes out.
How do I track Kimi K3 (Together AI) spend per customer or per feature?
The provider invoice is one number for the whole organization, so per-customer cost has to be attributed at the call. That means tagging every request with the customer, team, or agent it belongs to and recording the resolved cost against that tag in a ledger you can close monthly. Spendline does this by sitting in front of the API, which also lets a budget be enforced before the request is forwarded rather than reported after.
Know what this costs per customer, not just per token
A rate card tells you what a token costs. It does not tell you which customer, team, or agent spent it, or stop the one that is running away. Spendline sits in front of the API so every call is attributed and checked against a budget before it is forwarded.
Run the 5 minute assessment