Kimi K2 Instruct 0905 API pricing
Updated
Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 tie for the lowest blended standard price for Kimi K2 Instruct 0905; Featherless charges USD 0.60 per 1M input tokens and USD 2.50 per 1M output tokens. The median across 2 standard prices is USD 0.60 / USD 2.50. Each price is read from the provider's own pricing page.
Does Moonshot AI sell Kimi K2 Instruct 0905 directly?
Moonshot AI publishes no price for Kimi K2 Instruct 0905 on its own API that we could find, so this page compares hosts only.
Kimi K2 Instruct 0905 model facts
Facts from Moonshot AI's model card for moonshotai/Kimi-K2-Instruct-0905 and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (moonshotai/Kimi-K2-Instruct-0905) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 62 .safetensors files listed” |
| Licence | Custom licence: modified-mit | Moonshot AI model card metadata, checked 2026-11-16Quote“license: other; license_name: modified-mit” |
| Total parameters | 1T | Moonshot AI model card, checked 2026-11-16Quote“Total Parameters | 1T” |
| Active parameters per token | 32B | Moonshot AI model card, checked 2026-11-16Quote“Activated Parameters | 32B” |
| Context length | 256K | Moonshot AI model card, checked 2026-11-16Quote“Context Length | 256K” |
| Tool calling | Yes | Moonshot AI model card, checked 2026-11-16Quote“Kimi-K2-Instruct-0905 has strong tool-calling capabilities.” |
| First published on Hugging Face (not necessarily the release date) | 2025-09-03 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2025-09-03T03:34:36.000Z"” |
Kimi K2 Instruct 0905 price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Featherless tied cheapestmoonshotai/Kimi-K2-Instruct-0905Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). No cached price published. “PRICING: INPUT $0.6 / OUTPUT $2.5” | USD 0.60 | not published | USD 2.50 | USD 1.075 | 32,768 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | Novita AI tied cheapestmoonshotai/kimi-k2-0905Notes and source quote“Kimi K2 Instruct 0905 256K $0.6 /Mt $2.5 /Mt” | USD 0.60 | not published | USD 2.50 | USD 1.075 | 262,144 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Kimi K2 Instruct 0905 cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Featherless | USD 99.00 | USD 181.50 | exceeds context |
| Novita AI | USD 99.00 | USD 181.50 | USD 1,305 |
For the support chatbot, the cheapest price (Featherless and 1 other, tied, USD 99.00 a month) saves USD 0 against the median (USD 99.00). For the coding agent the gap is USD 0 a month.
Which Kimi K2 Instruct 0905 provider is cheapest for your traffic?
Both providers charge the same standard price, USD 0.60 input and USD 2.50 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Featherless (no cache price) | USD 1.075 cheapest | USD 1.075 cheapest | USD 1.075 cheapest |
| Novita AI (no cache price) | USD 1.075 cheapest | USD 1.075 cheapest | USD 1.075 cheapest |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
None of the 2 providers publishes a cached-input discount for Kimi K2 Instruct 0905, so cache hits do not change the ranking.
Context windows differ: 262,144 tokens at Novita AI; 32,768 tokens at Featherless. The cheapest row is not always the one that fits a long prompt.
What does Kimi K2 Instruct 0905 cost in other languages?
The same text needs a different number of tokens in each language. With the Kimi K3 tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Kimi K2 Instruct 0905:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.130 | Featherless |
| Arabic MSA | USD 0.288 | Featherless |
| Hindi | USD 0.341 | Featherless |
| Chinese | USD 0.327 | Featherless |
| Code | USD 0.156 | Featherless |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Estimate your own bill
- LLM API cost calculator with Kimi K2 Instruct 0905 preloaded: your traffic and cache rate, against any of 428 models.
- Kimi token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Kimi K2 Instruct 0905 compare with other Moonshot AI models?
The Moonshot AI models whose cheapest standard price is closest to Kimi K2 Instruct 0905's (USD 1.075 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Kimi K2 Instruct | USD 0.57 | USD 2.30 | 131,072 | 2 |
| Kimi K2.7 Code | USD 0.60 | USD 3 | 262,144 | 12 |
| Kimi K2 Thinking | USD 0.80 | USD 1.20 | 262,144 | 6 |
| Kimi K2.5 | USD 0.45 | USD 2.25 | 262,144 | 8 |
| Kimi K2.6 | USD 0.39 | USD 1.80 | 262,144 | 13 |
| Kimi K3 | USD 1.85 | USD 9.50 | 1,048,576 | 18 |
Priced closest from other makers: Qwen3.5 397B A17B (Qwen, USD 1.087) · GLM 5.3 (Z.ai, USD 1.047) · Qwen3.6 Plus (Qwen, USD 1.125).
Compare Kimi K2 Instruct 0905 with
- GLM 5.3 vs Kimi K2 0905: API price side by side
- Kimi K2 0905 vs Kimi K2: API price side by side
Also compared: vs GLM 5.3 · vs Kimi K2 Instruct.
Every Kimi K2 Instruct 0905 price comparison · All model-vs-model price comparisons
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Kimi K2 Instruct 0905 API cost per token?
From USD 0.60 per 1M input tokens (USD 0.0000006 per token) and USD 2.50 per 1M output tokens (USD 0.0000025 per token) at the lowest standard prices we found. The median of 2 standard prices is USD 0.60 input and USD 2.50 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Kimi K2 Instruct 0905?
Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), 2 are tied for the lowest price: Featherless and Novita AI, each USD 1.075 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.60 (Featherless and 1 other, tied); for output alone, USD 2.50 (Featherless and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Moonshot AI sell Kimi K2 Instruct 0905 on its own API?
Moonshot AI publishes no price for Kimi K2 Instruct 0905 on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Featherless at USD 0.60 / USD 2.50 per 1M tokens.
Does Kimi K2 Instruct 0905 have cached input pricing?
None of the 2 standard prices includes a cached-input price, so budget repeated prompts at the full input price.
What is the Kimi K2 Instruct 0905 context window?
Up to 262,144 tokens. 1 standard price comes with less, down to 32,768 tokens (Featherless). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Kimi K2 Instruct 0905?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 1,305 a month at Featherless, USD 1,305 at the median price and USD 1,305 at Novita AI. Try your own numbers.
Is Kimi K2 Instruct 0905 free to use through an API?
No provider in our data lists a free price for Kimi K2 Instruct 0905 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is Kimi K2 Instruct 0905 open source, with open weights, and what is its licence?
Moonshot AI publishes the weights on Hugging Face as moonshotai/Kimi-K2-Instruct-0905, in a public repository with no access gate. The licence, as the Moonshot AI model card metadata states it: Custom licence: modified-mit. Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Moonshot AI's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.
How many parameters does Kimi K2 Instruct 0905 have?
Total parameters, as the Moonshot AI model card states them: 1T. Active parameters per token: 32B. (checked 2026-11-16; BroadNet did not verify these figures.)
Does Kimi K2 Instruct 0905 support tool calling?
Yes, according to the Moonshot AI model card: “Kimi-K2-Instruct-0905 has strong tool-calling capabilities.” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.