Kimi K2 0905 APIOPEN WEIGHTS262K context
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2).
Pricing & specs mirror our live pricing as of July 2026 (pay-as-you-go).
What is Kimi K2 0905?
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...
Kimi K2 0905 on the release timeline
Kimi K2 0905 pricing
Pay-as-you-go on DataLLM Lab — these are our live list prices (identical to the pricing page):
| Model | Input / 1M | Output / 1M | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| Kimi K2 0905 | $0.60 | $2.50 | — | — | 262K |
On output price, Kimi K2 0905 is cheaper than 36% of the 309 models in the catalog. It is served by 2 providers; the best combined rate at our last snapshot was ≈ $0.60 / $2.50 per 1M via Novita, with upstream quantizations fp8.
What Kimi K2 0905 costs per month
| Workload | Tokens in / out (monthly) | Est. cost |
|---|---|---|
| Support chatbot | 40M / 12M | $54.00 |
| RAG / knowledge base | 200M / 20M | $170 |
| Coding agent | 80M / 25M | $111 |
| Batch extraction | 150M / 8M | $110 |
| Content generation | 20M / 40M | $112 |
Estimate your own monthly cost
Cost = input price × input volume + output price × output volume. The same five workloads run on every model page, so any two compare directly.
Kimi K2 0905 vs alternatives
| Model | Input / 1M | Output / 1M | Context | Our test |
|---|---|---|---|---|
| Kimi K2 0905 | $0.60 | $2.50 | 262K | — |
| Kimi K2 Thinking | $0.60 | $2.50 | 262K | — |
| Kimi K2 0711 | $0.57 | $2.30 | 131K | — |
| Kimi K2.5 | $0.38 | $2.02 | 262K | — |
| Nova 2 Lite | $0.30 | $2.50 | 1M | — |
| R1 | $0.70 | $2.50 | 164K | — |
Specs
| Model ID | moonshotai/kimi-k2-0905 |
| Modality | text->text (input: text) |
| Context window | 262,144 tokens |
| Max output | 100,352 tokens |
| Tool / function calling | ✅ Yes |
| Structured output (JSON) | ✅ Yes |
| Released | 2025-09-04 |
| Knowledge cutoff | 2024-12-31 |
| Open weights | ✅ moonshotai/Kimi-K2-Instruct-0905 · 1.5M downloads / 761 likes (30d) |
How to call Kimi K2 0905
from openai import OpenAI
client = OpenAI(base_url="https://api.datallmlab.com/v1", api_key="YOUR_DATALLM_LAB_KEY")
resp = client.chat.completions.create(
model="moonshotai/kimi-k2-0905",
messages=[{"role": "user", "content": "Hello"}],
# supports tools=[...] and tool_choice
)
print(resp.choices[0].message.content)curl https://api.datallmlab.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moonshotai/kimi-k2-0905","messages":[{"role":"user","content":"Hello"}]}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.datallmlab.com/v1", apiKey: process.env.DATALLM_KEY });
const r = await client.chat.completions.create({
model: "moonshotai/kimi-k2-0905",
messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);The same key routes Kimi K2 0905 and 300+ other models — switch models by changing one string. How OpenAI-compatible APIs work.
Prompting tips for Kimi K2 0905
- Be explicit and show the shape of the answer. Spell out format, tone and constraints up front, and include one short example of the output you want — Kimi K2 0905 follows concrete instructions better than abstract ones.
- Huge 262K context — but anchor the ask. You can paste whole documents or codebases; models attend most to the start and end, so put the key instruction at the top and restate it after long inputs.
- Give it real tools. Pass a
tools=[...]schema instead of asking it to "pretend" — let Kimi K2 0905 emit tool calls, execute them, and feed results back for the next turn. - Constrain JSON with a schema. Use
response_format/ structured outputs rather than "reply in JSON" to get valid, parseable objects every time.
Tips are derived from Kimi K2 0905's actual capabilities — context window, tool & JSON support, modality and price tier — not generic advice.
Open-source tools for Kimi K2 0905
Popular open-source projects for running and building with Kimi K2 0905 — star counts pulled from GitHub (July 2026).
Listed by GitHub stars; inclusion is by ecosystem relevance (inference engines, agent frameworks and SDKs), not affiliation. Stars change — see each repo for current numbers.
Migrating to Kimi K2 0905
Coming from OpenAI or another gateway? On an OpenAI-compatible setup the only changes are base_url → https://api.datallmlab.com/v1 and model → moonshotai/kimi-k2-0905. Messages, streaming, tool calls and the rest of your code stay the same. Routing & failover guide.
Self-host or use the API?
Kimi K2 0905 ships open weights (moonshotai/Kimi-K2-Instruct-0905, ~1.5M downloads and 761 likes in the last 30 days), with community quantizations (fp8) for smaller GPUs, so you can run it yourself. Most teams still use the API: no GPU to provision or keep warm, no inference ops, and instant access across 2 providers with automatic failover. Self-host when data residency or fixed per-token economics matter most.
Rate limits & reliability
Rate limits here are the DataLLM Lab gateway's, not the upstream vendor's. On 429 (rate limited) or 503 (provider busy), retry with exponential backoff; because Kimi K2 0905 is served by 2 providers, requests can fail over to a healthy one automatically. See the error-code guide and failover setup.
Related reading
Call Kimi K2 0905 with one key
300+ models behind one OpenAI-compatible endpoint — better prices, better uptime, no subscriptions.
Get an API keyCompare pricingFrequently asked questions
What is Kimi K2 0905?
Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It accepts text input with a 262K-token context window and was released on 2025-09-04. On DataLLM Lab it is callable through one OpenAI-compatible endpoint.
How much does Kimi K2 0905 cost?
On DataLLM Lab it is $0.60 per 1M input tokens and $2.50 per 1M output tokens — cheaper than about 36% of the 309-model catalog on output price. Pay-as-you-go, no subscription.
What is the context window of Kimi K2 0905?
262K tokens, with up to 100K max output tokens.
Is Kimi K2 0905 open source?
Yes — open weights are published on Hugging Face (moonshotai/Kimi-K2-Instruct-0905), with about 1.5M downloads and 761 likes in the last 30 days. You can self-host it or call it via DataLLM Lab.
How do I call the Kimi K2 0905 API?
Point any OpenAI SDK at https://api.datallmlab.com/v1 and set model to "moonshotai/kimi-k2-0905". One DataLLM Lab key routes this model and 300+ others; no code changes beyond the base URL and model string.
What are good alternatives to Kimi K2 0905?
Close options by price and capability include Kimi K2 Thinking, Kimi K2 0711, Kimi K2.5 — all callable with the same DataLLM Lab key.