Model index · Text · text generation · reasoning · open weights · MoonshotAI · released 2025-11-06
Kimi K2 Thinking pricing
Served by 5 providers from $0.8525 to $1.07 per 1M tokens on the standard tier — a 1.3× gap for identical weights.
A reasoning model — the headline price is not the whole bill
This model thinks before it answers, and those thinking tokens are billed at the output rate while never appearing in the response. A request can therefore cost several times what the per-1M figure suggests, and the multiplier depends on your prompts rather than on anything we can publish. Compare it against other reasoning models — the alternatives below are ordered to put those first.
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
MoonshotAI · 1058.12B parameters · modified-mit · first published 2025-11-06 · Text model · text generation · 262k context · description as published by the source, not written by us
Open weights: moonshotai/Kimi-K2-Thinking · 1058.12B parameters counted from the weight files · licence modified-mit · 0.0M downloads in the last 30 days . Parameter count and licence come from the public weights registry, not from a seller — and the download figure exists only for models published this way, so it is not a market-wide popularity measure.
$0.8525
Cheapest standard /1M — DeepInfra
262k
Native context window
5
Providers serving it
—
Quality not measured yet
Quality not measured yet
We measure models on request rather than pre-scoring the whole catalog, so this one has no score yet. Absence of a score is not a low score.
At 1M requests/month (1500 in / 500 out tokens), moving from Novita to DeepInfra saves about $445/month.
Illustrative traffic shape, stated so you can check it against your own. Same weights both sides — but confirm quantisation and context below before switching.
Every provider and service tier
Standard on-demand rows first, cheapest of each group first. Tiers are not interchangeable — see the note below the table.
| Provider | In /1M | Out /1M | Blended /1M | Tier | Region | Source |
|---|---|---|---|---|---|---|
| DeepInfra cheapest standard | $0.4700 | $2.00 | $0.8525 | standard | — | provider_api |
| Novita | $0.6000 | $2.50 | $1.07 | standard | — | third_party |
| $0.6000 | $2.50 | $1.07 | standard | — | third_party | |
| OpenRouter (default route) * resells other hosts | $0.6000 | $2.50 | $1.07 | standard | — | provider_api |
| Novita | $0.6000 | $2.50 | $1.07 | standard | — | provider_api |
* OpenRouter chooses a host for each request, and the figure above is what its default choice costs — not a fixed rate for this model. Selecting a specific host through the same account costs whatever that host charges, which is why this row can sit above or below the hosts listed beside it. Token rates are passed through from the underlying provider with no markup, so the per-1M price above is what that host charges directly — OpenRouter's own charge sits on funding instead: 5.5% (min $0.80) by Stripe or 5% by Coinbase to buy credits, 5% of the equivalent spend if you bring your own provider key. So budget about 5% above the rate shown unless you already hold credit. Fee schedule.
Compare Kimi K2 Thinking with alternatives
One model per vendor, ordered by how prominent the vendor is and how many independent providers serve the model — hosts only carry what customers ask for, so that is a real demand signal. This is not traffic or popularity data, which we do not have. Every alternative below does the same job — text generation — because a price comparison between a generator and, say, an upscaler is arithmetic rather than advice. Prices on both sides are standard on-demand rates, so the comparison is like for like — a discounted batch or flex rate is never shown against another model’s standard rate.
| Alternative | Vendor | $/1M | vs Kimi K2 Thinking | Quality | Kind | Context | Hosts |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | DeepSeek | $0.5281 Baidu | 38% cheaper | 100/100 | reasoning open weights | 1.05M | 19 |
| Claude Haiku 4.5 | Anthropic | $2.00 Anthropic | 135% dearer | 60/100 | reasoning | 200k | 8 |
| GPT-5.4 Nano | OpenAI | $0.4625 OpenAI | 46% cheaper | 40/100 | reasoning | 400k | 3 |
| Mistral Small 4 | Mistral | $0.2625 Mistral | 69% cheaper | 40/100 | reasoning | 262k | 2 |
| Qwen3 30B A3B Thinking 2507 | Alibaba | $0.7500 Alibaba | 12% cheaper | not measured | reasoning open weights | 82k | 1 |
| GLM 5.1 | Z.ai | $1.48 StreamLake | 74% dearer | not measured | reasoning open weights | 205k | 18 |
| MiMo-V2.5-Pro | Xiaomi | $0.5438 Xiaomi | 36% cheaper | not measured | reasoning open weights | 1.05M | 7 |
| Nemotron 3 Ultra | NVIDIA | $0.9250 DeepInfra | 9% dearer | not measured | reasoning open weights | 1M | 4 |
Prices are the cheapest host for each model, blended at a 3:1 input:output ratio. "Quality" is our own probe suite where we have run it — see what it measures. A cheaper alternative is only a real saving if it also passes on the capability your workload needs.
5 of these alternatives cost less than Kimi K2 Thinking — the cheapest being Mistral Small 4 at $0.2625 per 1M tokens blended (69% cheaper).
Cheaper is not automatically better: check the quality column, and confirm the context window and capabilities your workload depends on before switching.
Before you switch
Identical weights do not guarantee identical output. Check that the cheaper host serves the model at full precision rather than a quantised copy, that its context window matches what you need, and that its rate limits carry your peak traffic. A cheaper host that cannot take your throughput is not cheaper — it is an outage.
Move to DeepInfra without a rewrite
VernaOne fronts every provider on this page with one API, so switching host is a config change — with automatic fallback if quality or latency regresses.
Try VernaOne free →Frequently asked
How much does Kimi K2 Thinking cost?
The cheapest standard-tier provider is DeepInfra at $0.8525 per 1M tokens blended (3:1 input:output). The dearest is Novita at $1.07 — a 1.3× difference for the same weights. Prices change often; verify with the provider before budgeting.
Which provider is best for Kimi K2 Thinking?
Cheapest is not automatically best. Compare quantisation (a lossy copy of the weights changes output), the context window each host actually serves, and rate limits. Where a provider serves less context than the model's native window we flag it in the table above.
Can I switch providers for Kimi K2 Thinking without changing code?
Yes, if you route through an abstraction. VernaOne exposes one API across every provider listed here, so switching host is a config change and you keep automatic fallback if the new one degrades.
← All models · Generated catalog of AI models and every provider that serves them, with normalised prices in USD per 1,000,000 tokens. Blended prices assume a 3:1 input:output ratio.