Kimi K2 API prices across providers
Identical open weights, different invoices. All prices USD per 1M tokens, verified against provider sources. Last full sweep:
| Provider | In $/M | Out $/M | Spread vs cheapest | Context | tok/s | Last verified | Go link |
|---|---|---|---|---|---|---|---|
| Hyperbolic | 0.55 | 2.5 | 1.00× cheapest | 131k | — | Go ↗ |
Cache-hit pricing excluded — model your real mix in the Cost Calculator (ships week 2). Spread = output price ÷ cheapest output price.
Measured floor: Hyperbolic at $2.5/M out. Widest spread on this model today: 1.00×.
What a month costs
Worked examples at this model's verified prices (2026-08-23 sweep); cache-hit discounts excluded.
| Monthly workload | Novita AI | DeepInfra | Together | OpenRouter |
|---|---|---|---|---|
| Light — 1M in / 0.25M out | $1.15 | $1.22 | $1.28 | $1.33 |
| Mid — 10M in / 2M out | $10.2 | $10.9 | $11.36 | $11.86 |
| Heavy — 50M in / 10M out | $51 | $54.5 | $56.8 | $59.3 |
Related
Head-to-heads: DeepSeek R1 · GPT-OSS 120B
Also tracked: DeepSeek V3.x · DeepSeek R1 · Qwen3 235B · Qwen3 Coder · Llama 4 Maverick · GLM 4.7 · GPT-OSS 120B · Gemma 3 27B · MiniMax M3
How we verify
- Pull — provider pricing pages and /models endpoints, daily at 06:00 UTC.
- Probe — fixed 1k-in/256-out prompt per provider; billed tokens and latency recorded.
- Diff — changes beyond ±1% raise a price move; every row carries its own last-verified date, never a site-wide stamp.
- Disclose — affiliate Go links are labeled and never reorder this table; methodology and raw probes are published.
Freshness policy: rows older than 14 days carry the amber stale flag until re-probed. Stale data beats fresh guesses.
Spot a wrong number? File a correction — we re-probe within one sweep cycle.