Kimi K3 API pricing
Live per-token API pricing across providers, synced from OpenRouter. Compare input, output, and cache-read rates, throughput, latency, and uptime in one place - then estimate what your workload actually costs.
Refreshed about 13 hours ago via OpenRouter - some pricing may be stale.
Relace - $0.57/M input, $13.00/M output , $0.300/M cache
Per 1M tokens, USD. Verify on the provider's site before committing.
Per-provider pricing
Live per-provider pricing, throughput and uptime - refreshed about 13 hours ago via OpenRouter. Click a column to sort.
some pricing may be stale - last verified 2026-10-09
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
Relace
|
API | 0.57 | 13.00 | 0.300 | - | - | 100.00% | best uptime |
|
Sail Research
|
API | 0.84 | 13.50 | 0.300 | - | - | 100.00% | |
|
AkashML
|
API | 1.20 | 14.00 | 1.200 | - | - | 100.00% | |
|
Makora
|
API | 1.53 | 12.75 | 0.204 | - | - | 100.00% | |
|
Morph
|
API | 1.61 | 14.00 | 0.290 | - | - | 100.00% | |
|
Decart
|
API | 1.95 | 9.75 | 0.195 | - | - | 100.00% | |
|
Nous Portal
stale
|
API | 2.40 | 12.00 | - | - | - | - | |
|
DigitalOcean
|
API | 2.55 | 12.95 | 0.255 | - | - | 100.00% | |
|
Phala
|
API | 2.55 | 12.75 | 0.255 | - | - | 100.00% | |
|
Together
|
API | 2.70 | 13.50 | 0.270 | - | - | 100.00% | |
|
Wafer
|
API | 2.80 | 14.00 | 0.300 | - | - | 100.00% | |
|
DeepInfra
|
API | 2.85 | 14.25 | 0.285 | - | - | 100.00% | |
|
DigitalOcean
stale
|
API | 2.85 | 14.25 | 0.285 | - | - | - | |
|
InferenceNet
|
API | 2.99 | 15.00 | 0.450 | - | - | 100.00% | |
|
BaseTen
|
API | 3.00 | 15.00 | 0.300 | - | - | 100.00% | |
|
Ollama Cloud
stale
Not included in the Ollama Cloud flat subscription. Billed per-token from a separate metered 'extra usage' balance - a 402 'extra usage balance is empty' response means you must add funds or enable auto-reload at ollama.com/settings.
|
API | 3.00 | 15.00 | 0.300 | - | - | - | |
| API | 3.00 | 15.00 | 0.300 | - | - | 100.00% | ||
|
Moonshot AI
|
API | 3.00 | 15.00 | 0.300 | - | - | 100.00% | |
|
Parasail
|
API | 3.00 | 15.00 | 0.300 | - | - | 100.00% | |
|
Amazon Bedrock
|
API | 3.00 | 15.00 | 0.300 | - | - | 100.00% | |
|
Alibaba
|
API | 3.45 | 17.25 | 0.345 | - | - | 100.00% | |
|
Fireworks
risky
|
API | 4.50 | 22.50 | 0.450 | - | - | 92.59% | |
|
Chutes
avoid
|
API | 3.00 | 15.00 | 0.300 | - | - | 74.36% | |
| Sub | - | - | - | - | - | - | $10.00/mo Go ($5 first month) | |
| Sub | - | - | - | - | - | - | $20.00/mo Pro | |
| Sub | - | - | - | - | - | - | $100.00/mo Max |
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
Get this data as JSON
Same provider table, machine-readable. No auth, no rate limit beyond the edge cache.
curl -s https://tokenstead.ai/models/kimi-k3/pricing.json
JSON: model metadata, cheapest_api, providers[], subscriptions[], verified_at. Unit is USD per 1M tokens.
Estimate what Kimi K3 costs for your workload
Paste your prompt, set requests/day, and see monthly cost against self-hosting on your own GPU.
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.