← Model list
Kimi K3
moonshotai·moonshotai/kimi-k3·BETA·Open weights·kimi-k3 series·NEW
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
At a glance
Official price$3.00 / $15.00 per 1M
Cache read $0.30 · Moonshot AI
Lowest paid$2.00 / $8.00
CrofAI Gateway · 2.3× spread
4 more $0 channels
Context1,048,576
⚠ Providers report 262,144–1,048,576; the table below is authoritative
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF
Knowledge cutoff—
Released / updated2026-07-16 / 2026-07-16
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier max
Intelligence59.7
Value17
Coding76.2
Agentic54.3
Output speed38 tok/s
TTFT2.67 s
Cost per task$0.8375
Value formulaIQ 59.7 ÷ min blended $3.500 = 17
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
lowIQ 48.3 · 36 tok/s
maxIQ 59.7 · 38 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 56 providers51 with public prices · 1 free · 3 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Umans AI Coding Plan umans-kimi-k3 | Gateway | Subscription | $0 | $0 | 1,048,576 | 131,072 | ||
| Kenari | Gateway | Free | — | — | 1,048,576 | 131,072 | ||
| SCNet Token Plan Kimi-K3 | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| Kimi For Coding k3 | Gateway | Subscription | $0 | $0 | 1,048,576 | 131,072 | ||
| CrofAI | Gateway | $2.00 | $8.00 | $0.25 | — | 1,000,000 ⚠ | 262,144 | |
| Requesty | Gateway | $2.02 | $10.13 | $0.203 | — | 1,048,576 | 262,144 | |
| NanoGPT | Gateway | $2.50 | $13.50 | $0.25 | — | 1,048,576 | 1,048,576 | |
| ai& | Gateway | $3.00 | $12.50 | $0.50 | — | 1,048,576 | 131,072 | |
| Deep Infra moonshotai/Kimi-K3 | Cloud | $2.85 | $14.25 | $0.285 | — | 1,048,576 | 131,072 | |
| DigitalOcean | Cloud | $2.85 | $14.25 | $0.285 | — | 1,048,576 | 131,072 | |
| Moonshot AIOfficial | First-party | $3.00 | $15.00 | $0.30 | — | 1,048,576 | 131,072 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1CrofAI$590.00
2Requesty$692.55
3NanoGPT$905.00
4ai&$925.00
5Deep Infra$974.70
6DigitalOcean$974.70
11Moonshot AI · Official$1,026.00
4 more channels offer $0 (Umans AI Coding Plan, Kenari, SCNet Token Plan etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to CrofAI to save $436.00/mo (42%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark13 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| DeepSWE | harness: Kimi Code · variant: max effort · v1.1 | 67.5 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Kimi Code · variant: max effort · v2.1 | 88.3 | accuracy | Source ↗ |
| FrontierSWE | harness: Kimi Code · variant: max effort | 81.2 | dominance score | Source ↗ |
| Program Bench | harness: Kimi Code · variant: max effort | 77.8 | score | Source ↗ |
| SWE Marathon | harness: Claude Code · variant: max effort · v1.1 | 42 | resolve rate | Source ↗ |
| GDPval-AA | variant: max effort · vv2 | 1668 | Elo | Source ↗ |
| AA-Briefcase | variant: max effort | 1548 | Elo | Source ↗ |
| AutomationBench | variant: max effort · dataset: 600-task public subset | 30.8 | success rate | Source ↗ |
| JobBench | variant: max effort | 52.9 | score | Source ↗ |
| SpreadsheetBench | harness: Claude Code · variant: max effort · v2 | 34.8 | score | Source ↗ |
| BrowseComp | variant: max effort, context compaction | 91.2 | accuracy | Source ↗ |
| CharXiv Reasoning | variant: max effort, with tools | 91.3 | accuracy | Source ↗ |
| ZeroBench | variant: max effort, with tools | 41 | pass@5 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)effort = loweffort = higheffort = maxeffort = noneeffort = mediumbudget_tokens ≥ 1,024effort = minimaleffort = xhigh
10 / 56 providers expose no reasoning control (reasoning_options: []).
Related models
Kimi K3 Fastsame series$4.50 / $22.50Kimi K3 TEEsame series$3.00 / $15.00Kimi K3 (Fireworks AI)same series$3.00 / $15.00GLM-5.2cheaper alternative$1.40 / $4.40DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended