Kimi K3 (Low)
Context 1M tokens
Top 5 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Relacevia OpenRouter — Price via OpenRouter: OpenRouter's price for Relace's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Relace's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | $0.182 | $9.34 | |
| 2 | Wafervia OpenRouter — Price via OpenRouter: OpenRouter's price for Wafer's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Wafer's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | $0.276 | $9.60 | |
| 3 | Sail Researchvia OpenRouter — Price via OpenRouter: OpenRouter's price for Sail Research's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Sail Research's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | $0.224 | $10.72 | |
| 4 | Makoravia OpenRouter — Price via OpenRouter: OpenRouter's price for Makora's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Makora's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | $0.500 | $13.00 | |
| 5 | InferenceNetvia OpenRouter — Price via OpenRouter: OpenRouter's price for InferenceNet's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for InferenceNet's endpoint (https://openrouter.ai/moonshotai/kimi-k3/providers), collected 2026-11-03. | $0.234 | $16.50 |
Composite
6 of 7 inputs · 4 from the model family6 radar axes: DesignArena's two boards share one68.0
includes −2.9 for its Benchmaxxing signal (from 70.8; why, switch off in Options)
AA Coding v4.x 72.0Coding Agent v1.4 —AA Intelligence 17.4AA Agentic —Epoch ECI 158.3Software ECI 160.8DesignArena 1282/1315
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
19 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
- Software ECI · attached
- DesignArena Web Apps (agentic) · attached
- DesignArena Full-Stack · attached
Agentic
AA-Briefcase53987 Elo
AA-Briefcase published 2026-09-10 → · Published board — Tests multi-week professional knowledge-work projects with linked tasks and large source collections.
GDPval-AA v2651,196 Elo
GDPval-AA v2 v2 → · Published board — Tests professional knowledge-work deliverables across occupations using AA's Stirrup harness.
Terminal-Bench v2.1 (AA)8582.4%
Terminal-Bench v2.1 (AA) v2.1 → · Published board — Tests terminal-based work on the 89-task verified refresh using Terminus 2.
Coding
SciCode (AA subproblems) v1.0.16852.7%
SciCode (AA subproblems) v1.0.1 → · Published board — Tests scientific Python programming with scientist-annotated background information.
AA Coding Index v4.x · frozen 2026-10-278572.0
AA Coding Index v4.x · frozen 2026-10-27 → · Published board — Artificial Analysis withdrew the Coding Index with Intelligence Index v5.0 (2026-10-28). These are the last v4.x values, frozen with their own date (2026-10-27).
Knowledge
Humanity's Last Exam (AA text-only)7525.0%
Humanity's Last Exam (AA text-only) published 2026-09-10 → · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index843.92
AA-Omniscience Index published 2026-09-10 → · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
Long-context
GDP.pdf (AA)7318.6%
GDP.pdf (AA) published 2026-09-10 → · Published board — Tests professional reasoning over long PDFs with AA document preparation and grading.
AA-LCR v1.18579.3%
AA-LCR v1.1 v1.1 → · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Context Arena — MRCR v2 (8-needle)2660.0%
Context Arena — MRCR v2 (8-needle) 8-needle → · Published board — The model must find and reproduce the right one of eight near-identical earlier replies hidden in a long conversation, averaged over context lengths from 8k to 128k tokens.
Reasoning
ARC-AGI-11165.7%
ARC-AGI-1 v1 → · Published board — The first-generation ARC-AGI benchmark measuring passive fluid intelligence, with leaderboard score plotted against cost-per-task.
ARC-AGI-2712.4%
ARC-AGI-2 v2 → · Published board — The second-generation ARC-AGI benchmark of passive fluid intelligence, with leaderboard score plotted against cost-per-task.
Chess Puzzles (Epoch AI)3620.0%
Chess Puzzles (Epoch AI) published 2026-09-18 → · Published board — Best-move selection on 100 novel chess positions generated programmatically by Epoch AI, each with a single Stockfish-verified best move; probes spatial reasoning and planning.
Mystery Game Puzzles (Epoch AI)1212.0%
Mystery Game Puzzles (Epoch AI) published 2026-09-18 → · Published board — Best-move selection on 100 mid-game positions of a well-known game whose identity Epoch deliberately keeps undisclosed, generated programmatically like Chess Puzzles.
AA Intelligence Index v5.0 · snapshot-2026-11-031717.4
AA Intelligence Index v5.0 · snapshot-2026-11-03 → · Published board — Artificial Analysis Intelligence Index v5.0. Models AA has not rescored on v5.0 are listed as estimates from their frozen v4.x value (isotonic fit over the models measured on both versions), never as measurements.
Science
CritPt (AA)733.1%
CritPt (AA) published 2026-09-10 → · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)7684.2%
GPQA Diamond (AA) published 2026-09-10 → · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (Epoch AI run)3984.8%
GPQA Diamond (Epoch AI run) published 2026-09-18 → · Published board — Epoch AI's own inspect-ai runs of GPQA Diamond, the 198-question graduate-level science multiple-choice set.
Tool-use
AutomationBench-AA v1.0.66849.3%
AutomationBench-AA v1.0.6 → · Published board — Tests multi-app SaaS workflows through REST tools on a held-out AutomationBench split.
τ³-Banking (AA) v1.0.18841.6%
τ³-Banking (AA) v1.0.1 → · Published board — Tests banking support agents that retrieve policies and change account state through tools.
Vision
MMMU Pro (AA)7878.5%
MMMU Pro (AA) published 2026-09-10 → · Published board — Tests multimodal understanding using challenging ten-option questions.
Missing coverage · 300 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Variants / reasoning settings
Artificial Analysis snapshot 2026-11-03 · Intelligence Index v5.0 (est. = estimated from v4, not measured) · Coding Index v4.x frozen 2026-10-27 · Data: Artificial Analysis · Data: Epoch AI (CC BY)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| Kimi K3 (Max) | 76.2 | 33.4est. |
| Kimi K3 (Low) | 72.0 | 17.4 |
| Kimi K3 | — | — |
SUBSCRIPTION PLAN
GitHub Copilot
Current usage-based billing · model token cost is converted to AI Credits at 1 credit = $0.01.
Token offers by platform · 34 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
34 offers within the active global filters, 1 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
OpenRouter (29)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/moonshotai/kimi-k3/providers, collected 2026-11-03.
| Relace | globalrelace/fp4 | $0.182 raw in $/1M | $9.34 raw out $/1M | |
| Wafer | globalwafer/us | $0.276 raw in $/1M | $9.60 raw out $/1M | |
| Sail Research | globalsail-research/fp4/us | $0.224 raw in $/1M | $10.72 raw out $/1M | |
| Sail Research | globalsail-research/fp4 | $0.224 raw in $/1M | $10.72 raw out $/1M | |
| Wafer | globalwafer | $0.192 raw in $/1M | $15.00 raw out $/1M | |
| Makora | globalmakora/fp4 | $0.500 raw in $/1M | $13.00 raw out $/1M | |
| InferenceNet | globalinference-net/us | $0.234 raw in $/1M | $16.50 raw out $/1M | |
| InferenceNet | globalinference-net/fp4 | $0.234 raw in $/1M | $16.50 raw out $/1M | |
| ParetoAlpha | globalpareto-alpha/us | $1.00 raw in $/1M | $11.25 raw out $/1M | |
| Wafer | globalwafer/fast | $0.171 raw in $/1M | $22.00 raw out $/1M | |
| Chutes | globalchutes/mxfp4 | $1.85 raw in $/1M | $9.50 raw out $/1M | |
| Decart | globaldecart/mxfp4 | $1.95 raw in $/1M | $9.75 raw out $/1M | |
| Morph | globalmorph/fp8 | $1.42 raw in $/1M | $12.00 raw out $/1M | |
| InferenceNet | globalinference-net/us/fast | $0.500 raw in $/1M | $22.00 raw out $/1M | |
| InferenceNet | globalinference-net/fast | $0.500 raw in $/1M | $22.00 raw out $/1M | |
| Phala | globalphalaTEE | $2.55 raw in $/1M | $12.75 raw out $/1M | |
| DigitalOcean | globaldigitalocean | $2.55 raw in $/1M | $12.95 raw out $/1M | |
| AkashML | globalakashml/fp4 | $1.20 raw in $/1M | $14.00 raw out $/1M | |
| DeepInfra | globaldeepinfra/mxfp4 | $2.85 raw in $/1M | $14.25 raw out $/1M | |
| Parasail | globalparasail/fp4 | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Modal | globalmodal/mxfp4 | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Together | globaltogether | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Fireworks | globalfireworks | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| BaseTen | globalbaseten/fp8 | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Moonshot AI | globalmoonshotai | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Amazon Bedrock | globalamazon-bedrock/us-east-2 | $3.00 raw in $/1M | $15.00 raw out $/1M | |
| Fireworks | globalfireworks/us | $4.50 raw in $/1M | $22.50 raw out $/1M | |
| Fireworks | globalfireworks/fast | $4.50 raw in $/1M | $22.50 raw out $/1M | |
| Fireworks | globalfireworks/spot | $2.10 raw in $/1M | $10.50 raw out $/1M |
Chutes (1)
Direct prices from Chutes's own price list. Source: llm.chutes.ai/v1/models, collected 2026-11-03.
| Chutes | globalTEE | $1.85 raw in $/1M | $9.50 raw out $/1M |
TensorX (1)
Direct prices from TensorX's own price list. Source: tensorx.ai/pricing/, collected 2026-11-03.
| TensorX | euEU | $3.00 raw in $/1M | $15.00 raw out $/1M |
Nebius (1)
Direct prices from Nebius's own price list. Source: tokenfactory.nebius.com/models, collected 2026-11-03.
| Nebius | euEU | $3.00 raw in $/1M | $15.00 raw out $/1M |
Azure AI Foundry (2)
Direct prices from Azure AI Foundry's own price list. Source: prices.azure.com/api/retail/prices, collected 2026-11-03.
| Azure AI Foundry | us | $3.30 raw in $/1M | $16.50 raw out $/1M | |
| Azure AI Foundry | usfireworks | $3.30 raw in $/1M | $16.50 raw out $/1M |