Kimi K3 vs Inkling
Pick a route and service tier under each model. Prices, the calculator and the verdicts follow your choice.
At a glance
Generated from the rows below
Choose Kimi K3 for
- The highest Epoch Capabilities Index (158.3)
- The largest context window: 1,048,576 tokens
- The only one that takes video
Choose Inkling for
- The lowest cost per typical request ($0.004)
- The only one that takes audio
Overview
Pricing
Prices on the route and tier chosen under each model
What will it cost?
Estimate a month of requests on the route and tier chosen for each model
Uses the route and tier chosen under each model, over 30 days. Cached input is billed at the cache-read rate.
Performance
Live gateway traffic
Activity
Tokens sent through Phaseo each day over the last 30 days
None of these models has had traffic through Phaseo in the last 30 days.
Features
Features from the parameters Phaseo routes support
Benchmarks
Only results that two or more of the selected models report get a row
Epoch Capabilities Index Independent
Higher is better · dot is the estimate, band is the 95% confidence interval · Epoch AI, CC BY 4.0
Artificial Analysis Intelligence Index Independent
Higher is better · at Max effort · 1 of 2 models tested
Where they rank
The five leaders on each capability index, then the compared models. Each model at its best-scoring setting.
Artificial Analysis Intelligence Index42 models ranked
- #1Claude Opus 5.558.4
- #2GPT-6 Astra56.9
- #3GPT-6.1 Sol54.5
- #4Claude Sonnet 5.554.2
- #5GPT-6.1 Terra51.0
- #32Kimi K317.4
- #35Inkling12.5
Artificial Analysis Coding Index171 models ranked
- #1Claude Fable 5.181.6
- #2GPT 5.6 Sol78.3
- #3Claude Opus 578.0
- #4GPT-6 Astra77.1
- #5Grok 4.676.8
- #10Kimi K376.2
- #58Inkling52.1
Artificial Analysis Agentic Index112 models ranked
- #1Claude Fable 5.157.9
- #2Claude Opus 556.5
- #3Qwen 3.8 Max 090256.0
- #4Muse Spark 1.355.5
- #5Qwen 3.8 Flash Next53.6
- #13Kimi K350.0
- #44Inkling22.5
Epoch Capabilities Index164 models ranked
- #1GPT-6 Astra169.1
- #2Claude Opus 5.5168.4
- #3GPT-6.1 Terra168.1
- #4GPT-6.1 Sol167.8
- #5Claude Sonnet 5.5166.7
- #19Kimi K3158.3
- #66Inkling148.5
Lab-reported results come from each lab’s own launch materials and may use different settings. Independent results come from third-party evaluators.
Providers
Routes Phaseo serves today, standard-tier prices per 1M tokens
| Provider | Input | Output | Cache read | Context window | Max output | Tiers |
|---|---|---|---|---|---|---|
 | $1.44 | $9.00 | $0.30 | 1,048,576 | – | Standard |
| $1.44 | $9.00 | $0.30 | 1,048,576 | – | Standard | |
 | $2.70 | $13.50 | $0.27 | 1,048,576 | 1,048,576 | Standard |
 | $2.50 | $14.00 | $0.29 | 1,048,576 | 1,048,576 | Standard |
 | $2.85 | $14.25 | $0.285 | 1,048,576 | – | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | 1,048,576 | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | – | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | 1,048,576 | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | 262,144 | Standard |
 | $3.00 | $15.00 | $0.30 | 1,000,000 | 1,000,000 | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | – | Standard, Batch, Flex |
 | $3.00 | $15.00 | – | 1,048,576 | 131,072 | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | – | Standard, Priority |
 | $3.00 | $15.00 | $0.30 | 262,144 | – | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | 1,048,576 | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | – | Standard |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | 1,048,576 | Standard |
| $3.00 | $15.00 | $0.75 | 1,000,000 | – | Standard | |
 | $3.00 | $15.00 | $0.30 | 1,048,576 | – | Standard |
 | $3.06 | $15.30 | $1.53 | 1,048,576 | – | Standard |
 | – | – | – | 1,000,000 | 131,072 | Priority |
- Wafer
- Input
- $1.44
- Output
- $9.00
- Context window
- 1,048,576
Standard
- Wafer (ZDR)
- Input
- $1.44
- Output
- $9.00
- Context window
- 1,048,576
Standard
- SiliconFlow
- Input
- $2.70
- Output
- $13.50
- Context window
- 1,048,576
Standard
- Morph
- Input
- $2.50
- Output
- $14.00
- Context window
- 1,048,576
Standard
- DeepInfra
- Input
- $2.85
- Output
- $14.25
- Context window
- 1,048,576
Standard
- Moonshot AI
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- Arcee AI
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- AtlasCloud
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- Baseten
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- Canopy Wave
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,000,000
Standard
- Doubleword
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard, Batch, Flex
- EmpirioLabs AI
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- Fireworks
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard, Priority
- GMICloud
- Input
- $3.00
- Output
- $15.00
- Context window
- 262,144
Standard
- Inference.net
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- Nebius Token Factory
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- NovitaAI
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- TensorX
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,000,000
Standard
- Together
- Input
- $3.00
- Output
- $15.00
- Context window
- 1,048,576
Standard
- IO.net
- Input
- $3.06
- Output
- $15.30
- Context window
- 1,048,576
Standard
- Venice
- Input
- –
- Output
- –
- Context window
- 1,000,000
Priority
Standard-tier prices. The first row is the cheapest route; pick another under the model’s name at the top.
Also listed, not routed by Phaseo: 31 providers
Abacus, AkashML, Berget.AI, Chutes, Cloudflare, CoreWeave Forge, CrofAI, CrossModel, DigitalOcean, FastRouter, Hugging Face, Inference, Kilo Gateway, Modal, Moonshot AI Turbo, NanoGPT, Neuralwatt, NVIDIA, OpenRouter, OrcaRouter, Parasail, Perplexity Agent, Phala, Pioneer, Relace, Requesty, Sail Research, Tencent Cloud, Venice (E2EE), Vercel AI Gateway, ZenMux
Shown for reference: other gateways’ listings and routes Phaseo has retired or disabled.
Details
Kimi K3 vs Inkling: side-by-side summary
Kimi K3 and Inkling are both available through the Phaseo API, so switching between them is a change of model id rather than a new integration.
Kimi K3 is from Moonshot. It has a 1,048,576-token context window. On its cheapest route it costs $1.44 per 1M input tokens and $9.00 per 1M output tokens.
Inkling is from Thinking Machines Lab. It has a 1,000,000-token context window. On its cheapest route it costs $1.00 per 1M input tokens and $4.05 per 1M output tokens.
Kimi K3 model details, providers and pricingInkling model details, providers and pricing
Kimi K3 vs Inkling at a glance
| Attribute | Kimi K3 | Inkling |
|---|---|---|
| Lab | Moonshot | Thinking Machines Lab |
| Input price per 1M tokens | $1.44 | $1.00 |
| Output price per 1M tokens | $9.00 | $4.05 |
| Context window | 1,048,576 tokens | 1,000,000 tokens |
| Max output | 1,048,576 tokens | 65,536 tokens |
| Artificial Analysis Intelligence Index | 17.4 (#32) | 12.5 (#35) |
Prices are each model's cheapest standard route on Phaseo. Benchmark ranks use each model's best-scoring evaluated setting.
Frequently asked questions
Which is cheaper, Kimi K3 or Inkling?
Inkling is cheaper for both input and output tokens. Kimi K3 costs $1.44 per 1M input tokens and $9.00 per 1M output tokens; Inkling costs $1.00 and $4.05, each on its cheapest standard route on Phaseo.
Which has the longer context window, Kimi K3 or Inkling?
Kimi K3 has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for Inkling.
Which scores higher on the Artificial Analysis Intelligence Index, Kimi K3 or Inkling?
Kimi K3 scores higher on the Artificial Analysis Intelligence Index. Kimi K3 scores 17.4, ranked #32 of 42. Inkling scores 12.5, ranked #35 of 42.
Can I use Kimi K3 and Inkling through one API?
Yes. Both are served through the Phaseo API, so you can switch between them by changing the model id.