kimi-k3

Explore kimi-k3: model specifications, capabilities, benchmark results, platform pricing and original sources.

cheaperInference/kimi-k3

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
1000000
Max output · tokens
1048576
Capabilities
multimodal, reasoning, structuredOutputs, toolCalling, visionInput

Published prices

1–5 / 5

kimi-k3 ↗

$0.19

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cached input tokens (per 1M)

kimi-k3 ↗

$3.83

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_write_1h_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cache write, 1 hour (per 1M)

kimi-k3 ↗

$1.92

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
cache_write_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Cache write, 5 minutes (per 1M)

kimi-k3 ↗

$1.92

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
input_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Input tokens (per 1M)

kimi-k3 ↗

$9.58

Inference provider
cheaperInference
Platform
Cheaper Inference
Unit
output_tokens_per_million
Currency
USD
Billing conditions
zdr
false
protocol
chat_completions
service_tier
standard
Billing label
Output tokens (per 1M)

Provider specifications & access

1–1 / 1

kimi-k3 ↗

source model id
kimi-k3
hosting
gateway
platforms
  • Cheaper Inference
context length
1000000
max output tokens
1048576
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities
  • reasoning
  • structuredOutputs
  • toolCalling
  • visionInput

Original sources

1–1 / 1

api.cheaperinference.com · Source snapshot ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace