MoonshotAI: Kimi K2.5

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over app…

moonshotai/kimi-k2.5-0127

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed visual and text tokens, it delivers strong performance in general reasoning, visual coding, and agentic tool-calling.

Specifications & capabilities

Input
text, image
Output
text
Context window · tokens
262144
Knowledge cutoff
2025-01
Published model ID
Kimi-K2.5
Capabilities
multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Description source ↗

Evaluations

21–24 / 24

OpenRouter Benchmarks

84.512%

source id
openRouterBenchmarks
leaderboard name
GPQA Diamond · Accuracy · auto-routing
dimension
knowledge
metric
GPQA Diamond · Accuracy
rank
62
sample size
1188
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
6
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
gpqa_diamond
name
GPQA Diamond
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T16:01:53.650Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
GPQA Diamond · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
1188
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/gpqa-diamond
measurements
accuracy
0.8451178333333333
accuracy_std_dev
0.04928392495671267
cost_per_task_usd
0.09621632239057239
output_tokens_per_task
37856.02356902357
latency_seconds_per_task
1254.4996717171719
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
132
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k2.5-0127
source model id
moonshotai/kimi-k2.5-0127
Original result ↗

OpenRouter Benchmarks

70%

source id
openRouterBenchmarks
leaderboard name
tau2-bench Verified Airline · Accuracy · auto-routing
dimension
agentic
metric
tau2-bench Verified Airline · Accuracy
rank
73
sample size
350
aggregation scope
status
published
harness
url
https://github.com/OpenRouterTeam/benchmark-harness
name
OpenRouter benchmark harness
direction
higherIsBetter
run_count
7
conditions
window
newest 90 days; successful visible nonzero runs
dataset
benchmark-leaderboard
benchmark
id
tau_bench_verified_airline
name
tau2-bench Verified Airline
record_kind
aggregate
provider_name
auto-routing
attribution
Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter.
last_run_at
2026-10-31T22:10:13.617Z
license_url
https://creativecommons.org/licenses/by/4.0/
methodology
Rows aggregate the benchmark-runs dataset exactly as the leaderboard pages do, over each benchmark's non-zero-score runs from the newest 90 days: accuracy is the task-weighted mean of per-run accuracy, accuracy_std_dev is the population standard deviation of per-run accuracy (null with a single run), and the per-task averages divide summed cost, generation time, and output tokens by summed tasks. Rows are ordered by accuracy descending, then model name.
metric_kind
tau2-bench Verified Airline · Accuracy
rank_method
competition rank among reported evaluations in identical conditions, including unlinked observations
sample_size
350
source_file
benchmark-leaderboard.json
source_page
https://openrouter.ai/benchmarks/tau2-bench-airline
measurements
accuracy
0.7
accuracy_std_dev
0.03266000904120248
cost_per_task_usd
0.055787651428571436
output_tokens_per_task
9284.377142857144
latency_seconds_per_task
343.67110285714284
published_at
2026-11-16T01:46:02.653Z
snapshot_date
2026-11-16
source_revision
7ccaf17664252a3053dcb7df8ad0a46e72954a3b4524ddc1c8a7ef8a41b15568
transformations
TensorTrace preserves source results, converts latency to seconds and derives ranks within matching conditions. Individual runs have no derived rank.
metric_population
128
benchmark_evaluation
true
openrouter_permaslug
moonshotai/kimi-k2.5-0127
source model id
moonshotai/kimi-k2.5-0127
Original result ↗

Published prices

1–13 / 13

moonshotai/kimi-k2.5 ↗

$0.15

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

moonshotai/kimi-k2.5 ↗

$0.50

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

moonshotai/kimi-k2.5 ↗

$2.50

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

moonshotai/Kimi-K2.5 ↗

$0.07

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input tokens (per 1M)

moonshotai/Kimi-K2.5 ↗

$0.45

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input tokens (per 1M)

moonshotai/Kimi-K2.5 ↗

$2.25

Inference provider
siliconFlow
Platform
SiliconFlow
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output tokens (per 1M)

moonshotai/kimi-k2.5 ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
bedrock
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
bedrock | moonshotai/kimi-k2.5
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.5 ↗

$3.00

Inference provider
vercelAIGatewayCatalog
Platform
bedrock
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
bedrock | moonshotai/kimi-k2.5
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.5 ↗

$0.10

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | moonshotai/kimi-k2.5
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Cached input / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.5 ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | moonshotai/kimi-k2.5
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.5 ↗

$3.00

Inference provider
vercelAIGatewayCatalog
Platform
novita
Unit
output_tokens_per_million
Currency
USD
Billing conditions
endpoint
novita | moonshotai/kimi-k2.5
model_type
language
billing_scope
via Vercel AI Gateway
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.5 ↗

$0.60

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

moonshotai/kimi-k2.5 ↗

$3.00

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
output_tokens_per_million
Currency
USD
Billing conditions
model_type
language
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Output tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–4 / 4

Kimi K2.5 ↗

source model id
moonshotai.kimi-k2.5
hosting
bedrock-managed
platforms
  • Amazon Bedrock
architecture
input_modalities
  • text
  • image
output_modalities
  • text
capabilities

    Kimi K2.5 ↗

    source model id
    moonshotai/kimi-k2.5
    hosting
    vercel-gateway
    platforms
    • Vercel AI Gateway
    context length
    256000
    max output tokens
    256000
    architecture
    input_modalities
    • text
    • image
    output_modalities
    • text
    capabilities
    • promptCaching
    • reasoning
    • structuredOutputs
    • toolCalling
    • visionInput

    Kimi-K2.5 ↗

    source model id
    moonshotai/Kimi-K2.5
    hosting
    siliconflow-hosted
    platforms
    • SiliconFlow
    max output tokens
    262144
    architecture
    input_modalities
    • text
    • image
    output_modalities
    • text
    capabilities
    • promptCaching
    • reasoning
    • structuredOutputs
    • toolCalling

    Kimi-K2.5 ↗

    source model id
    publishers/moonshotai/models/kimi-k2-5@kimi-k2.5
    hosting
    vertex-self-deployed
    platforms
    • Google Cloud Vertex AI
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      Source specification observations

      1–7 / 7

      openRouter ↗

      field
      context_length
      value
      262144
      normalized value
      262144
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      context_length
      value
      262K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      vercelAIGatewayCatalog ↗

      field
      context_length
      value
      256000
      normalized value
      256000
      scope
      source-model
      source id
      vercelAIGatewayCatalog
      confidence
      1

      vercelAIGatewayCatalog ↗

      field
      knowledge_cutoff
      reported field
      knowledge_cutoff
      value
      2025-01
      normalized value
      2025-01
      precision
      month
      scope
      source-model
      source id
      vercelAIGatewayCatalog
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      235929
      normalized value
      235929
      scope
      source-model
      source id
      openRouter
      confidence
      1

      siliconFlow ↗

      field
      max_output_tokens
      value
      262K
      scope
      source-model
      source id
      siliconFlow
      confidence
      1

      vercelAIGatewayCatalog ↗

      field
      max_output_tokens
      value
      256000
      normalized value
      256000
      scope
      source-model
      source id
      vercelAIGatewayCatalog
      confidence
      1

      Original sources

      1–18 / 18

      SiliconFlow · Model page ↗

      Hugging Face · Model repository ↗

      Google Cloud · Model page ↗

      OpenRouter · Model page ↗

      SiliconFlow · Playground ↗

      Vercel AI Gateway · Model page ↗

      SiliconFlow · API documentation ↗

      arXiv · Model reference ↗

      Amazon Web Services · Model page ↗

      Amazon Bedrock · Model documentation ↗

      Amazon Web Services · Catalog ↗

      Epoch AI · Catalog ↗

      Google Cloud · Catalog ↗

      Hugging Face · Catalog ↗

      OpenRouter · Catalog ↗

      OpenRouter · Catalog ↗

      SiliconFlow · Catalog ↗

      Vercel AI Gateway · Catalog ↗

      Source links

      1–10 / 10

      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