Kimi K2 Instruct

MoonshotReleasedJul 11, 2025KnowledgeJul 2024
Context
131K
Max output
131K
Serving providers
6
Cheapest input
$0.50 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Hugging Face leaderboards
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
SWE-bench Pro28%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.50 to $2.00 per 1M tokens across 6 providers, so the dearest route costs 300% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
DeepInfraCheapest$0.50$2.001
ComponentUnitStandardBatchCached
Text input/1M tok$0.5000
Text output/1M tok$2.00
Novita$0.57$2.301
Fireworks AI$0.60$2.501
Wandb$0.60$2.501
Together AI$1.00$3.001
Hyperbolic$2.00$2.001

Price history

input + output $/1M since we started tracking
Input Output
Input down 50% since first tracked
$0.000$1.00$2.00$3.00Jul 16Jul 21Dec 4Jun 22$2.00$0.500

Cost calculator

estimate your monthly spend on this model
$260
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/moonshotai/Kimi-K2-Instructnovita/moonshotai/kimi-k2-instructfireworks_ai/accounts/fireworks/models/kimi-k2-instructwandb/moonshotai/Kimi-K2-Instructtogether_ai/moonshotai/Kimi-K2-Instructhyperbolic/moonshotai/Kimi-K2-Instruct

Frequently asked questions

Kimi K2 Instruct pricing, context and availability

How much does Kimi K2 Instruct cost?

Kimi K2 Instruct costs $0.50 per 1M input tokens and $2.00 per 1M output tokens at its cheapest provider via DeepInfra. Across 6 serving providers, input prices range from $0.50 to $2.00 per 1M tokens.

What is the context window of Kimi K2 Instruct?

Kimi K2 Instruct accepts up to 131K tokens of context and can return up to 131K output tokens.

Which providers serve Kimi K2 Instruct?

Kimi K2 Instruct is available from 6 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.

What can Kimi K2 Instruct do?

Kimi K2 Instruct supports tool use and structured output.

Other Moonshot models

compare pricing across the Moonshot lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI