KymaKyma
Moonshot

Moonshot

Kimi K2.5

Kimi K2.5 is a frontier multimodal model optimized for agentic workflows, tool use, and vision tasks. Developers building autonomous agents or complex coding pipelines should use it when they need reliable structured outputs and long-context reasoning.

Modalities

Text+Image → Text

Input

$0.6075 /1M

Output

$3.038 /1M

Context

262K

Speed

medium

Performance

Live production data from real requests on Kyma — not synthetic benchmarks.

Rank

#15

of 87 active models

Tokens served

34.8M

all-time

Success rate

98.9%

last 7 days

Median throughput27 tok/s
Total requests2,301
Platform share1.5%
Tokens · last 15 daysJul 19 → Aug 2

Pricing

Pay per token. Cached input is billed at 10% of the input rate.

$0.6075 /1M input$3.038 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.82/mo
Production1,000 req/day · 2K in / 500 out
~$82.02/mo
Scale20,000 req/day · 2K in / 500 out
~$1,640/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$82.02

$2.73 / day on Kimi K2.5

Same workload on:

Kimi K3$547+567%
Kimi K2.7 Code$132+61%

Estimates use list pricing. Actual bills depend on real token counts — every response includes its exact cost.

When to use Kimi K2.5

Updated 2026-07-31

Where this model earns its cost — and where it doesn't.

Kimi K2.5 is a multimodal language model from Moonshot with a 262,144 token context window. It accepts text and image inputs, outputs text, and includes native support for tool calling, structured outputs, and explicit reasoning traces. It operates in the premium tier and delivers medium inference speed.

On Kyma, the model runs through an OpenAI-compatible endpoint using a single platform API key. Every request receives automatic failover if a serving path degrades, and responses return exact token costs in usage.cost alongside an X-Kyma-Model header. While Kyma bills repeated prompt prefixes at 10% of the input rate, this specific model does not support caching, so all input tokens bill at the full rate. New accounts include a $0.50 free credit with no card required.

The model caps generation at 32,768 output tokens per request. It does not process audio or video inputs, and its medium speed tier makes it unsuitable for strict low-latency requirements. Platform telemetry shows a 99.5% success rate across approximately 34.8 million tokens served.

Autonomous Agent Workflows

Leverages tool calling and structured outputs to coordinate multi-step tasks.

Code Generation and Review

Processes long codebases within its 262K context window for refactoring and debugging.

Image Analysis Pipelines

Extracts structured data and reasoning from uploaded images alongside text prompts.

Complex Chat Applications

Maintains conversational state across extended sessions with reliable reasoning capabilities.

Not ideal for: Do not use this model for high-throughput, low-latency streaming or tasks that require prompt caching to reduce input costs.

How it compares

Against the peers people actually weigh it against.

SpecKimi K2.5Kimi K3Kimi K2.7 Code
Input /1M$0.6075$4.05$1.009
Output /1M$3.038$20.25$4.774
Context262K1M262K
ToolsYesYesYes
ReasoningYesYesYes
Speedmediummediummedium

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit, no card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2.5",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Kimi K2.5?

Kimi K2.5 has a 262K-token context window — roughly 386 pages of text in a single request.

How much does the Kimi K2.5 API cost?

$0.6075 per 1M input tokens and $3.038 per 1M output tokens. No subscription; you pay only for what you use.

Does Kimi K2.5 support function calling?

Yes — Kimi K2.5 supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

How do I use Kimi K2.5?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to kimi-k2.5. Signing up is free and includes $0.50 of credit — no card required.

Does Kimi K2.5 support prompt caching on Kyma?

No. This model does not support caching, so all input tokens bill at the standard rate regardless of repetition.

How do I verify which model actually processed my request?

Check the X-Kyma-Model header in the response, which reports the exact model that ran after any automatic failover routing.

What is the maximum output length per request?

The model caps generation at 32,768 tokens per request.

Start with $0.50 free credit — no card required.Create account →

More models by Moonshot

ModelContextInputOutput
MoonshotKimi K31M$4.05$20.25
MoonshotKimi K2.7 Code262K$1.009$4.774
MoonshotKimi K2.6262K$0.776$3.622