Kimi K2.5
Amazon Bedrock chatKimi K2.5 is an Amazon Bedrock chat model.It supports a 262,144-token context windowwith up to 16,000 output tokens.Input is priced at $0.600/M tokens and output at $3.00/M tokens. Capabilities include function calling, vision, reasoning. Route Kimi K2.5 via Future AGI's Agent Command Center for unified observability, caching, and 15 routing strategies including cost-optimized fallback.
Estimate Kimi K2.5 spend
Pick a workload, fine-tune the sliders, and see the monthly bill.
Estimate uses $0.6000/M input · $3.00/M output. Provider pricing changes. Production costs vary with retries, streaming overhead, and tool-call rounds.
Want this for free? Cache + route via Agent Command Center — first 100K requests and 100K cache hits free every month.
Pricing
Per-token rates, expressed in USD per 1M tokens. Verified Oct 22, 2026.
| Input | $0.600/M | |
| Output | $3.00/M | |
| Blended (3:1 in:out) | $1.20/M Cross-model comparable price |
Context & limits
- Context window
- 262,144 tokens
- Max input
- 262,144 tokens
- Max output
- 16,000 tokens
- Modalities
- vision, video, text
Capabilities
- Function calling ✓ supported
- Parallel tool calls — not advertised
- Vision input ✓ supported
- Audio input — not advertised
- Audio output — not advertised
- PDF input — not advertised
- Streaming ✓ supported
- Structured output ✓ supported
- Prompt caching — not advertised
- Reasoning ✓ supported
Strengths & caveats — when to pick Kimi K2.5
Data-driven from Kimi K2.5's percentile within chat peers.
Where it's strong
- +multi-step reasoning and analysis tasks
- +agentic workflows that depend on reliable tool calls
- +document, chart, and screenshot understanding
Watch out for
- No major caveats flagged from public spec.
Benchmarks pending
We haven't logged public benchmark scores for Kimi K2.5 yet. Have one to contribute? Submit a source — citations help us prioritise.
Call Kimi K2.5 via Agent Command Center
One OpenAI-compatible endpoint. Routing, fallback, semantic caching, guardrails, and cost tracking come along for the ride. First 100K requests + 100K cache hits free every month.
agentcc / @agentcc/client). Per-call metadata — provider, cost, latency, cache hit, request id — is returned on x-agentcc-* response headers, so any HTTP client can read it.# Kimi K2.5 via the Agent Command Center Python SDK
# pip install agentcc
import os
from agentcc import AgentCC
client = AgentCC(
api_key=os.environ["AGENTCC_API_KEY"], # from app.futureagi.com → Settings → API Keys
base_url="https://gateway.futureagi.com/v1",
)
resp = client.chat.completions.create(
model="bedrock/moonshotai-kimi-k2-5",
messages=[{"role": "user", "content": "Hello, Kimi K2.5!"}],
)
print(resp.choices[0].message.content)
print(f"Tokens: {resp.usage.total_tokens}")
# Per-call gateway metadata is returned on x-agentcc-* response headers.
# When you need it programmatically, use .with_raw_response to get them:
raw = client.chat.completions.with_raw_response.create(
model="bedrock/moonshotai-kimi-k2-5",
messages=[{"role": "user", "content": "Same call, but I want the headers."}],
)
print("Provider:", raw.headers.get("x-agentcc-provider"))
print("Latency:", raw.headers.get("x-agentcc-latency-ms"), "ms")
print("Cost: ", raw.headers.get("x-agentcc-cost"), "USD")
print("Cache: ", raw.headers.get("x-agentcc-cache"))AGENTCC_API_KEY with a key fromapp.futureagi.com.Gateway docs ↗Same model on other providers
moonshotai-kimi-k2-5 is also available via 5 other routes. Pricing, regions, and capabilities can differ — compare before routing production traffic.
| Provider | Input / 1M | Output / 1M | Verified |
|---|---|---|---|
| Novita AI | $0.600/M | $3.00/M | Oct 22, 2026 |
| W&B Inference | $0.600/M | $3.00/M | Oct 22, 2026 |
| Together AI | $0.500/M | $2.80/M | Aug 6, 2026 |
| DeepInfra | $0.450/M | $2.25/M | Oct 22, 2026 |
| OpenRouter | $0.600/M | $3.00/M | Aug 6, 2026 |
Explore similar models
Kimi K2.5 doesn't have a public Arena ELO score yet, so we group by provider only — quality-tier comparisons need a benchmark. Side-by-side links appear where a comparison page exists; otherwise, open the model profile.
- DeepSeek v3.2Amazon Bedrock · $0.620/M in · $1.85/M out · 164,000 ctxCompare side-by-side →
- Amazon Nova 2 Lite v1.0Amazon Bedrock · $0.300/M in · $2.50/M out · 1,000,000 ctxCompare side-by-side →
- Amazon Nova 2 Lite v1.0 (Global)Amazon Bedrock · $0.300/M in · $2.50/M out · 1,000,000 ctxCompare side-by-side →
- Amazon Nova 2 Lite v1.0 (JP)Amazon Bedrock · $0.396/M in · $3.31/M out · 1,000,000 ctxCompare side-by-side →
FAQ
How much does Kimi K2.5 cost?
Input is priced at $0.600 per 1M tokens and output at $3.00 per 1M tokens (Amazon Bedrock, last verified Oct 22, 2026).
What is the context window of Kimi K2.5?
Kimi K2.5 supports a 262,144-token context window with up to 16,000 output tokens.
Does Kimi K2.5 support function calling?
Yes — Kimi K2.5 supports function (tool) calling.
Is Kimi K2.5 good for production?
Kimi K2.5 is well-suited for multi-step reasoning and analysis tasks and agentic workflows that depend on reliable tool calls.
How can I route to Kimi K2.5 with fallback?
Use Agent Command Center: a single OpenAI-compatible endpoint that supports cost-optimized routing, latency-aware retries, model fallback, and shadow traffic. Configure once, swap models without app changes.
Useful links for Kimi K2.5
Official sources, independent benchmarks, and pricing aggregators — no random search-engine guesses.
Third-party evals — verify the marketing.
Cross-check our number against the rest of the ecosystem.