moonshotai.kimi-k2.5
Bedrock · Chat model
moonshotai.kimi-k2.5 is listed here as a chat model from Bedrock. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Provider and model identifiers are kept in their original form for accuracy.
bedrock-bedrock-moonshotai-kimi-k2-5
Catalog generated: Aug 10, 2026
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $0.6000 / 1M tokens |
| Output | $3.0300 / 1M tokens |
| Cached input | $0.0600 / 1M tokens |
| Embedding | $0.6000 / 1M tokens |
Limits
Capabilities
| Capability | Supported |
|---|---|
| Vision | Supported |
| Function calling | Supported |
| Parallel function calling | - |
| Tool choice | Supported |
| Prompt caching | - |
| Reasoning | Supported |
| Response schema | - |
| System messages | Supported |
| Audio input | - |
| Audio output | - |
| Web search | - |
| PDF input | - |
| Video input | Supported |
| Native streaming | - |
| Computer use | - |
| Assistant prefill | - |
| Structured output | - |
| Output config | - |
| URL context | - |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| GPQA Diamond | 87.6 | Score | Base model: Kimi-K2.5 (Kimi-K2.5) | 2026-05-31 | Link |
| LiveCodeBench v6 | 85.0 | Pass@1 | Base model: Kimi-K2.5 (Kimi-K2.5) | 2026-05-31 | Link |
| SWE-bench Pro | 50.7 | score | Base model: Kimi-K2.5 (Kimi-K2.5) | 2026-05-31 | Link |
| SWE-bench Verified | 70.8 * | score | Base model: Kimi-K2.5 (Kimi-K2.5) | 2026-05-31 | Link |
| Terminal-Bench 2.0 | 43.2 * | score | Base model: Kimi-K2.5 (Kimi-K2.5) | 2026-05-31 | Link |
| Apex Agents | 14.4 * | score | Base model: Kimi-K2.5 (Kimi-K2.5) | 2026-05-31 | Link |
| Artificial Analysis Intelligence Index | 46.8 | score | Base model: kimi-k2.5 (moonshotai/kimi-k2.5) | 2026-05-31 | Link |
| Artificial Analysis Coding Index | 39.6 | score | Base model: kimi-k2.5 (moonshotai/kimi-k2.5) | 2026-05-31 | Link |
| Artificial Analysis Agentic Index | 58.9 | score | Base model: kimi-k2.5 (moonshotai/kimi-k2.5) | 2026-05-31 | Link |
Related articles
Articles relevant to this model's provider, capabilities, and use cases.
Reasoning LLM API Pricing Guide
Which reasoning models are cheapest, which are most expensive, and when to use reasoning vs non-reasoning models.
AWS Bedrock Provider Guide
AWS Bedrock model access, pricing, and when to choose Bedrock for managed multi-model inference.
Model Routing Cascade
A four-tier Budget, Mid, Premium, and Reasoning model selection framework for routing queries to the lowest-cost suitable tier.
Hidden Costs of LLM APIs
Fine-tuning, rate limits, latency tradeoffs, evaluation, integration, and vendor risk — the LLM API costs that don't show up in per-token comparisons.
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
| Catalog generated | 2026-08-10T21:27:29.020Z |
Docs
| Official docs |