Moonshot AI

Kimi K2 Thinking

262K ctxText Tools Reasoning

Released Nov 6, 2025 · 158B tokens this week · 4 providers

Overview

A reasoning variant of Kimi K2 that interleaves thinking with hundreds of sequential tool calls. Aimed at deep research and long autonomous sessions rather than snappy chat. Holds up remarkably well across very long trajectories.

reasoningagentsacademia

Providers

Reference data — not yet measured from live traffic

PROVIDERMAX OUTOUTPUT /MQUANT
Novita AICheapest
262K66K$0.60$2.50880ms5898.50%fp8
DeepInfra
262K66K$0.63$2.63840ms6498.60%fp8
Together AI
262K66K$0.66$2.75195ms7899.30%Full
Fireworks AI
262K66K$0.70$2.90740ms8899.45%Full

Latency p50 reflects a provider’s API endpoint responsiveness — the round-trip to its API, not per-token inference time. These figures, with throughput and uptime, are reference data until the gateway aggregates its own traffic.

Price comparison

Blended $ per 1M tokens

Kimi K2 Thinking$2.02
GPT-5.2$10.94

Blended rate per 1M tokens, weighted one part prompt to three parts completion — roughly the shape of a chat workload. Your mix will move the number.

Call it

OpenAI-compatible — swap the base URL and go

curl https://model.cards/api/v1/chat/completions \
  -H "Authorization: Bearer $MODELCARDS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2-thinking",
    "messages": [
      { "role": "user", "content": "Summarize the tradeoffs of speculative decoding." }
    ]
  }'