Overview
Model specifications
- Context
- 262,144 tokens
- Maximum output
- 98,304 tokens
- Architecture
- text->text
- Tokenizer
- Other
- Knowledge cutoff
- Not provided
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.6 per 1M tokens
- Output
- $2.5 per 1M tokens
- Cache read
- $0.15 per 1M tokens
API
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- Yes
API
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moonshotai/kimi-k2-thinking","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
text
Output
text
Reasoning
Yes
API
Supported API parameters
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pAvailable providers
2 providers
Checked: September 13, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
- Context
- 262K
- Maximum output
- 236K
- Input
- $0.6
- Output
- $2.5
- Cache read
- Not provided
- Cache write
- Not provided
Novita
bf16- Context
- 262K
- Maximum output
- 98K
- Input
- $0.6
- Output
- $2.5
- Cache read
- $0.15
- Cache write
- Not provided