Overview
Model specifications
- Context
- 163,840 tokens
- Maximum output
- 147,456 tokens
- Architecture
- text->text
- Tokenizer
- DeepSeek
- Knowledge cutoff
- 2024-07-31
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.25 per 1M tokens
- Output
- $1 per 1M tokens
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":"deepseek/deepseek-chat-v3-0324","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
text
Output
text
API
Supported API parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pAvailable providers
4 providers
Checked: September 12, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
DeepInfra
fp4- Context
- 164K
- Maximum output
- 16K
- Input
- $0.24
- Output
- $0.9
- Cache read
- $0.135
- Cache write
- Not provided
SiliconFlow
fp8- Context
- 164K
- Maximum output
- 147K
- Input
- $0.25
- Output
- $1
- Cache read
- Not provided
- Cache write
- Not provided
GMICloud
fp8- Context
- 164K
- Maximum output
- 147K
- Input
- $0.29
- Output
- $1.14
- Cache read
- $0.11
- Cache write
- Not provided
Crusoe
bf16- Context
- 164K
- Maximum output
- 147K
- Input
- $0.5
- Output
- $1.5
- Cache read
- $0.25
- Cache write
- Not provided