Overview
Model specifications
- Context
- 163,840 tokens
- Maximum output
- 65,536 tokens
- Architecture
- text->text
- Tokenizer
- DeepSeek
- Knowledge cutoff
- Not provided
- Moderated
- No
OPENROUTER
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.269 per 1M tokens
- Output
- $0.4 per 1M tokens
- Cache read
- $0.1345 per 1M tokens
API
Model configuration
Default parameters
temperature- 1
top_p- 0.95
Reasoning
- Reasoning required
- No
- Default parameters
- No
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-v3.2","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
text
Output
text
Reasoning
No
API
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pAvailable providers
15 providers
Checked: September 21, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
GMICloud
fp8- Context
- 164K
- Maximum output
- 147K
- Input
- $0.2088
- Output
- $0.3096
- Cache read
- $0.0216
- Cache write
- Not provided
StreamLake
fp8- Context
- 128K
- Maximum output
- 64K
- Input
- $0.2145
- Output
- $0.3217
- Cache read
- $0.0215
- Cache write
- Not provided
SiliconFlow
fp8- Context
- 164K
- Maximum output
- 147K
- Input
- $0.259
- Output
- $0.42
- Cache read
- $0.135
- Cache write
- Not provided
DeepInfra
fp4- Context
- 164K
- Maximum output
- 16K
- Input
- $0.26
- Output
- $0.38
- Cache read
- $0.13
- Cache write
- Not provided
AtlasCloud
fp8- Context
- 164K
- Maximum output
- 147K
- Input
- $0.26
- Output
- $0.38
- Cache read
- $0.13
- Cache write
- Not provided
Venice
Not provided- Context
- 160K
- Maximum output
- 33K
- Input
- $0.2683
- Output
- $0.3902
- Cache read
- $0.1301
- Cache write
- Not provided
Novita
fp8- Context
- 164K
- Maximum output
- 66K
- Input
- $0.269
- Output
- $0.4
- Cache read
- $0.1345
- Cache write
- Not provided
Baidu
fp8- Context
- 131K
- Maximum output
- 66K
- Input
- $0.28
- Output
- $0.42
- Cache read
- $0.028
- Cache write
- Not provided
DigitalOcean
Not provided- Context
- 164K
- Maximum output
- 147K
- Input
- $0.3
- Output
- $0.96
- Cache read
- $0.09
- Cache write
- Not provided
Alibaba
fp8- Context
- 131K
- Maximum output
- 66K
- Input
- $0.3705
- Output
- $1.1115
- Cache read
- $0.0741
- Cache write
- $0.4634
Friendli
Not provided- Context
- 164K
- Maximum output
- 147K
- Input
- $0.5
- Output
- $1.5
- Cache read
- $0.25
- Cache write
- Not provided
- Context
- 164K
- Maximum output
- 66K
- Input
- $0.56
- Output
- $1.68
- Cache read
- Not provided
- Cache write
- Not provided
Phala
Not provided- Context
- 164K
- Maximum output
- 64K
- Input
- $1
- Output
- $1
- Cache read
- $0.5
- Cache write
- Not provided
Mara
Not provided- Context
- 33K
- Maximum output
- 7K
- Input
- $3
- Output
- $4.5
- Cache read
- Not provided
- Cache write
- Not provided
SambaNova
Not provided- Context
- 33K
- Maximum output
- 7K
- Input
- $3
- Output
- $4.5
- Cache read
- Not provided
- Cache write
- Not provided