Overview
Model specifications
- Context
- 1,048,576 tokens
- Maximum output
- 384,000 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
- $0.9553 per 1M tokens
- Output
- $1.9105 per 1M tokens
- Cache read
- $0.0796 per 1M tokens
API
Model configuration
Default parameters
temperature- 1
top_p- 1
Reasoning
- Reasoning required
- No
- Default parameters
- high
- Capabilities
- xhigh, high
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-v4-pro","messages":[{"role":"user","content":"Hello!"}]}'Capabilities
Input → Output
Input
text
Output
text
Reasoning
No · xhigh · high
API
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_pAvailable providers
16 providers
Checked: September 22, 2026
Live providers on OpenRouter
OpenRouter Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
StreamLake
fp8- Context
- 1.0M
- Maximum output
- 384K
- Input
- $0.9553
- Output
- $1.9105
- Cache read
- $0.0796
- Cache write
- Not provided
GMICloud
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.957
- Output
- $1.914
- Cache read
- $0.0798
- Cache write
- Not provided
DigitalOcean
Not provided- Context
- 1.0M
- Maximum output
- 384K
- Input
- $1.044
- Output
- $2.088
- Cache read
- $0.2088
- Cache write
- Not provided
Cloudflare
Not provided- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.15
- Output
- $2.55
- Cache read
- $0.2
- Cache write
- Not provided
DeepInfra
fp8- Context
- 1.0M
- Maximum output
- 16K
- Input
- $1.3
- Output
- $2.6
- Cache read
- $0.1
- Cache write
- Not provided
Alibaba
fp8- Context
- 1M
- Maximum output
- 393K
- Input
- $1.416
- Output
- $2.832
- Cache read
- $0.118
- Cache write
- Not provided
SiliconFlow
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.5016
- Output
- $3.135
- Cache read
- $0.135
- Cache write
- Not provided
Novita
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.6
- Output
- $3.2
- Cache read
- $0.135
- Cache write
- Not provided
Venice
Not provided- Context
- 1M
- Maximum output
- 33K
- Input
- $1.65
- Output
- $3.301
- Cache read
- $0.33
- Cache write
- Not provided
AtlasCloud
fp4- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.68
- Output
- $3.38
- Cache read
- $0.13
- Cache write
- Not provided
Baidu
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $1.69
- Output
- $3.38
- Cache read
- $0.14
- Cache write
- Not provided
NextBit
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.74
- Output
- $3.48
- Cache read
- $0.145
- Cache write
- Not provided
BaseTen
fp4- Context
- 1.0M
- Maximum output
- 262K
- Input
- $1.74
- Output
- $3.48
- Cache read
- $0.145
- Cache write
- Not provided
BaseTen
fp4- Context
- 1.0M
- Maximum output
- 262K
- Input
- $1.74
- Output
- $3.48
- Cache read
- $0.145
- Cache write
- Not provided
Parasail
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $1.74
- Output
- $3.48
- Cache read
- $0.1
- Cache write
- Not provided
Azure
Not provided- Context
- 1.0M
- Maximum output
- 384K
- Input
- $1.91
- Output
- $3.83
- Cache read
- $0.16
- Cache write
- Not provided