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
- $0.0886 per 1M tokens
- Output
- $0.1772 per 1M tokens
- Cache read
- $0.0177 per 1M tokens
API
Model configuration
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-flash","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_atop_ktop_logprobstop_pAvailable providers
15 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.
OpenInference
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.04
- Output
- $0.3
- Cache read
- $0.014
- Cache write
- Not provided
StreamLake
fp8- Context
- 1.0M
- Maximum output
- 384K
- Input
- $0.0886
- Output
- $0.1772
- Cache read
- $0.0177
- Cache write
- Not provided
DeepInfra
fp8- Context
- 1.0M
- Maximum output
- 66K
- Input
- $0.09
- Output
- $0.18
- Cache read
- $0.018
- Cache write
- Not provided
GMICloud
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.091
- Output
- $0.182
- Cache read
- $0.0182
- Cache write
- Not provided
Venice
Not provided- Context
- 1M
- Maximum output
- 33K
- Input
- $0.0966
- Output
- $0.1925
- Cache read
- $0.0196
- Cache write
- Not provided
DigitalOcean
Not provided- Context
- 1.0M
- Maximum output
- 384K
- Input
- $0.098
- Output
- $0.196
- Cache read
- $0.0196
- Cache write
- Not provided
SiliconFlow
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $0.13
- Output
- $0.28
- Cache read
- $0.028
- Cache write
- Not provided
Alibaba
fp8- Context
- 1M
- Maximum output
- 393K
- Input
- $0.134
- Output
- $0.268
- Cache read
- $0.0268
- Cache write
- Not provided
Baidu
fp8- Context
- 1.0M
- Maximum output
- 131K
- Input
- $0.14
- Output
- $0.28
- Cache read
- $0.028
- Cache write
- Not provided
Novita
fp8- Context
- 1.0M
- Maximum output
- 393K
- Input
- $0.14
- Output
- $0.28
- Cache read
- $0.028
- Cache write
- Not provided
AtlasCloud
fp4- Context
- 1.0M
- Maximum output
- 393K
- Input
- $0.14
- Output
- $0.28
- Cache read
- $0.028
- Cache write
- Not provided
Parasail
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.14
- Output
- $0.28
- Cache read
- $0.07
- Cache write
- Not provided
NextBit
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.15
- Output
- $0.3
- Cache read
- $0.035
- Cache write
- Not provided
Mancer 2
fp8- Context
- 1.0M
- Maximum output
- 944K
- Input
- $0.19
- Output
- $0.5
- Cache read
- Not provided
- Cache write
- Not provided
Azure
Not provided- Context
- 1.0M
- Maximum output
- 384K
- Input
- $0.21
- Output
- $0.56
- Cache read
- $0.031
- Cache write
- Not provided