OpenRouter
Catalog quote- Input
- $0.2088
- Output
- $0.4176
- Cached input
- $0.0174
deepseek-aiListed Apr 22, 2026
DeepSeek-V4-Pro
DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.
Context window1M
Max output393.2K
Provider endpoints22
Benchmark results0
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
22 quotesPrices across providers
Your token mix
USD · listed token ratesnovita
via Hugging Face- Input
- $1.60
- Output
- $3.20
featherless-ai
via Hugging Face- Input
- —
- Output
- —
deepinfra
via Hugging Face- Input
- $1.30
- Output
- $2.60
- Input
- $1.30
- Output
- $2.60
Experiential
Standard list rate
- Input
- $1.74
- Output
- $3.48
- Cached input
- $0.145
Catalog list rate. Plan allowances and temporary discounts are separate.
- Input
- $0.1775
- Output
- $0.3549
- Cached input
- $0.0147
Source discount 89.5%; rates as published
- Input
- $0.2088
- Output
- $0.4176
- Cached input
- $0.0174
Source discount 88%; rates as published
- Input
- $0.45
- Output
- $3.48
- Cached input
- $0.10
Endpoint degraded (status -2)
- Input
- $0.90
- Output
- $3.00
- Cached input
- $0.16
- Input
- $0.957
- Output
- $1.914
- Cached input
- $0.0798
Source discount 45%; rates as published
- Input
- $1.044
- Output
- $2.088
- Cached input
- $0.2088
- Input
- $1.05
- Output
- $2.10
- Cached input
- $0.21
Source discount 30%; rates as published
- Input
- $1.15
- Output
- $2.55
- Cached input
- $0.20
- Input
- $1.30
- Output
- $2.60
- Cached input
- $0.10
- Input
- $1.416
- Output
- $2.832
- Cached input
- $0.118
Max prompt 1000000 tokens · Endpoint degraded (status -2)
- Input
- $1.5016
- Output
- $3.135
- Cached input
- $0.135
- Input
- $1.56
- Output
- $3.12
- Cached input
- $0.13
Max prompt 1000000 tokens
- Input
- $1.60
- Output
- $3.20
- Cached input
- $0.135
- Input
- $1.65
- Output
- $3.301
- Cached input
- $0.33
- Input
- $1.68
- Output
- $3.38
- Cached input
- $0.13
- Input
- $1.91
- Output
- $3.83
- Cached input
- $0.16
Model specifications
- Developer
- deepseek-ai
- Modality
- Language
- Context
- 1,048,576 tokens
- Maximum output
- 393,216 tokens
- Weights
- Open weights
- Provider listed
- Apr 22, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
deepseek/deepseek-v4-pro - huggingface
deepseek-ai/DeepSeek-V4-Pro - deepinfra
deepseek-ai/DeepSeek-V4-Pro - experiential
deepseek-v4-pro
Sources
Updated Oct 17, 2026
More from deepseek-ai
View all ↗deepseek-aiListed Today
DeepSeek-V4.1-Flash-1017
DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model…
1M contextImage inputTool callingNo reported score
No reported score
$0.10in$0.50out/ 1M tokens · USDInferenceNet · via OpenRouter · 7 endpointsinference-net/fp8 · quantization=fp8
deepseek-aiListed Aug 21
DeepSeek-V4-Flash-Vision-Exp
DeepSeek-V4-Flash-Vision-Exp is DeepSeek's experimental multimodal model in the V4-Flash family, adding visual understanding to the V4-Flash architecture. It serves a 1M-token (1,048,576) context window and…
1M contextImage inputTool calling
$0.2156in$0.6468out/ 1M tokens · USDDeepInfra · via OpenRouter · 6 endpointsdeepinfra/fp8 · quantization=fp8
deepseek-aiListed Aug 12
DeepSeek-V4-Pro-0813
DeepSeek-V4-Pro-0813 is the official release of DeepSeek-V4-Pro, superseding the preview version, with greatly enhanced agentic capabilities and performance improvements that are especially pronounced in…
1M contextTool callingStructured outputNo reported score
No reported score
deepseek-aiListed Jul 31
DeepSeek-V4-Flash-0731
DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro…
1M contextTool callingStructured outputNo reported score
No reported score
$0.0071in$1.28out/ 1M tokens · USDOpenInference · via OpenRouter · 35 endpointsopen-inference/fp4 · quantization=fp4