deepseek-v4-pro-0813
deepseek-v4-pro-0813Availability100.0%
Available
Samples: 16
Latency1.7 s
DeepSeek V4 Pro, pinned to the 0813 release.
- Input / 1M tokens
- $1.32
- Output / 1M tokens
- $3.96
- Context window
- 1,048,576
- Route
- Default
DefaultRoleplay
Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.
Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.
LiveBench · Story constraint following
deepseek-v4-pro-0813: 74.93
71 Models · 2026-10-25
LiveBench · Theory of mind
deepseek-v4-pro-0813: 84.62
71 Models · 2026-10-25
8.2/ 10
Routes
Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.
| Use this model | ||||||
|---|---|---|---|---|---|---|
| forge | $0.66 | $1.98 | $0.022 | 8.2/10 | 7.8/10 | Plans and tiers |
| ollama_pro | $0.66 | $1.98 | $0.022 | 8.2/10 | 7.8/10 | Plans and tiers |
| deepseek_official | $1.32 | $3.96 | $0.044 | 8.2/10 | 5.9/10 | Plans and tiers |
| Default | $1.32 | $3.96 | $0.044 | 8.2/10 | 5.9/10 | Use this model |
| opencode_plus | $1.32 | $3.96 | $0.044 | 8.2/10 | 5.9/10 | Plans and tiers |
ollama_pro
opencode_plusQuick start
Access and billingcurl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "deepseek-v4-pro-0813",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'