DeepSeek V4.1 Flash (Max)Ready
deepseek-v4-1-flash
Serverless APILLMReasoningVisionPrompt cachingOpen weights
A throughput-first tier delivering frontier-adjacent quality at commodity prices. It ranks #18 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 39.5. Released September 10, 2026.
1M
Context
552B
Parameters
#18
Intelligence rank · 39.5
Open
Weights · MIT
View full spec
ReleasedSep 10, 2026
Knowledge cutoff—
Size classlarge
Input modalitiestext, image
Output modalitiestext
Median output speed176 tok/s
Median time to first token1.2s
LicenseMIT
Usage guide
1. Choose how you'd like to use DeepSeek V4.1 Flash (Max)
☁️ Serverless
Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.
Usage tiers · Standard • Priority
Try it — sign in
curl https://tokenhub-staging.coality.io/v1/chat/completions \
-H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-1-flash",
"messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
}'Pricing
| Bucket | Price | Notes |
|---|---|---|
| Input tokens | $0.3750 | per 1M tokens |
| Output tokens | $1.50 | per 1M tokens |
| Cache read | $0.0075 | cached input · 98% off |
| Cache write | — | per 1M tokens |
Billed per token with micro-dollar precision · effective Oct 26, 2026 · default key limits 600 req/min · 200K tokens/min
Benchmarks
Humanity's Last Exam
39.2
MMMU-Pro
77.0
SciCode
51.9
Terminal-Bench 4.0
26.8
Long Context Reasoning
84.0
Frontier Code
44.0
Scores from the Artificial Analysis evaluation suite (0–100 scale).
About this model
552B-parameter open-weight model, with a 1M context window, native image input, visible reasoning traces, prompt caching at a 98% discount on cached input, 176 output tokens/s median serving speed and 1.2s to first token.