// AI Platform Drift
DeepSeek Flash Latest: prompt pricing cut 53%, completion tokens capped at 384k
OpenRouter model catalogue · published 2026-09-26 03:56 UTC
CORRECTED 2026-10-02 17:58 UTC — [CORRECTION · triage.triage reasoning] Original: “max output tokens cut by half” Fact: Maximum output tokens decrease 59.3%, from 943,718 to 384,000.
Stood 158h 2m · cause arithmetic · every correction ↗
Captured arithmetic only; vendor rate validity, applicability and effective conditions remain unverified.
WHAT CHANGEDOpenRouter's deepseek/deepseek-flash-latest model pricing dropped from $0.000000075 to $0.000000035 per prompt token (53% reduction) and $0.0000003 to $0.00000029 per completion token (3% reduction). The max_completion_tokens limit decreased from 943,718 to 384,000 tokens.
WHY IT MATTERSExisting requests generating more than 384k completion tokens will now fail or truncate. Cost projections for this model are no longer accurate—workloads will cost roughly half as much for prompts but may require splitting long completions across multiple requests.
WHAT TO DOAudit any code calling this model: check if you request or rely on completions exceeding 384k tokens, and if so, implement chunking or switch models. Update cost forecasts to reflect the new prompt pricing.
Model-reported confidence 95% (not measured accuracy)
Primary source ↗
written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
id: ~deepseek/deepseek-flash-latest name: DeepSeek: DeepSeek Flash Latest -pricing.prompt: 0.000000075 -pricing.completion: 0.0000003 +pricing.prompt: 0.000000035 +pricing.completion: 0.00000029 context_length: 1048576 -top_provider.max_completion_tokens: 943718 +top_provider.max_completion_tokens: 384000
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
| triage verdict | MATERIAL at 0.98, needed 0.5 |
|---|---|
| triage reasoning | Pricing dropped significantly and max output tokens cut by half. Teams budgeting or optimizing this model need to know. |
| signals | prompt pricing decreased ~53% · completion pricing decreased ~3% · max_completion_tokens reduced from 943718 to 384000 (~59% decrease) · pricing changes affect cost calculations for existing workloads · token limit reduction may break or require refactoring existing requests |
| suppression | — |
| triage model | anthropic/claude-haiku-4.5 ($0.00000) |
| writer model | anthropic/claude-sonnet-4.5 ($0.00000) |