DeepSeek V4 Flash 0731 completion price increased 352.5%
OpenRouter's pricing for deepseek/deepseek-v4-flash-0731 changed on 2026-10-17.
Method: on 2026-10-30 we checked a random sample of 50 items from the last 30 days against their sources. 43 were right, 2 were wrong, and 5 could not be checked because the source no longer shows the old data. The 95.6% figure leaves those 5 out; the strict 86% figure counts them as wrong. This sample was checked by RADAR's build assistant and was not independently double-checked by a person. With a sample this size the true rate is likely between 85.2% and 98.8%. One sample, not a guarantee.
OpenRouter's pricing for deepseek/deepseek-v4-flash-0731 changed on 2026-10-17.
OpenRouter's ~deepseek/deepseek-v4-flash-latest model pricing changed on 2026-10-17.
OpenRouter's ~deepseek/deepseek-pro-latest model completion rate decreased from $8.00 to $0.3831 per 1M tokens, and prompt rate decreased from $0.234 to $0.12332 per 1M…
OpenRouter added deepseek/deepseek-v4.1-flash-1017 to its model catalogue on 17 October 2026.
OpenRouter's deepseek/deepseek-v4.1-flash model pricing changed on 17 October 2026.
Azure Foundry set retirement date 2026-12-09 for Ministral-3B (becomes ministral-ministral-4b-instruct), mistral-medium-2505 (becomes mistral-medium-3-5), and mistral-sm…
OpenRouter's ~deepseek/deepseek-flash-latest model changed on 2026-10-16: captured completion base rate changed from $0.6633 to $0.6435 per 1M tokens, and max_completion…
OpenRouter's pricing for ~deepseek/deepseek-flash-latest changed on 16 October 2026.
OpenRouter's deepseek/deepseek-v4.1-flash prompt pricing changed from $0.018 to $0.036 per 1M tokens.
Fast mode for Claude Opus 5.5 is out of research preview as of October 15, 2026.
Claude Opus 5.5 fast mode is now generally available as of October 15, 2026.
OpenRouter's ~deepseek/deepseek-flash-latest model pricing changed effective 15 October 2026.
OpenRouter's pricing for deepseek/deepseek-v4.1-flash changed on 15 October 2026.
OpenRouter changed pricing for google/gemma-4-31b-it effective immediately.
Four gpt-chat-latest preview versions had their retirement dates pushed back: 2026-05-05 now retires 2026-11-17 (was 2026-08-05), 2026-05-28 now retires 2026-12-08 (was…
OpenAI added /v1/audio/translations to its 2026-08-26 transcription-models deprecation table, with a shutdown date of February 26, 2027 and v1/realtime/translations as t…
OpenRouter reduced the prompt token price for ~deepseek/deepseek-flash-latest from $0.02016 to $0.01584 per 1M tokens, effective as of the 14 October 2026 catalogue upda…
OpenRouter reduced pricing for mistralai/mistral-small-3.2-24b-instruct: completion tokens from $0.25 to $0.20 per 1M tokens, prompt tokens from $0.09375 to $0.075 per 1…
OpenRouter reduced the prompt token price for deepseek/deepseek-v4.1-flash from $0.02016 to $0.01584 per 1M tokens, a 21.4% decrease.
The retirement schedule page removed an inline table listing 13 Fireworks models (FW-DeepSeek-V3.1, FW-DeepSeek-V3.2, FW-GLM-4.7, FW-GLM-5, FW-GLM-5.1, FW-GPT-OSS-120B,…
OpenRouter reduced pricing for deepseek/deepseek-v4-pro-0813 by 50% across both token types.
OpenRouter added google/gemini-4-argon:batch to its model catalogue on 13 October 2026.
OpenRouter added google/gemini-4-argon to its model catalogue on 2026-10-13.
On October 14, 2026, OpenAI announced the retirement of GPT-4o (gpt-4o-2024-08-06, gpt-4o-2024-11-20), GPT-4o mini (gpt-4o-mini-2024-07-18), GPT-4.1 (gpt-4.1-2025-04-14)…
OpenRouter's pricing for ~deepseek/deepseek-v4-flash-latest changed on 13 October 2026.
OpenRouter raised pricing for meta-llama/llama-3.3-70b-instruct effective 13 October 2026.
OpenRouter's deepseek/deepseek-v4-flash model reduced its captured prompt base rate from $0.0131 to $0.0048 per 1M tokens, a 63.4% decrease.
OpenRouter's deepseek/deepseek-v3.1-terminus model reduced prompt pricing from $0.30 to $0.27 per 1M tokens and increased max_completion_tokens from 65,536 to 147,456 to…
OpenRouter's pricing for ~deepseek/deepseek-v4-flash-latest changed on 2026-10-12.
deepseek/deepseek-v4-flash: captured prompt base rate changed from $0.0216 to $0.0131 per 1M tokens.
OpenRouter's deepseek/deepseek-v4-flash-vision-exp model pricing dropped 51% on both prompt and completion tokens: captured completion base rate changed from $1.32 to $0…
OpenRouter's pricing for deepseek/deepseek-v4-flash-0731 changed on 2026-10-11.
~deepseek/deepseek-v4-flash-latest prompt token pricing decreased from $0.0116 to $0.0095 per 1M tokens, effective as of the 10 October 2026 catalogue update.
OpenRouter's catalogue shows ~deepseek/deepseek-flash-latest prompt pricing changed from $0.0038 to $0.0001 per 1M tokens, a 97.4% reduction.
OpenRouter's pricing for deepseek/deepseek-v4.1-flash changed on 2026-10-10.
Claude Code, previously exclusive to the Max tier, is now included in both Pro ($17/month) and Max (from $100/month) tiers.
Claude Fable 5 and Claude Mythos 5 launched 9 June 2026 with a new tokenizer that produces roughly 30% more tokens for the same text compared to models before Claude Opu…
Anthropic's pricing page now shows monthly API credits included with paid subscription tiers: $100/month for one tier and $200/month for another.
Claude Platform introduced dynamic workflows for Managed Agents on October 9, 2026, available in beta with the managed-agents-2026-04-01 header.
OpenRouter's pricing for ~deepseek/deepseek-flash-latest changed on 2026-10-09.
OpenRouter's pricing for ~deepseek/deepseek-flash-latest changed: captured completion base rate changed from $1.20 to $0.60 per 1M tokens, and captured prompt base rate…
OpenRouter's deepseek/deepseek-v4-flash model reduced its prompt token price from $0.0173 to $0.0057 per 1M tokens, a 67.1% decrease.
Azure Foundry moved the gpt-4.1-nano retirement date from 2026-10-14 to 2027-04-14.
OpenRouter reduced the prompt token price for deepseek-pro-latest from $0.135 to $0.108 per 1M tokens, effective as of the 2026-10-08 catalogue update.
OpenRouter's catalogue shows ~deepseek/deepseek-flash-latest completion pricing changed from $0.60 to $1.00 per 1M tokens and prompt pricing changed from $0.0184 to $0.0…
OpenRouter's catalogue now shows Mistral Large 4 with a context_length of 1,048,576 tokens, up from 524,288 tokens.
OpenRouter reduced pricing for deepseek/deepseek-v4.1-flash: completion tokens from $1.20 to $1.00 per 1M tokens (16.7% decrease), prompt tokens from $0.05 to $0.0356 pe…
OpenRouter's ~deepseek/deepseek-flash-latest model changed its captured completion base rate from $0.424 to $0.60 per 1M tokens and its captured prompt base rate from $0…
OpenRouter reduced pricing for meta-llama/llama-3.3-70b-instruct effective immediately.
OpenRouter's ~deepseek/deepseek-flash-latest model pricing dropped from $0.05 to $0.019 per 1M prompt tokens and from $1.20 to $0.424 per 1M completion tokens.