Language Models

2026/11/02

  1. Fast mode on Claude Opus 4.8 ends on 30 November; on Opus 5.5 it costs $8 input and $40 output
    PriceAnthropic

2026/10/19

  1. Sending Claude API traces to Datadog and other platforms with OpenTelemetry
    How to UseAnthropic
  2. OpenAI's Decisions API does not charge for output, at $0.10 per million input tokens
    PriceOpenAI

2026/10/18

  1. Creating GPT-Live voices from text for free, plus new Japanese voices Harema and Shida
    How to UseOpenAI
  2. Fast mode for Claude Opus 5.5 no longer needs an access request (at twice the standard price)
    PriceAnthropic

2026/10/13

  1. How much does speech-to-text cost per hour? Comparing the xAI and Mistral APIs
    PricexAIMistral
  2. Mistral Large 4 costs $1.36 in and $4.18 out, at half price for two weeks after launch
    PriceMistral
  3. Claude Managed Agents' web_fetch now fetches only URLs that already appear in the session
    How to UseAnthropic
  4. xAI's speech-to-text API costs $0.10 an hour in batch, and moved to 2.0 on 2 October
    PricexAI
  5. Claude Max and Team plans now include monthly API credits ($100 on Max 5x)
    PriceAnthropic
  6. GPT-6.1 Sol charges less than GPT-6 Sol for cached input
    ModelOpenAI
  7. Claude Sonnet 5.5 keeps Sonnet 5's price, and its cache reads were halved on 7 October
    ModelAnthropic
  8. Claude Haiku 5.5 is priced like GPT-6 Luna up to 100K tokens, and five times higher beyond
    PriceAnthropicOpenAI

2026/09/29

  1. Gemini 2.5 models are now limited to users who have used them before
    ModelGoogle
  2. Grok 4.7 joins xAI's model list at the same price and context as Grok 4.6
    ModelxAI
  3. Gemini 3.8 Live pricing: audio in at $0.005 a minute and audio out at $0.018
    PriceGoogle

2026/09/28

  1. Gemini 3.8 Flash TTS and Flash-Lite TTS prices double on 1 January 2027
    PriceGoogle
  2. Claude Opus 5.5 is $4 in and $20 out, and the model Anthropic now recommends first
    ModelAnthropic
  3. GPT-6 Sol and GPT-6 Luna: Luna costs a twentieth of Sol
    ModelOpenAI

2026/09/15

  1. DeepSeek V4.1 Flash takes over from V4 Flash at a lower price
    ModelDeepSeek
  2. Sakana AI's Fugu Ultra v2 and Fugu Max answer by routing work to other models
    ModelSakana AIOpenAI
  3. Cognition's SWE-2 is a coding model built on Kimi K3
    ModelCognitionMoonshot
  4. Inception's Mercury 2.5, a diffusion model at $0.75 per million output tokens
    PriceInceptionOpenAIAnthropic
  5. GPT-Live 1 bills by the minute, at $0.05, with the reasoning model on top
    PriceOpenAI

2026/09/08

  1. Meta sells the same model at two prices, and the cheap one is paid for with your prompts
    PriceMeta
  2. Grok 4.6 is the flagship, and it holds half the context of Grok 4.3
    ModelxAI
  3. Kimi K3 holds a million tokens at one flat rate
    ModelMoonshot
  4. The same Qwen model costs less from Beijing than from Singapore
    PriceAlibaba
  5. On Mistral, Large costs a third of Medium
    PriceMistral
  6. GPT-6 Astra and the three models that make up GPT-6
    ModelOpenAI
  7. GPT-6 Astra prices, and the 272K line that reprices the whole request
    PriceOpenAIAnthropic
  8. Claude Fable 5.1 takes the top of the lineup, and Fable 5 moves to legacy
    ModelAnthropic
  9. Cache reads on Fable 5.1 are a quarter of what they cost on Fable 5
    CostAnthropic

2026/09/02

  1. The current Claude lineup: 1M context, 128K output, retirement more than a year out
    ModelAnthropic
  2. SWE-bench Verified is at 97, and the top of the table is hard to read
    BenchmarkAnthropic
  3. A benchmark number means nothing without the conditions it was taken under
    BenchmarkAnthropicOpenAIGoogleDeepSeek
  4. Claude API prices, and the Sonnet 5 increase that did not happen
    PriceAnthropic
  5. OpenAI API prices: the GPT-5.6 line has long-context rates too
    PriceOpenAI
  6. Gemini API prices, and the two dates that change them
    PriceGoogle
  7. DeepSeek now charges double during peak hours
    PriceDeepSeek
  8. Perplexity Sonar ends on 27 September 2026, replaced by the Agent API
    PricePerplexity
  9. What prompt caching actually costs, and where the tenth does not hold
    CostOpenAIAnthropicGoogleDeepSeekxAIMetaMistralAlibabaMoonshotSakana AI
  10. Long context: who reprices the whole request, and who does not
    CostOpenAIAnthropicGooglexAIAlibabaMoonshotSakana AI
  11. Adding an MCP server to Claude Code, and which scope to pick
    How to UseAnthropic

English

TermsPrivacy

© Rollpie

X

Fast mode on Claude Opus 4.8 ends on 30 November; on Opus 5.5 it costs $8 input and $40 output

PriceAnthropic
2026/11/02

Anthropic deprecated fast mode for Claude Opus 4.8 on 30 October 2026⁠[1]. It will be removed on 30 November, and after that, requests to claude-opus-4-8 with speed: "fast" will return an error⁠[1,2].

To keep using fast mode, Anthropic says to migrate to Claude Opus 5.5⁠[1,2]. The steps are in its guide to migrating from Opus 4.8 to Opus 5.5⁠[2].

Fast mode runs the same model with a faster inference configuration, with no change to intelligence or capabilities⁠[2]. Output tokens per second are up to 2.5 times higher⁠[2].

Per million tokens, fast mode costs $10 input and $50 output on Opus 4.8 and Opus 5, and $8 input and $40 output on Opus 5.5⁠[2]. The price is a multiplier on standard rates across the full context window, including requests over 200k input tokens⁠[2]. Prompt caching and data residency multipliers apply on top⁠[2].

Fast mode on Opus 4.8 and Opus 5 is in research preview and available only on the Claude API⁠[2]. Requests need the fast-mode-2026-02-01 beta header, and access to fast mode on Opus 5 requires contacting an account manager or joining the waitlist⁠[2].

Fast mode on Opus 5.5 needs no beta header and runs on the Claude API, Claude Models on Google Cloud (Anthropic managed) and Microsoft Foundry hosted on Azure⁠[2]. Its rate limit is granted by default in the Start, Build and Scale usage tiers⁠[2].

Fast mode is not available with the Batch API or with a Priority Tier commitment⁠[2]. A request that exceeds the rate limit can be retried at standard speed, but requests at different speeds do not share cached prefixes, so the prompt cache misses⁠[2].

Sources

  1. [1]Anthropic - Claude Platform release notes
  2. [2]Anthropic - Fast mode