Get started
The market log

33 events in a year. Then 155 in the next.

Every model-market event Vitna has recorded since Mar 2023, newest first. Each entry links to a primary source on a domain the provider itself publishes on, and carries the date that source was last fetched; the newest of those checks is 2026-11-19. The log only ever gains entries.

01 / 03Density
10 of 216 events. policy.

Every event at its true date, newest left.

10 of 216 events on the axisMar 2023 to Nov 2026
launchprice movepolicydeprecationavailability
02 / 03Detected moves, sized
83 moves · cuts left, rises right

Each move as a share of the price before it.

  1. 19 Nov 2026Novita AIKimi K3, Novita AIper 1M tokens
    1. cache write price, 1 hour retention, Novita AI Kimi K3$6.00 → $0.30 · -95%
    2. cache write price, 5 minute retention, Novita AI Kimi K3$3.00 → $6.00 · +100%
    3. cached input price, Novita AI Kimi K3$0.30 → $3.00 · +900%
  2. 19 Nov 2026Novita AIQwen3.8-Max, Novita AIper 1M tokens
    1. cache write price, 5 minute retention, Novita AI Qwen3.8-Max$2.50 → $0.25 · -90%
    2. cached input price, Novita AI Qwen3.8-Max$0.25 → $2.50 · +900%
  3. 19 Nov 2026Novita AIQwen3.8-Flash, Novita AIper 1M tokens
    1. cache write price, 5 minute retention, Novita AI Qwen3.8-Flash$0.20 → $0.016 · -92%
    2. cached input price, Novita AI Qwen3.8-Flash$0.016 → $0.20 · +1150%
  4. 16 Nov 2026Together AIQwen Image 2.0, Together AIper image
    1. per image, Together AI Qwen Image 2.0$0.04 → $0.035 · -12%
  5. 16 Nov 2026Together AIQwen Image 2.0 Pro, Together AIper image
    1. per image, Together AI Qwen Image 2.0 Pro$0.08 → $0.075 · -6.3%
  6. 16 Nov 2026Together AIGemini 3.1 Flash Image (Nano Banana 2), Together AIper image
    1. per image, Together AI Gemini 3.1 Flash Image (Nano Banana 2)$0.05 → $0.0466 · -6.9%
  7. 16 Nov 2026DeepgramNova-3 Multilingual, Deepgramper audio-minute
    1. streaming transcription, Deepgram Nova-3 Multilingual$0.0092 → $0.0058 · -37%
  8. 16 Nov 2026DeepgramNova-3 Monolingual, Deepgramper audio-minute
    1. streaming transcription, Deepgram Nova-3 Monolingual$0.0077 → $0.0048 · -38%
  9. 16 Nov 2026DeepgramFlux English, Deepgramper audio-minute
    1. streaming transcription, Deepgram Flux English$0.0077 → $0.0065 · -16%
  10. 16 Nov 2026LambdaA100 80GB, Lambdaper GPU-hour
    1. on-demand list price, Lambda A100 80GB$2.79 → $3.19 · +14%
  11. 16 Nov 2026LambdaB200, Lambdaper GPU-hour
    1. on-demand list price, Lambda B200$6.69 → $7.69 · +15%
  12. 16 Nov 2026LambdaH100 SXM, Lambdaper GPU-hour
    1. on-demand list price, Lambda H100 SXM$3.99 → $4.59 · +15%
  13. 13 Nov 2026RunPodH100 SXM, RunPodper GPU-hour
    1. on-demand list price, RunPod H100 SXM$3.99 → $4.39 · +10%
  14. 7 Nov 2026LlamaIndexLlamaParse Agentic Plus, LlamaIndexper page
    1. structure from a page, LlamaIndex LlamaParse Agentic Plus$0.0563 → $0.0375 · -33%
  15. 7 Nov 2026LlamaIndexLlamaParse Agentic, LlamaIndexper page
    1. structure from a page, LlamaIndex LlamaParse Agentic$0.0125 → $0.015 · +20%
  16. 7 Nov 2026LlamaIndexLlamaParse Cost-effective, LlamaIndexper page
    1. structure from a page, LlamaIndex LlamaParse Cost-effective$0.00375 → $0.0045 · +20%
  17. 7 Nov 2026LlamaIndexLlamaParse Fast, LlamaIndexper page
    1. text from a page, LlamaIndex LlamaParse Fast$0.00125 → $0.0015 · +20%
  18. 6 Nov 2026Together AIQwen3.7-Max, Together AIper 1M tokens
    1. output price, Together AI Qwen3.7-Max$4.50 → $7.50 · +67%
    2. cached input price, Together AI Qwen3.7-Max$0.30 → $0.50 · +67%
    3. input price, Together AI Qwen3.7-Max$1.50 → $2.50 · +67%
  19. 3 Nov 2026DeepInfraNVIDIA-Nemotron-3-Super-120B-A12B, DeepInfraper 1M tokens
    1. input price, DeepInfra NVIDIA-Nemotron-3-Super-120B-A12B$0.085 → $0.075 · -12%
  20. 2 Nov 2026DeepgramNova-3 Multilingual, Deepgramper audio-minute
    1. streaming transcription, Deepgram Nova-3 Multilingual$0.0058 → $0.0092 · +59%
  21. 2 Nov 2026DeepgramNova-3 Monolingual, Deepgramper audio-minute
    1. streaming transcription, Deepgram Nova-3 Monolingual$0.0048 → $0.0077 · +60%
  22. 2 Nov 2026DeepgramFlux English, Deepgramper audio-minute
    1. streaming transcription, Deepgram Flux English$0.0065 → $0.0077 · +18%
  23. 15 Oct 2026RunPodB200, RunPodper GPU-hour
    1. on-demand list price, RunPod B200$6.79 → $7.99 · +18%
  24. 15 Oct 2026RunPodH200, RunPodper GPU-hour
    1. on-demand list price, RunPod H200$4.59 → $5.29 · +15%
  25. 15 Oct 2026RunPodH100 SXM, RunPodper GPU-hour
    1. on-demand list price, RunPod H100 SXM$3.49 → $3.99 · +14%
  26. 13 Oct 2026Together AIKimi K3, Together AIper 1M tokens
    1. cached input price, Together AI Kimi K3$0.27 → $0.30 · +11%
  27. 12 Oct 2026Together AIKimi K3, Together AIper 1M tokens
    1. output price, Together AI Kimi K3$13.50 → $15.00 · +11%
    2. input price, Together AI Kimi K3$2.70 → $3.00 · +11%
  28. 8 Oct 2026DeepInfraMistral-Nemo-Instruct-2407, DeepInfraper 1M tokens
    1. input price, DeepInfra Mistral-Nemo-Instruct-2407$0.019 → $0.029 · +53%
  29. 7 Oct 2026AnthropicClaude Sonnet 5.5, Anthropicper 1M tokens
    1. cached input price, Anthropic Claude Sonnet 5.5$0.20 → $0.10 · -50%
  30. 5 Oct 2026Together AIKimi K3, Together AIper 1M tokens
    1. output price, Together AI Kimi K3$15.00 → $13.50 · -10%
    2. cached input price, Together AI Kimi K3$0.30 → $0.27 · -10%
    3. input price, Together AI Kimi K3$3.00 → $2.70 · -10%
  31. 5 Oct 2026Together AIQwen3.8-Flash, Together AIper 1M tokens
    1. output price, Together AI Qwen3.8-Flash$0.28 → $0.47 · +68%
    2. input price, Together AI Qwen3.8-Flash$0.09 → $0.15 · +67%
  32. 4 Oct 2026DeepInfragemma-4-31B-it, DeepInfraper 1M tokens
    1. input price, DeepInfra gemma-4-31B-it$0.15 → $0.20 · +33%
  33. 2 Oct 2026DeepInfraQwen3.6-35B-A3B, DeepInfraper 1M tokens
    1. output price, DeepInfra Qwen3.6-35B-A3B$0.95 → $0.10 · -89%
  34. 1 Oct 2026DeepInfragemma-4-31B-it, DeepInfraper 1M tokens
    1. output price, DeepInfra gemma-4-31B-it$0.38 → $0.40 · +5.3%
    2. input price, DeepInfra gemma-4-31B-it$0.13 → $0.15 · +15%
  35. 29 Sep 2026DeepInfraNVIDIA-Nemotron-3.5-Lightning, DeepInfraper 1M tokens
    1. output price, DeepInfra NVIDIA-Nemotron-3.5-Lightning$0.20 → $0.16 · -20%
    2. cached input price, DeepInfra NVIDIA-Nemotron-3.5-Lightning$0.04 → $0.03 · -25%
    3. input price, DeepInfra NVIDIA-Nemotron-3.5-Lightning$0.08 → $0.06 · -25%
  36. 22 Sep 2026Together AIQwen3.7-Max, Together AIper 1M tokens
    1. output price, Together AI Qwen3.7-Max$7.50 → $4.50 · -40%
    2. cached input price, Together AI Qwen3.7-Max$0.25 → $0.30 · +20%
    3. input price, Together AI Qwen3.7-Max$2.50 → $1.50 · -40%
  37. 22 Sep 2026Together AIQwen3.8-Flash, Together AIper 1M tokens
    1. output price, Together AI Qwen3.8-Flash$0.47 → $0.28 · -40%
    2. input price, Together AI Qwen3.8-Flash$0.15 → $0.09 · -40%
  38. 16 Sep 2026Together AIQwen3.7-Max, Together AIper 1M tokens
    1. output price, Together AI Qwen3.7-Max$6.00 → $7.50 · +25%
    2. input price, Together AI Qwen3.7-Max$2.00 → $2.50 · +25%
  39. 11 Sep 2026AzureGPT-5.6 Sol, Azureper 1M tokens
    1. output price, Azure GPT-5.6 Sol$30.00 → $20.00 · -33%
    2. cached input price, Azure GPT-5.6 Sol$0.50 → $0.40 · -20%
    3. input price, Azure GPT-5.6 Sol$5.00 → $4.00 · -20%
  40. 10 Sep 2026Together AIQwen3.7-Max, Together AIper 1M tokens
    1. output price, Together AI Qwen3.7-Max$3.75 → $6.00 · +60%
    2. cached input price, Together AI Qwen3.7-Max$0.13 → $0.25 · +92%
    3. input price, Together AI Qwen3.7-Max$1.25 → $2.00 · +60%
  41. 9 Sep 2026Novita AIMacaron V1 Tall, Novita AIper 1M tokens
    1. output price, Novita AI Macaron V1 Tall$2.60 → $1.43 · -45%
    2. cached input price, Novita AI Macaron V1 Tall$0.08 → $0.044 · -45%
    3. input price, Novita AI Macaron V1 Tall$0.45 → $0.247 · -45%
  42. 9 Sep 2026Novita AIMacaron V1 Venti, Novita AIper 1M tokens
    1. output price, Novita AI Macaron V1 Venti$4.50 → $2.48 · -45%
    2. cached input price, Novita AI Macaron V1 Venti$0.30 → $0.165 · -45%
    3. input price, Novita AI Macaron V1 Venti$1.50 → $0.825 · -45%
  43. 9 Sep 2026Novita AIDeepSeek V4 Pro 0813, Novita AIper 1M tokens
    1. cached input price, Novita AI DeepSeek V4 Pro 0813$0.132 → $0.044 · -67%
  44. 8 Sep 2026GoogleGemini Robotics ER 2 Streaming Preview, Googleper 1M tokens
    1. output price, Google Gemini Robotics ER 2 Streaming Preview$10.00 → $5.00 · -50%
    2. input price, Google Gemini Robotics ER 2 Streaming Preview$2.00 → $1.00 · -50%
  45. 8 Sep 2026GoogleGemini Robotics ER 2 Preview, Googleper 1M tokens
    1. batch output price, Google Gemini Robotics ER 2 Preview$5.00 → $2.50 · -50%
    2. batch input price, Google Gemini Robotics ER 2 Preview$1.00 → $0.50 · -50%
    3. output price, Google Gemini Robotics ER 2 Preview$10.00 → $5.00 · -50%
    4. cached input price, Google Gemini Robotics ER 2 Preview$0.20 → $0.10 · -50%
    5. input price, Google Gemini Robotics ER 2 Preview$2.00 → $1.00 · -50%
  46. 6 Sep 2026DeepInfraDeepSeek V4 Flash 0731, DeepInfraper 1M tokens
    1. cached input price, DeepInfra DeepSeek V4 Flash 0731$0.016 → $0.015 · -6.3%
    2. input price, DeepInfra DeepSeek V4 Flash 0731$0.08 → $0.06 · -25%
  47. 6 Sep 2026RunPodH100 SXM, RunPodper GPU-hour
    1. on-demand list price, RunPod H100 SXM$3.29 → $3.49 · +6.1%
  48. 1 Sep 2026DeepInfraClaude Sonnet 5, DeepInfraper 1M tokens
    1. output price, DeepInfra Claude Sonnet 5$10.00 → $15.00 · +50%
    2. input price, DeepInfra Claude Sonnet 5$2.00 → $3.00 · +50%
  49. 28 Aug 2026Together AIQwen3.8-2.4T-A95B, Together AIper 1M tokens
    1. output price, Together AI Qwen3.8-2.4T-A95B$6.25 → $6.00 · -4%
    2. cached input price, Together AI Qwen3.8-2.4T-A95B$0.50 → $0.25 · -50%
    3. input price, Together AI Qwen3.8-2.4T-A95B$2.50 → $2.00 · -20%

83 detected moves carry both of their periods, so each bar is the move as a share of the price before it: cuts run left, rises run right, and the longest bar is the largest move. Each model leads to its own page and each meter to the move's own page. Curated entries cite an announcement rather than two readings and list below without a bar.

03 / 03The ledger
newest first

Every entry, with the document behind it.

  1. 2026Anthropicpolicy

    Claude Opus 4.1 retired

    Corrected. The row that supersedes this one stands in the record.

    Deprecated June 5 with 60 days' notice; requests to the model now fail. The recommended replacement is Opus 4.8.

    source
  2. Anthropicpolicy

    US export-control directive suspends Fable 5 and Mythos 5

    All customer access disabled three days after launch; restored at the end of June.

    source
  3. Googlepolicy

    Flex and Priority inference tiers open on the Gemini API

    Two service levels at two prices for the same models, the latency-for-money trade the batch discount makes in reverse.

    source
  4. Anthropicpolicy

    The 1M token context window leaves beta at standard pricing

    Requests over 200k tokens work with no beta header on Opus 4.6 and Sonnet 4.6, and are billed at the same per-token rate as a short one.

    source
  5. Anthropicpolicy

    US-only inference is priced at a premium

    Data residency controls arrive with the inference_geo parameter; pinning inference to the US costs 1.1x standard rates on models released after 1 February 2026.

    source
  6. 2025Anthropicpolicy

    Global endpoint pricing introduced on Bedrock and Vertex AI

    Regional routing starts carrying a premium over global on the partner clouds. First-party Claude API pricing is unaffected.

    source
  7. 2024Anthropicpolicy

    The Message Batches API opens at half the standard rate

    Large asynchronous batches are processed for 50 percent less, matching the discount OpenAI set in April.

    source
  8. OpenAIpolicy

    Prompt caching, distillation and the Realtime API arrive together

    Caching lands on the same day as the Realtime API, model distillation, image fine-tuning and Evals.

    source
  9. Anthropicpolicy

    Prompt caching enters beta on the Claude API

    A cached prompt prefix is re-read at a fraction of the input rate, which changes the unit price of a repeated system prompt rather than the model.

    source
  10. OpenAIpolicy

    The Batch API arrives and halves the rate for patient work

    Asynchronous request processing at a discount to the synchronous rate, the first time latency is priced separately from capability.

    source
Inclusion rule

An event appears here only with a primary-source URL verified on the date the entry carries. Secondary coverage can corroborate a date but never stands as the source. A detected price move is published only after a second read at least an hour later agrees, and cites the archived document either side of it.

By the week

A week with 3 events or more is a page of its own, with its counts, its sized moves and every entry in it. The newest is the week of 16 Nov 2026, with 16 price moves, and all 16 are listed by week.

Follow it

This log is published as a JSON Feed at /api/v1/feed.json, public and with no key, carrying every entry here and the decisions the engine has proposed against them, and as RSS at /log/rss.xml for a feed reader, with the same items under the same ids. Every headline above is also a page of its own, at an address that keeps pointing at it. Nothing in either feed is a recommendation to act.