Skip to content

providers: sync vendor rates (2026-10-15, review) - #262

Merged
jaredLunde merged 2 commits into
mainfrom
rates/sync-2026-10-15
Oct 16, 2026
Merged

providers: sync vendor rates (2026-10-15, review)#262
jaredLunde merged 2 commits into
mainfrom
rates/sync-2026-10-15

Conversation

@github-actions

@github-actions github-actions Bot commented Oct 15, 2026

Copy link
Copy Markdown
Contributor

Needs review. A routine rule failed:

  • added: OpenRouter deepseek/deepseek-v4-pro-0813 @ relace/fp4
  • added: OpenRouter deepseek/deepseek-v4.1-flash @ baseten/fp32
  • added: OpenRouter deepseek/deepseek-v4.1-flash @ cloudflare
  • added: OpenRouter deepseek/deepseek-v4.1-flash @ primeintellect
  • added: OpenRouter minimax/minimax-m3 @ modelrun/fp8
  • added: OpenRouter moonshotai/kimi-k2.7-code @ phala
  • added: OpenRouter z-ai/glm-5.2 @ alibaba/fp8/us-east-1
  • added: OpenRouter z-ai/glm-5.2 @ baseten/fp8/us
  • added: OpenRouter z-ai/glm-5.2 @ baseten/us/fast
  • added: OpenRouter z-ai/glm-5.2 @ relace
  • added: OpenRouter z-ai/glm-5.3 @ alibaba/prime
  • added: OpenRouter z-ai/glm-5.3 @ baseten/fp4/us
  • added: OpenRouter z-ai/glm-5.3 @ baseten/us/fast
  • added: OpenRouter z-ai/glm-5.3 @ mistral/nvfp4/eu
  • added: OpenRouter z-ai/glm-5.3 @ modelrun/fp4
  • added: OpenRouter z-ai/glm-5.3 @ relace
  • added: OpenRouter z-ai/glm-5.3-flash @ baseten/fp8/us
  • added: OpenRouter z-ai/glm-5.3-flash @ makora
  • added: OpenRouter z-ai/glm-5.3-flash @ nextbit/fp4
  • removed: OpenRouter deepseek/deepseek-v4-pro-0813 @ reka
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4: standard.cache_read moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4: standard.cache_write_5m moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4: standard.input moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4: standard.output moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us: standard.cache_read moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us: standard.cache_write_5m moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us: standard.input moved more than 2x
  • OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us: standard.output moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ atlas-cloud/fp8: standard.cache_read moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8: standard.cache_read moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8: standard.cache_write_5m moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8: standard.input moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8: standard.output moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ coreweave/fp8: standard.cache_read moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ ionstream: standard.cache_write_5m moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ ionstream: standard.input moved more than 2x
  • OpenRouter deepseek/deepseek-v4.1-flash @ open-inference/fp4: standard.cache_read moved more than 2x
  • removed: OpenRouter minimax/minimax-m3 @ modelrun/fp4
  • OpenRouter moonshotai/kimi-k3 @ relace/fp4: standard.cache_write_5m moved more than 2x
  • OpenRouter moonshotai/kimi-k3 @ relace/fp4: standard.input moved more than 2x
  • OpenRouter moonshotai/kimi-k3 @ wafer: standard.cache_write_5m moved more than 2x
  • OpenRouter moonshotai/kimi-k3 @ wafer: standard.input moved more than 2x
  • OpenRouter moonshotai/kimi-k3 @ wafer/us: standard.cache_write_5m moved more than 2x
  • OpenRouter moonshotai/kimi-k3 @ wafer/us: standard.input moved more than 2x
  • removed: OpenRouter qwen/qwen3.8-2.4t-a95b @ modal
  • OpenRouter qwen/qwen3.8-27b @ modelrun/fp4: standard.cache_write_5m moved more than 2x
  • OpenRouter qwen/qwen3.8-27b @ modelrun/fp4: standard.input moved more than 2x
  • OpenRouter qwen/qwen3.8-27b @ tenstorrent/fp4: standard.output moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fast: standard.cache_read moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fast: standard.cache_write_5m moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fast: standard.input moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fast: standard.output moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fp8: standard.cache_read moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fp8: standard.cache_write_5m moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fp8: standard.input moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ baidu/fp8: standard.output moved more than 2x
  • removed: OpenRouter z-ai/glm-5.2 @ decart/mxfp4
  • OpenRouter z-ai/glm-5.2 @ inceptron/fp4: standard.output moved more than 2x
  • removed: OpenRouter z-ai/glm-5.2 @ inference-net/fp4
  • OpenRouter z-ai/glm-5.2 @ morph/fp8: standard.cache_write_5m moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ morph/fp8: standard.input moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ wafer/us: standard.cache_read moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ wafer/us: standard.cache_write_5m moved more than 2x
  • OpenRouter z-ai/glm-5.2 @ wafer/us: standard.input moved more than 2x
  • removed: OpenRouter z-ai/glm-5.3 @ alibaba/fast
  • OpenRouter z-ai/glm-5.3 @ baidu/fp8: standard.cache_read moved more than 2x
  • OpenRouter z-ai/glm-5.3 @ baidu/fp8: standard.cache_write_5m moved more than 2x
  • OpenRouter z-ai/glm-5.3 @ baidu/fp8: standard.input moved more than 2x
  • OpenRouter z-ai/glm-5.3 @ baidu/fp8: standard.output moved more than 2x
  • OpenRouter z-ai/glm-5.3 @ inceptron/fp4: standard.output moved more than 2x
  • OpenRouter z-ai/glm-5.3-flash @ inference-net/fp4: standard.output moved more than 2x
  • OpenRouter z-ai/glm-5.3-flash @ morph/fp8: standard.cache_write_5m moved more than 2x
  • OpenRouter z-ai/glm-5.3-flash @ morph/fp8: standard.input moved more than 2x
  • OpenRouter z-ai/glm-5.3-flash @ near-ai/fp8: standard.cache_read moved more than 2x
  • OpenRouter z-ai/glm-5.3-flash @ open-inference/fp4: standard.cache_read moved more than 2x
  • OpenRouter z-ai/glm-5.3-flash @ wafer: standard.cache_read moved more than 2x
Item Rate Old New Source
OpenRouter deepseek/deepseek-v4-pro-0813 @ baidu/fp8 standard.cache_read $0.007938/MTok $0.006426/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ baidu/fp8 standard.cache_write_5m $0.24948/MTok $0.20196/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ baidu/fp8 standard.input $0.24948/MTok $0.20196/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ baidu/fp8 standard.output $0.74844/MTok $0.60588/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4 standard.cache_read $0.033/MTok $0.1866/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4 standard.cache_write_5m $0.4/MTok $0.8957/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4 standard.input $0.4/MTok $0.8957/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/fp4 standard.output $3/MTok $0.99/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us standard.cache_read $0.033/MTok $0.1866/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us standard.cache_write_5m $0.4/MTok $0.8957/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us standard.input $0.4/MTok $0.8957/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ sail-research/us standard.output $3/MTok $0.99/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4-pro-0813 @ wafer standard.cache_read $0.2/MTok $0.249/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-pro-0813/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ atlas-cloud/fp8 standard.cache_read $0.03/MTok $0.00384/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ atlas-cloud/fp8 standard.cache_write_5m $0.3/MTok $0.192/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ atlas-cloud/fp8 standard.input $0.3/MTok $0.192/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ atlas-cloud/fp8 standard.output $1.2/MTok $0.768/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8 standard.cache_read $0.006/MTok $0.002994/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8 standard.cache_write_5m $0.3/MTok $0.1497/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8 standard.input $0.3/MTok $0.1497/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ baidu/fp8 standard.output $1.2/MTok $0.5988/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ coreweave/fp8 standard.cache_read $0.03/MTok $0.006/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ coreweave/fp8 standard.cache_write_5m $0.2/MTok $0.15/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ coreweave/fp8 standard.input $0.2/MTok $0.15/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ digitalocean standard.cache_write_5m $0.165/MTok $0.225/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ digitalocean standard.input $0.165/MTok $0.225/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ digitalocean standard.output $0.66/MTok $0.9/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ inference-net/fp8 standard.cache_write_5m $0.077/MTok $0.1/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ inference-net/fp8 standard.input $0.077/MTok $0.1/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ inference-net/fp8 standard.output $0.55/MTok $0.66/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ ionstream standard.cache_read $0.01/MTok $0.005/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ ionstream standard.cache_write_5m $0.1/MTok $0.27/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ ionstream standard.input $0.1/MTok $0.27/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ ionstream standard.output $0.75/MTok $1.1/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ morph/fp8 standard.cache_write_5m $0.042/MTok $0.033/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ morph/fp8 standard.input $0.042/MTok $0.033/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ open-inference/fp4 standard.cache_read $0.0336/MTok $0.0054/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ open-inference/fp4 standard.cache_write_5m $0.0336/MTok $0.02376/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ open-inference/fp4 standard.input $0.0336/MTok $0.02376/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ open-inference/fp4 standard.output $1.188/MTok $0.72/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ relace standard.cache_read $0.008/MTok $0.01/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ relace standard.cache_write_5m $0.05/MTok $0.0264/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ relace standard.input $0.05/MTok $0.0264/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ relace standard.output $0.6/MTok $0.8/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ sail-research/fp4 standard.cache_read $0.01/MTok $0.006/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ sail-research/fp4 standard.cache_write_5m $0.08/MTok $0.09/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ sail-research/fp4 standard.input $0.08/MTok $0.09/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ sail-research/fp4 standard.output $0.4/MTok $0.3/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ wafer standard.cache_read $0.034/MTok $0.02/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ wafer standard.cache_write_5m $0.07/MTok $0.1/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ wafer standard.input $0.07/MTok $0.1/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter deepseek/deepseek-v4.1-flash @ wafer standard.output $0.99/MTok $0.65/MTok https://openrouter.ai/api/v1/models/deepseek/deepseek-v4.1-flash/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ io-net/bf16 standard.cache_read $0.049/MTok $0.041/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ io-net/bf16 standard.cache_write_5m $0.123/MTok $0.11/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ io-net/bf16 standard.input $0.123/MTok $0.11/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ io-net/bf16 standard.output $0.35/MTok $0.32/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ makora standard.cache_read $0.032/MTok $0.05/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ makora standard.cache_write_5m $0.08/MTok $0.1/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ makora standard.input $0.08/MTok $0.1/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter google/gemma-4-26b-a4b-it @ makora standard.output $0.32/MTok $0.28/MTok https://openrouter.ai/api/v1/models/google/gemma-4-26b-a4b-it/endpoints
OpenRouter moonshotai/kimi-k2.6 @ baidu/fp4 standard.cache_read $0.0728/MTok $0.07344/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ baidu/fp4 standard.cache_write_5m $0.43225/MTok $0.43605/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ baidu/fp4 standard.input $0.43225/MTok $0.43605/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ baidu/fp4 standard.output $1.82/MTok $1.836/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ inceptron/int4 standard.cache_read $0.1149/MTok $0.1312/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ inceptron/int4 standard.cache_write_5m $0.4323/MTok $0.4365/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ inceptron/int4 standard.input $0.4323/MTok $0.4365/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k2.6 @ inceptron/int4 standard.output $2.45/MTok $3.2/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k2.6/endpoints
OpenRouter moonshotai/kimi-k3 @ decart/mxfp4 standard.cache_read $0.255/MTok $0.213/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ decart/mxfp4 standard.cache_write_5m $2.55/MTok $2.13/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ decart/mxfp4 standard.input $2.55/MTok $2.13/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ decart/mxfp4 standard.output $12.75/MTok $10.65/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fast standard.cache_read $0.45/MTok $0.35/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fast standard.cache_write_5m $2.99/MTok $2.49/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fast standard.input $2.99/MTok $2.49/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fp4 standard.cache_read $0.55/MTok $0.28/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fp4 standard.cache_write_5m $0.73/MTok $0.45/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fp4 standard.input $0.73/MTok $0.45/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ inference-net/fp4 standard.output $10/MTok $15/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ morph/fp8 standard.cache_write_5m $1/MTok $0.8/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ morph/fp8 standard.input $1/MTok $0.8/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ relace/fp4 standard.cache_write_5m $2/MTok $0.32/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ relace/fp4 standard.input $2/MTok $0.32/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ together standard.cache_read $0.27/MTok $0.3/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ together standard.cache_write_5m $2.7/MTok $3/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ together standard.input $2.7/MTok $3/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ together standard.output $13.5/MTok $15/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ wafer standard.cache_write_5m $0.72/MTok $0.31/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ wafer standard.input $0.72/MTok $0.31/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ wafer/us standard.cache_read $0.3/MTok $0.32/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ wafer/us standard.cache_write_5m $2.8/MTok $0.33/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ wafer/us standard.input $2.8/MTok $0.33/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter moonshotai/kimi-k3 @ wafer/us standard.output $15.5/MTok $14.9/MTok https://openrouter.ai/api/v1/models/moonshotai/kimi-k3/endpoints
OpenRouter openai/gpt-5.6-sol @ openai long.cache_read $0.4/MTok $0.8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai long.cache_write_5m $5/MTok $10/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai long.input $4/MTok $8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai long.output $15/MTok $30/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai standard.cache_read $0.2/MTok $0.4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai standard.cache_write_5m $2.5/MTok $5/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai standard.input $2/MTok $4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai standard.output $10/MTok $20/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast long.cache_read $0.8/MTok $1.6/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast long.cache_write_5m $10/MTok $20/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast long.input $8/MTok $16/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast long.output $30/MTok $60/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast standard.cache_read $0.4/MTok $0.8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast standard.cache_write_5m $5/MTok $10/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast standard.input $4/MTok $8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/fast standard.output $20/MTok $40/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex long.cache_read $0.2/MTok $0.4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex long.cache_write_5m $2.5/MTok $5/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex long.input $2/MTok $4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex long.output $7.5/MTok $15/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex standard.cache_read $0.1/MTok $0.2/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex standard.cache_write_5m $1.25/MTok $2.5/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex standard.input $1/MTok $2/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol @ openai/flex standard.output $5/MTok $10/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai long.cache_read $0.4/MTok $0.8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai long.cache_write_5m $5/MTok $10/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai long.input $4/MTok $8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai long.output $15/MTok $30/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai standard.cache_read $0.2/MTok $0.4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai standard.cache_write_5m $2.5/MTok $5/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai standard.input $2/MTok $4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai standard.output $10/MTok $20/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast long.cache_read $0.8/MTok $1.6/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast long.cache_write_5m $10/MTok $20/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast long.input $8/MTok $16/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast long.output $30/MTok $60/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast standard.cache_read $0.4/MTok $0.8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast standard.cache_write_5m $5/MTok $10/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast standard.input $4/MTok $8/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/fast standard.output $20/MTok $40/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex long.cache_read $0.2/MTok $0.4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex long.cache_write_5m $2.5/MTok $5/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex long.input $2/MTok $4/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex long.output $7.5/MTok $15/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex standard.cache_read $0.1/MTok $0.2/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex standard.cache_write_5m $1.25/MTok $2.5/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex standard.input $1/MTok $2/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter openai/gpt-5.6-sol-pro @ openai/flex standard.output $5/MTok $10/MTok https://openrouter.ai/api/v1/models/openai/gpt-5.6-sol-pro/endpoints
OpenRouter qwen/qwen3.8-27b @ darkbloom/fp4 standard.cache_read $0.025/MTok $0.0175/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ darkbloom/fp4 standard.cache_write_5m $0.05/MTok $0.035/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ darkbloom/fp4 standard.input $0.05/MTok $0.035/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ modelrun/fp4 standard.cache_read $0.135/MTok $0.09/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ modelrun/fp4 standard.cache_write_5m $0.7/MTok $0.2/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ modelrun/fp4 standard.input $0.7/MTok $0.2/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ modelrun/fp4 standard.output $4.7/MTok $2.5/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ tenstorrent/fp4 standard.cache_read $0.018/MTok $0.009/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ tenstorrent/fp4 standard.cache_write_5m $0.04/MTok $0.02/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ tenstorrent/fp4 standard.input $0.04/MTok $0.02/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ tenstorrent/fp4 standard.output $1.35/MTok $0.5/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter qwen/qwen3.8-27b @ wafer standard.cache_read $0.0198/MTok $0.039/MTok https://openrouter.ai/api/v1/models/qwen/qwen3.8-27b/endpoints
OpenRouter z-ai/glm-5.2 @ alibaba/fp8 standard.cache_read $0.224/MTok $0.1932/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ alibaba/fp8 standard.cache_write_5m $1.12/MTok $0.966/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ alibaba/fp8 standard.input $1.12/MTok $0.966/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ alibaba/fp8 standard.output $3.52/MTok $3.036/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fast standard.cache_read $0.18872/MTok $0.56/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fast standard.cache_write_5m $0.75825/MTok $2.25/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fast standard.input $0.75825/MTok $2.25/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fast standard.output $2.65556/MTok $7.88/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fp8 standard.cache_read $0.0312/MTok $0.11492/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fp8 standard.cache_write_5m $0.168/MTok $0.6188/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fp8 standard.input $0.168/MTok $0.6188/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ baidu/fp8 standard.output $0.528/MTok $1.9448/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ coreweave/fp4 standard.cache_write_5m $0.76/MTok $0.62/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ coreweave/fp4 standard.input $0.76/MTok $0.62/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ inceptron/fp4 standard.cache_write_5m $0.95/MTok $0.69/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ inceptron/fp4 standard.input $0.95/MTok $0.69/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ inceptron/fp4 standard.output $1.056/MTok $3.15/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ morph/fp8 standard.cache_read $0.137/MTok $0.079/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ morph/fp8 standard.cache_write_5m $0.4/MTok $0.079/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ morph/fp8 standard.input $0.4/MTok $0.079/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ siliconflow/fp8 standard.cache_read $0.221/MTok $0.13/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ siliconflow/fp8 standard.cache_write_5m $1.19/MTok $0.7/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ siliconflow/fp8 standard.input $1.19/MTok $0.7/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ siliconflow/fp8 standard.output $3.74/MTok $2.2/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ streamlake/fp8 standard.cache_read $0.11934/MTok $0.113854/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ streamlake/fp8 standard.cache_write_5m $0.6426/MTok $0.61306/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ streamlake/fp8 standard.input $0.6426/MTok $0.61306/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ streamlake/fp8 standard.output $2.0196/MTok $1.92676/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ wafer/us standard.cache_read $0.059/MTok $0.019/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ wafer/us standard.cache_write_5m $0.06/MTok $0.02/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.2 @ wafer/us standard.input $0.06/MTok $0.02/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.2/endpoints
OpenRouter z-ai/glm-5.3 @ baidu/fp8 standard.cache_read $0.03692/MTok $0.26/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ baidu/fp8 standard.cache_write_5m $0.1988/MTok $1.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ baidu/fp8 standard.input $0.1988/MTok $1.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ baidu/fp8 standard.output $0.6248/MTok $4.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ crusoe/fp4 standard.cache_read $0.26/MTok $0.13/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ decart/fp4 standard.cache_read $0.22/MTok $0.163/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ decart/fp4 standard.cache_write_5m $0.96/MTok $0.84/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ decart/fp4 standard.input $0.96/MTok $0.84/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ decart/fp4 standard.output $3.04/MTok $4.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ inceptron/fp4 standard.cache_read $0.2/MTok $0.18/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ inceptron/fp4 standard.cache_write_5m $0.6/MTok $0.55/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ inceptron/fp4 standard.input $0.6/MTok $0.55/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ inceptron/fp4 standard.output $0.6248/MTok $2.2/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ inference-net/fp4 standard.cache_read $0.055/MTok $0.06/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ inference-net/fp4 standard.output $4.4/MTok $4.8/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ mistral/nvfp4 standard.cache_read $0.154/MTok $0.14/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ mistral/nvfp4 standard.cache_write_5m $1.54/MTok $1.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ mistral/nvfp4 standard.input $1.54/MTok $1.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ mistral/nvfp4 standard.output $4.84/MTok $4.4/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ morph/fp8 standard.cache_read $0.06/MTok $0.076/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ morph/fp8 standard.cache_write_5m $0.055/MTok $0.076/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ morph/fp8 standard.input $0.055/MTok $0.076/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ morph/fp8 standard.output $5/MTok $6/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ sail-research/fp8 standard.cache_read $0.15/MTok $0.14/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ sail-research/fp8 standard.cache_write_5m $0.2/MTok $0.15/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ sail-research/fp8 standard.input $0.2/MTok $0.15/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ sail-research/us standard.cache_read $0.15/MTok $0.14/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ sail-research/us standard.cache_write_5m $0.2/MTok $0.15/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ sail-research/us standard.input $0.2/MTok $0.15/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ siliconflow/fp8 standard.cache_read $0.208/MTok $0.13/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ siliconflow/fp8 standard.cache_write_5m $1.12/MTok $0.7/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ siliconflow/fp8 standard.input $1.12/MTok $0.7/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ siliconflow/fp8 standard.output $3.52/MTok $2.2/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ wafer standard.cache_read $0.16/MTok $0.169/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3 @ wafer/us standard.cache_read $0.059/MTok $0.078/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3/endpoints
OpenRouter z-ai/glm-5.3-flash @ coreweave/nvfp4 standard.cache_read $0.05/MTok $0.029/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ digitalocean standard.cache_write_5m $0.15/MTok $0.13125/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ digitalocean standard.input $0.15/MTok $0.13125/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ digitalocean standard.output $0.5/MTok $0.4375/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ inceptron/fp8 standard.cache_write_5m $0.0696/MTok $0.108/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ inceptron/fp8 standard.input $0.0696/MTok $0.108/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ inference-net/fp4 standard.cache_write_5m $0.07/MTok $0.083/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ inference-net/fp4 standard.input $0.07/MTok $0.083/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ inference-net/fp4 standard.output $0.05/MTok $0.15/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ morph/fp8 standard.cache_read $0.015/MTok $0.028/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ morph/fp8 standard.cache_write_5m $0.029/MTok $0.071/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ morph/fp8 standard.input $0.029/MTok $0.071/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ near-ai/fp8 standard.cache_read $0.0245/MTok $0.012/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ near-ai/fp8 standard.cache_write_5m $0.105/MTok $0.08/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ near-ai/fp8 standard.input $0.105/MTok $0.08/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ near-ai/fp8 standard.output $0.35/MTok $0.5/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ open-inference/fp4 standard.cache_read $0.0232/MTok $0.01125/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ open-inference/fp4 standard.cache_write_5m $0.0232/MTok $0.036/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ open-inference/fp4 standard.input $0.0232/MTok $0.036/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ open-inference/fp4 standard.output $1.2/MTok $0.9/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ wafer standard.cache_read $0.012/MTok $0.06/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ wafer standard.cache_write_5m $0.06/MTok $0.12/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
OpenRouter z-ai/glm-5.3-flash @ wafer standard.input $0.06/MTok $0.12/MTok https://openrouter.ai/api/v1/models/z-ai/glm-5.3-flash/endpoints
card together:moonshotai/Kimi-K3 standard.cache_read $0.27/MTok $0.3/MTok https://api.together.xyz/v1/models
card together:moonshotai/Kimi-K3 standard.cache_write_5m $2.7/MTok $3/MTok https://api.together.xyz/v1/models
card together:moonshotai/Kimi-K3 standard.input $2.7/MTok $3/MTok https://api.together.xyz/v1/models
card together:moonshotai/Kimi-K3 standard.output $13.5/MTok $15/MTok https://api.together.xyz/v1/models

Settled [[conflict]] entries (their sources agree again, so the agreed value is the table's; removed from verify/catalog_truth.toml):

  • together:moonshotai/Kimi-K3 cache_read

RATE_VERSION is bumped (rates-sync rate-version), and every golden vector in verify/pricing_vectors.json that priced a moved rate is recomputed by the independent reference pricer (verify/pricing_reference.py). A human merges this PR.

Snapshots that changed: anthropic.pricing, xai.pricing, together.models, together.docs, together.pricing, openrouter.models, openrouter.endpoints/deepseek/deepseek-v4-pro-0813, openrouter.endpoints/deepseek/deepseek-v4.1-flash, openrouter.endpoints/google/gemma-4-26b-a4b-it, openrouter.endpoints/minimax/minimax-m3, openrouter.endpoints/moonshotai/kimi-k2.6, openrouter.endpoints/moonshotai/kimi-k2.7-code, openrouter.endpoints/moonshotai/kimi-k3, openrouter.endpoints/openai/gpt-5.6-sol, openrouter.endpoints/openai/gpt-5.6-sol-pro, openrouter.endpoints/qwen/qwen3.8-2.4t-a95b, openrouter.endpoints/qwen/qwen3.8-27b, openrouter.endpoints/z-ai/glm-5.2, openrouter.endpoints/z-ai/glm-5.3, openrouter.endpoints/z-ai/glm-5.3-flash

@github-actions github-actions Bot added the rates-review Automatic rate sync: a change a human must review before merging label Oct 15, 2026
@jaredLunde
jaredLunde enabled auto-merge October 16, 2026 06:27
@github-actions
providers: sync vendor rates (2026-10-15, review)
999ad56 
Generated by the rates-drift workflow (rates-sync classify: review).
@github-actions
github-actions Bot force-pushed the rates/sync-2026-10-15 branch from 5cc1d20 to 999ad56 Compare October 16, 2026 08:22
@jaredLunde @claude
rates-sync: conflict tests bring their own [[conflict]], not the live…
61d5276 
… Kimi K3 promotion

Together's Kimi K3 promotion ended (models API, docs table and pricing page all
$3 / $0.30 cached / $15 on 2026-10-15/16), so the sync settled and removed the
[[conflict]] the two classify tests edited the snapshot around. Each now injects
the promotion-era conflict into the spec itself and edits the models snapshot by
model id, so a vendor settling a real conflict no longer breaks the suite.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JimHGjsfk2Ktm5GxyZJKKk
@jaredLunde jaredLunde mentioned this pull request Oct 16, 2026
Closed
@jaredLunde
jaredLunde added this pull request to the merge queue Oct 16, 2026
Merged via the queue into main with commit d8df85f Oct 16, 2026
13 checks passed
@jaredLunde
jaredLunde deleted the rates/sync-2026-10-15 branch October 16, 2026 16:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

rates-review Automatic rate sync: a change a human must review before merging

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@jaredLunde