Prices

What changed since 2025-06-01

1446 recorded entries from 2025-06-01 (UTC) to the last recompute, 2026-11-14T20:34:06+00:00. Dates are the day the ledger first saw a change; each row names the snapshot before it, so a change happened between the two. List prices, not transacted prices.

Counts for the whole period

Sources that are stopped now 3; nothing from them is filled in

Only sources that are not updating today are listed. An outage in this period that has since recovered is not recorded and not listed.

  • baseten-pricing (baseten): last good read 2026-11-02.
  • cerebras-models (cerebras): last good read 2026-11-05.
  • together-pricing (together): last good read 2026-11-10.

2026-10 100

Date (UTC)ItemWhatSource
2026-10-23
after 2026-10-22
moonshotai/kimi-k2.6 via Inceptron (int4)openrouter · inference 0.5621 → 0.6026 USD (+7.2%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via Wafer (unknown)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via Together (unknown)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via Parasail (fp8)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via Novita (fp16)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via Nebius (fp4)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via InferenceNet (fp4)openrouter · inference New at 0.1 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via GMICloud (fp8)openrouter · inference New at 0.1425 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
minimax/minimax-m3.1-flash via DigitalOcean (unknown)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
google/gemma-4-31b-it via DekaLLM (unknown)openrouter · inference New at 0.14 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
google/gemma-4-26b-a4b-it via NextBit (bf16)openrouter · inference 0.0765 → 0.0675 USD (-11.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
google/gemma-3-12b-it via NextBit (int4)openrouter · inference 0.1 → 0.075 USD (-25.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash via PrimeIntellect (unknown)openrouter · inference 0.03 → 0.006 USD (-80.0%)per_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash via Morph (fp8)openrouter · inference 0.253 → 0.361 USD (+42.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash via ModelRun (fp4)openrouter · inference 0.2 → 0.17 USD (-15.0%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash via DigitalOcean (unknown)openrouter · inference 0.225 → 0.165 USD (-26.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash via Baidu (fp8)openrouter · inference 0.075 → 0.0537 USD (-28.4%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash-1017 via Reka (unknown)openrouter · inference 0.15 → 0.08 USD (-46.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash-1017 via Novita (fp8)openrouter · inference 0.3 → 0.24 USD (-20.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash-1017 via Nebius (fp8)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash-1017 via Morph (fp8)openrouter · inference 0.253 → 0.361 USD (+42.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash-1017 via Modal (unknown)openrouter · inference New at 0.25 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4.1-flash-1017 via DigitalOcean (unknown)openrouter · inference 0.3 → 0.225 USD (-25.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-pro via StreamLake (fp8)openrouter · inference 0.442656 → 0.692694 USD (+56.5%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-pro via Baidu (fp8)openrouter · inference 0.44109 → 0.70135 USD (+59.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-pro-0813 via Relace (fp4)openrouter · inference 0.1307 → 0.1188 USD (-9.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-pro-0813 via DekaLLM (unknown)openrouter · inference 0.88 → 1.08 USD (+22.7%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-pro-0813 via Baidu (fp8)openrouter · inference 0.1452 → 0.132 USD (-9.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-flash via StreamLake (fp8)openrouter · inference 0.07 → 0.04592 USD (-34.4%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-flash via Relace (fp4)openrouter · inference 0.05 → 0.0436 USD (-12.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-flash via Baidu (fp8)openrouter · inference 0.09086 → 0.04662 USD (-48.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-flash-0731 via StreamLake (fp8)openrouter · inference 0.132 → 0.088 USD (-33.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-22
deepseek/deepseek-v4-flash-0731 via Relace (fp4)openrouter · inference 0.0275 → 0.027 USD (-1.8%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-23
after 2026-10-23
minimax/minimax-m3 via SambaNova (unknown)sambanova · inference Removed, was 0.6 USDper_1m_tokens_in sambanova-models not verified now
2026-10-23
after 2026-10-23
minimax/minimax-m3.1-flash via SambaNova (unknown)sambanova · inference New at 0.3 USDper_1m_tokens_in sambanova-models
2026-10-23
after 2026-10-23
xiaomi/mimo-v2.5 via Novita (unknown)hf-router · inference Removed, was 0.168 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-23
after 2026-10-23
xiaomi/mimo-v2.5-pro via Novita (unknown)hf-router · inference Removed, was 0.522 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
thinkingmachines/inkling via DeepInfra (fp8)openrouter · inference Removed, was 0.95 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
qwen/qwen3-235b-a22b-2507 via Nebius (fp8)openrouter · inference Removed on 2026-10-22, listed again on 2026-11-11, was 0.2 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
minimax/minimax-m3.1-flash:free via Minimax (unknown)openrouter · inference Removed, was 0.0 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
minimax/minimax-m2.5 via Friendli (unknown)openrouter · inference Removed, was 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via Ionstream (unknown)openrouter · inference Removed, was 0.22 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4-pro via Parasail (fp8)openrouter · inference Removed, was 0.45 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.3 via Io Net (fp8)openrouter · inference 0.19 → 0.15 USD (-21.1%)per_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.3 via Inceptron (fp4)openrouter · inference 0.55 → 0.4 USD (-27.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Wafer (nvfp4)openrouter · inference 0.06 → 0.073 USD (+21.7%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Relace (unknown)openrouter · inference 0.0413 → 0.0052 USD (-87.4%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Reka (unknown)openrouter · inference 1.6 → 2.0 USD (+25.0%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Parasail (fp4)openrouter · inference 0.1875 → 0.15 USD (-20.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via OpenInference (fp4)openrouter · inference 0.15 → 0.0052 USD (-96.5%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Morph (fp8)openrouter · inference 1.149 → 0.142 USD (-87.6%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Inceptron (fp8)openrouter · inference 0.15 → 0.18 USD (+20.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Cohere (unknown)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.2 via StreamLake (fp8)openrouter · inference 0.6118 → 0.56 USD (-8.5%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.2 via Inceptron (fp4)openrouter · inference 0.69 → 0.55 USD (-20.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.2 via Baidu (fp8)openrouter · inference 0.6188 → 0.189 USD (-69.5%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
z-ai/glm-5.2 via Ambient (fp8)openrouter · inference New at 0.6 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
xiaomi/mimo-v2.6-flash via GMICloud (bf16)openrouter · inference 0.14 → 0.119 USD (-15.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
xiaomi/mimo-v2.6-flash via Cohere (unknown)openrouter · inference New at 0.14 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
tencent/hy4-preview via Cohere (unknown)openrouter · inference New at 0.834 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
reflection/beam-1.0-501b-a23b via DigitalOcean (unknown)openrouter · inference New at 0.4 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
qwen/qwen3.6-27b via Reka (unknown)openrouter · inference 3.0 → 3.2 USD (+6.7%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
moonshotai/kimi-k3 via ParetoAlpha (unknown)openrouter · inference New at 3.0 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
moonshotai/kimi-k3 via Parasail (fp4)openrouter · inference 4.5 → 3.0 USD (-33.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
moonshotai/kimi-k3 via Morph (fp8)openrouter · inference 0.875 → 1.014 USD (+15.9%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
moonshotai/kimi-k2.6 via Inceptron (int4)openrouter · inference 0.4946 → 0.5621 USD (+13.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
minimax/minimax-m3.1-flash via Minimax (unknown)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via Wafer (mxfp4)openrouter · inference 0.006 → 0.012 USD (+100.0%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via OpenInference (fp4)openrouter · inference 0.3 → 0.07 USD (-76.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via Morph (fp8)openrouter · inference 0.216 → 0.253 USD (+17.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via ModelRun (fp4)openrouter · inference New at 0.2 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via Cohere (unknown)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via Baidu (fp8)openrouter · inference 0.0342 → 0.075 USD (+119.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via OpenInference (fp4)openrouter · inference 0.3 → 0.07 USD (-76.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Morph (fp8)openrouter · inference 0.216 → 0.253 USD (+17.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Makora (fp8)openrouter · inference 0.3 → 0.15 USD (-50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Ionstream (unknown)openrouter · inference 0.02 → 0.019 USD (-5.0%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via GMICloud (fp8)openrouter · inference 0.3 → 0.18 USD (-40.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via DigitalOcean (unknown)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Decart (fp4)openrouter · inference 0.09 → 0.138 USD (+53.3%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Baidu (fp8)openrouter · inference New at 0.28 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4-pro via StreamLake (fp8)openrouter · inference 0.386976 → 0.442656 USD (+14.4%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4-pro via Baidu (fp8)openrouter · inference 0.3887 → 0.44109 USD (+13.5%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
deepseek/deepseek-v4-flash via Wafer (mxfp4)openrouter · inference 0.013 → 0.2 USD (+1438.5%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-22
after 2026-10-21
togethercomputer/tev1-4b-experimental via Together (unknown)hf-router · inference Removed, was 0.042 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
reflection/beam-1.0-501b-a23b-nvfp4 via Together (unknown)hf-router · inference Removed, was 0.4 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4 via Together (unknown)hf-router · inference Removed, was 0.15 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
meta-models/muse-spark-open-816b-a42b-nvfp4 via Together (unknown)hf-router · inference Removed, was 1.25 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash via Together (unknown)hf-router · inference Removed, was 0.3 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Together (unknown)hf-router · inference Removed, was 0.3 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.3 via Together (unknown)hf-router · inference Removed, was 1.4 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.3-flash via Together (unknown)hf-router · inference Removed, was 0.15 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
z-ai/glm-5.2 via Together (unknown)hf-router · inference Removed, was 1.4 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
thinkingmachines/inkling via Together (unknown)hf-router · inference Removed, was 1.0 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
openai/gpt-oss-120b via Together (unknown)hf-router · inference Removed, was 0.15 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
openai/gpt-oss-120b via Fireworks (unknown)hf-router · inference Removed, was 0.15 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
nvidia/nvidia-nemotron-3-ultra-550b-a55b-nvfp4 via Fireworks (unknown)hf-router · inference Removed, was 0.6 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
moonshotai/kimi-k3 via Together (unknown)hf-router · inference Removed, was 3.0 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
moonshotai/kimi-k3 via Fireworks (unknown)hf-router · inference Removed, was 3.0 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
meta-models/muse-glimmer-30b via Together (unknown)hf-router · inference Removed, was 0.35 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now

Older entriesSame data: JSON, MCP tool changes_since.

Cite this

Free to reuse under CC BY 4.0 with this credit.

InfraRabbit, list-price changes since 2025-06-01, as of 2026-11-14T20:34:06+00:00, https://infrarabbit.com/prices/changes?since=2025-06-01&category=inference

All recent changes · largest moves per category (JSON)