Prices

What changed since 2024-09-01

1446 recorded entries from 2024-09-01 (UTC) to the last recompute, 2026-11-14T21:38:36+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
2026-10-22
after 2026-10-21
meta-llama/llama-3.3-70b-instruct via Together (unknown)hf-router · inference Removed, was 1.04 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4-pro-0813 via Together (unknown)hf-router · inference Removed, was 1.32 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
deepseek/deepseek-v4-flash-0731 via Together (unknown)hf-router · inference Removed, was 0.14 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
qwen/qwen3.8-2.4t-a95b via Together (unknown)hf-router · inference Removed, was 2.0 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
qwen/qwen3.5-9b via Together (unknown)hf-router · inference Removed, was 0.17 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-22
after 2026-10-21
minimax/minimax-m3 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
minimax/minimax-m3 via Fireworks (unknown)hf-router · inference Removed, was 0.3 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-20
xiaomi/mimo-v2.5 via Xiaomi (fp8)openrouter · inference Removed, was 0.14 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
xiaomi/mimo-v2.5-pro via Xiaomi (fp8)openrouter · inference Removed, was 0.435 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
qwen/qwen3.5-9b via Venice (fp8)openrouter · inference Removed, was 0.1 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
google/gemini-2.5-flash-lite:batch via Google AI Studio (unknown)openrouter · inference Removed, was 0.05 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
z-ai/glm-5.3 via Nebius (fp4)openrouter · inference None → 0.26 USDper_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3 via Inceptron (fp4)openrouter · inference 1.0 → 1.96 USD (+96.0%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3 via Amazon Bedrock (unknown)openrouter · inference New at 1.68 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash:batch via DeepInfra (fp4)openrouter · inference 0.06 → 0.12 USD (+100.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via StreamLake (fp8)openrouter · inference 0.058845 → 0.0435 USD (-26.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via Relace (unknown)openrouter · inference 0.075 → 0.0413 USD (-44.9%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via Reka (unknown)openrouter · inference 0.06 → 0.08 USD (+33.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via OpenInference (fp4)openrouter · inference 0.047076 → 0.15 USD (+218.6%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via NextBit (fp4)openrouter · inference 0.12 → 0.15 USD (+25.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via Morph (fp8)openrouter · inference 0.168 → 1.149 USD (+583.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via Inceptron (fp8)openrouter · inference 0.1 → 0.15 USD (+50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.3-flash via DeepInfra (fp4)openrouter · inference 0.075 → 0.15 USD (+100.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
z-ai/glm-5.2 via Nebius (fp4)openrouter · inference None → 0.14 USDper_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
xiaomi/mimo-v2.6-pro via StreamLake (unknown)openrouter · inference New at 0.522 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
xiaomi/mimo-v2.6-flash via Relace (mxfp4)openrouter · inference 0.05 → 0.13 USD (+160.0%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
reflection/beam-1.0-501b-a23b via Nebius (fp8)openrouter · inference None → 0.05 USDper_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
reflection/beam-1.0-501b-a23b via BaseTen (fp4)openrouter · inference 1.3 → 0.4 USD (-69.2%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
recursive/flint-v1.0:free via Recursive (bf16)openrouter · inference New at 0.0 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
nvidia/nemotron-3.5-super-vl via Io Net (nvfp4)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
moonshotai/kimi-k3 via Morph (fp8)openrouter · inference 0.977 → 0.875 USD (-10.4%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
moonshotai/kimi-k2.7-code via Nebius (fp4)openrouter · inference None → 0.15 USDper_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
moonshotai/kimi-k2.6 via Inceptron (int4)openrouter · inference 0.441 → 0.4946 USD (+12.2%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
moonshotai/kimi-k2.6 via Baidu (fp4)openrouter · inference 0.42275 → 0.44935 USD (+6.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
meta/muse-spark-open via Nebius (fp4)openrouter · inference None → 0.15 USDper_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
meta/muse-spark-open via Makora (fp4)openrouter · inference New at 1.25 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via Sail Research (fp4)openrouter · inference 0.101 → 0.09 USD (-10.9%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via Reka (unknown)openrouter · inference New at 0.105 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via OpenInference (fp4)openrouter · inference 0.02832 → 0.3 USD (+959.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via Nebius (fp8)openrouter · inference None → 0.01 USDper_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via Morph (fp8)openrouter · inference 0.158 → 0.216 USD (+36.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via Ionstream (unknown)openrouter · inference 0.27 → 0.22 USD (-18.5%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash via Baidu (fp8)openrouter · inference 0.0354 → 0.0342 USD (-3.4%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via Sail Research (fp4)openrouter · inference New at 0.101 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via Reka (unknown)openrouter · inference New at 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via Phala (unknown)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via OpenInference (fp4)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via Morph (fp8)openrouter · inference 0.158 → 0.216 USD (+36.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via Makora (fp8)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via Ionstream (unknown)openrouter · inference New at 0.22 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4.1-flash-1017 via AtlasCloud (fp8)openrouter · inference 0.3 → 0.195 USD (-35.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-pro via StreamLake (fp8)openrouter · inference 0.339648 → 0.386976 USD (+13.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-pro via Baidu (fp8)openrouter · inference 0.338 → 0.3887 USD (+15.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-pro-0813 via Sail Research (fp4)openrouter · inference 0.9 → 0.45 USD (-50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-flash-0731 via Relace (fp4)openrouter · inference 0.057 → 0.0422 USD (-26.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-flash-0731 via Reka (unknown)openrouter · inference 0.021 → 0.05 USD (+138.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-flash-0731 via Inceptron (fp4)openrouter · inference 0.13 → 0.11 USD (-15.4%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-20
deepseek/deepseek-v4-flash-0731 via Baidu (fp8)openrouter · inference 0.1298 → 0.04444 USD (-65.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-21
after 2026-10-21
togethercomputer/tev1-4b-experimental via Together (unknown)hf-router · inference New at 0.042 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-21
reflection/beam-1.0-501b-a23b-nvfp4 via Together (unknown)hf-router · inference New at 0.4 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-21
nvidia/nvidia-nemotron-3.5-super-vl-120b-a12b-nvfp4 via Together (unknown)hf-router · inference New at 0.15 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-21
meta-models/muse-spark-open-816b-a42b-nvfp4 via Together (unknown)hf-router · inference New at 1.25 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-21
deepseek/deepseek-v4.1-flash via Together (unknown)hf-router · inference New at 0.3 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-21
deepseek/deepseek-v4.1-flash-1017 via Together (unknown)hf-router · inference New at 0.3 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-10-21
after 2026-10-20
reflection/beam-1.0-501b-a23b via BaseTen (unknown)hf-router · inference 1.3 → 0.4 USD (-69.2%)per_1m_tokens_in hf-inference-providers community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-4.7-flash via Venice (fp8)openrouter · inference Removed, was 0.06 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
xiaomi/mimo-v2.5 via StreamLake (unknown)openrouter · inference Removed, was 0.168 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
xiaomi/mimo-v2.5-pro via StreamLake (unknown)openrouter · inference Removed, was 0.522 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
qwen/qwen3.8-27b via Tenstorrent (fp4)openrouter · inference Removed on 2026-10-20, listed again on 2026-10-22, was 0.02 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
moonshotai/kimi-k2.7-code via Phala (unknown)openrouter · inference Removed, was 0.95 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
inclusionai/ling-3.1-flash via DeepInfra (mxfp4)openrouter · inference Removed, was 0.075 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-pro:batch via Google (unknown)openrouter · inference Removed, was 0.625 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-pro via Google (unknown)openrouter · inference Removed, was 1.25 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-pro-preview via Google (unknown)openrouter · inference Removed, was 1.25 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-flash:batch via Google (unknown)openrouter · inference Removed, was 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-flash via Google (unknown)openrouter · inference Removed, was 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-flash-lite:batch via Google (unknown)openrouter · inference Removed, was 0.05 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
google/gemini-2.5-flash-lite via Google (unknown)openrouter · inference Removed, was 0.1 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
deepseek/deepseek-v4-flash via OpenInference (fp4)openrouter · inference Removed, was 0.00864 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
deepseek/deepseek-v4-flash-0731 via OpenInference (fp4)openrouter · inference Removed, was 0.00912 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
z-ai/glm-5.3 via Novita (fp8)openrouter · inference 0.7 → 0.63 USD (-10.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.3 via Morph (fp8)openrouter · inference 0.051 → 0.289 USD (+466.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.3 via Inceptron (fp4)openrouter · inference 1.4 → 1.0 USD (-28.6%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.3-flash via StreamLake (fp8)openrouter · inference 0.073845 → 0.058845 USD (-20.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.3-flash via Reka (unknown)openrouter · inference 0.04 → 0.06 USD (+50.0%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.3-flash via OpenInference (fp4)openrouter · inference 0.048 → 0.047076 USD (-1.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.3-flash via Morph (fp8)openrouter · inference 0.153 → 0.168 USD (+9.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.2 via StreamLake (fp8)openrouter · inference 0.61306 → 0.6118 USD (-0.2%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.2 via Morph (fp8)openrouter · inference 0.051 → 0.289 USD (+466.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
z-ai/glm-5.2 via Decart (fp4)openrouter · inference 2.5 → 1.2 USD (-52.0%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
z-ai/glm-5.2 via Baidu (fp4)openrouter · inference 2.25 → 0.61875 USD (-72.5%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
xiaomi/mimo-v2.6-pro via DeepInfra (fp8)openrouter · inference 0.43 → 0.387 USD (-10.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
xiaomi/mimo-v2.6-flash via Relace (mxfp4)openrouter · inference 0.2 → 0.05 USD (-75.0%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-10-20
after 2026-10-19
upstage/solar-pro4 via Upstage (unknown)openrouter · inference 0.09 → 0.15 USD (+66.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
qwen/qwen3.8-27b via Wafer (fp8)openrouter · inference 0.04 → 0.06 USD (+50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
qwen/qwen3.8-27b via Modal (unknown)openrouter · inference New at 0.04 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
qwen/qwen3.6-35b-a3b via Parasail (fp8)openrouter · inference 0.15 → 0.1 USD (-33.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
nvidia/nemotron-3.5-super-vl via DeepInfra (fp4)openrouter · inference 0.1 → 0.15 USD (+50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
nvidia/nemotron-3.5-super-vl via BaseTen (fp4)openrouter · inference New at 0.2 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-10-20
after 2026-10-19
moonshotai/kimi-k3 via Sail Research (fp4)openrouter · inference 0.4 → 0.2 USD (-50.0%)per_1m_tokens_cached_in openrouter-endpoints community cross-check

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 2024-09-01, as of 2026-11-14T21:38:36+00:00, https://infrarabbit.com/prices/changes?since=2024-09-01&category=inference

All recent changes · largest moves per category (JSON)