Prices

What changed since 2026-05-01

1446 recorded entries from 2026-05-01 (UTC) to the last recompute, 2026-11-14T19:29:03+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.

2026-11 100

Date (UTC)ItemWhatSource
2026-11-04
after 2026-11-03
deepseek/deepseek-v4-flash via Cloudflare (unknown)openrouter · inference Removed, was 0.44 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
deepseek/deepseek-v4-flash-vision-exp via SiliconFlow (fp8)openrouter · inference Removed, was 0.44 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
deepseek/deepseek-v3.2 via SambaNova (unknown)openrouter · inference Removed, was 3.0 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
deepseek/deepseek-v3.2 via Mara (unknown)openrouter · inference Removed, was 3.0 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
deepseek/deepseek-chat-v3.1 via Mara (unknown)openrouter · inference Removed, was 0.6 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
z-ai/glm-5.3 via Morph (fp8)openrouter · inference 0.078 → 0.12 USD (+53.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
z-ai/glm-5.3 via Io Net (fp8)openrouter · inference 0.15 → 0.11 USD (-26.7%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
z-ai/glm-5.3 via Cloudflare (unknown)openrouter · inference 1.4 → 0.7 USD (-50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
z-ai/glm-5.3-flash via Sail Research (fp4)openrouter · inference 0.35 → 0.175 USD (-50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
z-ai/glm-5.3-flash via NextBit (fp4)openrouter · inference 0.045 → 0.03 USD (-33.3%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
z-ai/glm-5.3-flash via Morph (fp8)openrouter · inference 0.3 → 0.268 USD (-10.7%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
z-ai/glm-5.2 via Morph (fp8)openrouter · inference 0.078 → 0.12 USD (+53.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
qwen/qwen3.8-27b via StreamLake (unknown)openrouter · inference 0.5 → 0.3 USD (-40.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
qwen/qwen3.8-27b via PrimeIntellect (fp8)openrouter · inference 0.006 → 0.023 USD (+283.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
qwen/qwen3.6-35b-a3b via PrimeIntellect (fp8)openrouter · inference 0.011 → 0.01 USD (-9.1%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
openai/gpt-oss-20b via PrimeIntellect (fp4)openrouter · inference 0.006 → 0.02 USD (+233.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
openai/gpt-oss-120b via PrimeIntellect (fp4)openrouter · inference 0.043 → 0.031 USD (-27.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
nvidia/nemotron-3-super-120b-a12b via DeepInfra (bf16)openrouter · inference 0.085 → 0.075 USD (-11.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
moonshotai/kimi-k3 via Sail Research (fp4)openrouter · inference 0.23 → 0.336 USD (+46.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
moonshotai/kimi-k3 via Relace (fp4)openrouter · inference 0.1824 → 0.1729 USD (-5.2%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
moonshotai/kimi-k3 via ParetoAlpha (unknown)openrouter · inference 3.0 → 1.0 USD (-66.7%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
moonshotai/kimi-k3 via Morph (fp8)openrouter · inference 0.4 → 0.35 USD (-12.5%)per_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
moonshotai/kimi-k3 via Makora (fp4)openrouter · inference 0.5 → 0.36 USD (-28.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
moonshotai/kimi-k2.6 via Inceptron (int4)openrouter · inference 3.5 → 3.75 USD (+7.1%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
google/gemma-4-31b-it via PrimeIntellect (fp8)openrouter · inference 0.235 → 0.073 USD (-68.9%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-04
after 2026-11-03
google/gemma-4-26b-a4b-it via PrimeIntellect (bf16)openrouter · inference 0.062 → 0.07 USD (+12.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash via OpenInference (fp4)openrouter · inference 0.035 → 0.0366 USD (+4.6%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash via Morph (fp8)openrouter · inference 0.05 → 0.035 USD (-30.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash-1017 via StreamLake (fp8)openrouter · inference 0.15 → 0.144 USD (-4.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash-1017 via StepFun (fp8)openrouter · inference 0.195 → 0.15 USD (-23.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash-1017 via Reka (unknown)openrouter · inference 0.06 → 0.16 USD (+166.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash-1017 via OpenInference (fp4)openrouter · inference 0.035 → 0.0333 USD (-4.9%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash-1017 via Morph (fp8)openrouter · inference 0.05 → 0.035 USD (-30.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4-pro-0813 via Sail Research (fp4)openrouter · inference 0.675 → 1.35 USD (+100.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4-flash-0731 via Wafer (nvfp4)openrouter · inference 0.14 → 0.13 USD (-7.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
x-ai/grok-4.7:batch via xAI (unknown)openrouter · inference New at 1.6 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
x-ai/grok-4.6:batch via xAI (unknown)openrouter · inference New at 1.6 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
reflection/beam-1.0-501b-a23b via CoreWeave (nvfp4)openrouter · inference New at 0.3 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4.1-flash-1017 via DekaLLM (unknown)openrouter · inference New at 0.18 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-11-04
after 2026-11-03
deepseek/deepseek-v4-pro via Nebius (fp8)openrouter · inference New at 1.75 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-4b-instruct-2507 via nscale (unknown)hf-router · inference Removed, was 0.01 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
openai/gpt-oss-20b via nscale (unknown)hf-router · inference Removed, was 0.05 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
openai/gpt-oss-120b via nscale (unknown)hf-router · inference Removed, was 0.1 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
meta-llama/llama-4-scout-17b-16e-instruct via nscale (unknown)hf-router · inference Removed, was 0.09 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
meta-llama/llama-3.1-8b-instruct via nscale (unknown)hf-router · inference Removed, was 0.06 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
deepseek/deepseek-r1-distill-qwen-7b via nscale (unknown)hf-router · inference Removed, was 0.15 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
deepseek/deepseek-r1-distill-qwen-14b via nscale (unknown)hf-router · inference Removed, was 0.2 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
deepseek/deepseek-r1-distill-llama-8b via nscale (unknown)hf-router · inference Removed, was 0.05 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-8b via nscale (unknown)hf-router · inference Removed, was 0.07 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-4b-thinking-2507 via nscale (unknown)hf-router · inference Removed, was 0.01 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-32b via nscale (unknown)hf-router · inference Removed, was 0.08 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-235b-a22b via nscale (unknown)hf-router · inference Removed, was 0.2 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-235b-a22b-instruct-2507 via nscale (unknown)hf-router · inference Removed, was 0.2 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen3-14b via nscale (unknown)hf-router · inference Removed, was 0.07 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen2.5-coder-7b-instruct via nscale (unknown)hf-router · inference Removed, was 0.01 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen2.5-coder-3b-instruct via nscale (unknown)hf-router · inference Removed, was 0.01 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-03
qwen/qwen2.5-coder-32b-instruct via nscale (unknown)hf-router · inference Removed, was 0.06 USDper_1m_tokens_in hf-inference-providers community cross-check not verified now
2026-11-03
after 2026-11-02
xiaomi/mimo-v2.6-flash via Relace (fp4)openrouter · inference Removed, was 0.087 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
deepseek/deepseek-v4.1-flash-1017 via Makora (fp8)openrouter · inference Removed on 2026-11-03, listed again on 2026-11-05, was 0.15 USDper_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via AkashML (fp8)openrouter · inference Removed, was 0.19 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
xiaomi/mimo-v2.6-pro via Novita (fp8)openrouter · inference Removed, was 0.435 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
xiaomi/mimo-v2.6-flash via Novita (fp8)openrouter · inference Removed, was 0.14 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
nousresearch/hermes-3-llama-3.1-70b via DeepInfra (fp8)openrouter · inference Removed, was 0.7 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
nousresearch/hermes-3-llama-3.1-405b via DeepInfra (fp8)openrouter · inference Removed, was 1.0 USDper_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via PrimeIntellect (unknown)openrouter · inference 0.98 → 0.5 USD (-49.0%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via Makora (fp4)openrouter · inference 0.14 → 0.18 USD (+28.6%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via Io Net (fp8)openrouter · inference 0.19 → 0.15 USD (-21.1%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via Inceptron (fp4)openrouter · inference 2.64 → 3.96 USD (+50.0%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via Decart (fp4)openrouter · inference 2.7 → 2.71 USD (+0.4%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3 via CoreWeave (fp8)openrouter · inference 1.2 → 0.75 USD (-37.5%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
z-ai/glm-5.3-flashx via Z.AI (fp8)openrouter · inference 0.09 → 0.075 USD (-16.7%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3-flash via OpenInference (fp4)openrouter · inference 0.16 → 0.22 USD (+37.5%)per_1m_tokens_out openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3-flash via NextBit (fp4)openrouter · inference 0.11 → 0.12 USD (+9.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.3-flash via Makora (unknown)openrouter · inference 0.024 → 0.04 USD (+66.7%)per_1m_tokens_cached_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
z-ai/glm-5.3-flash via Inceptron (fp8)openrouter · inference 0.19 → 0.16 USD (-15.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.2 via StreamLake (fp8)openrouter · inference 0.55552 → 0.61306 USD (+10.4%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
z-ai/glm-5.2 via Inceptron (fp4)openrouter · inference 0.16 → 0.19 USD (+18.8%)per_1m_tokens_cached_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
xiaomi/mimo-v2.6-pro via GMICloud (bf16)openrouter · inference 0.435 → 0.348 USD (-20.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
xiaomi/mimo-v2.6-flash via GMICloud (bf16)openrouter · inference 0.14 → 0.112 USD (-20.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
tencent/hy4-preview via DeepInfra (fp4)openrouter · inference 0.7923 → 0.834 USD (+5.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
qwen/qwen3.8-27b via Reka (fp8)openrouter · inference 0.04 → 0.15 USD (+275.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
qwen/qwen3.8-27b via PrimeIntellect (fp8)openrouter · inference 0.004 → 0.006 USD (+50.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
qwen/qwen3.8-27b via Mancer 2 (fp8)openrouter · inference 0.18 → 0.175 USD (-2.8%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
qwen/qwen3.6-35b-a3b via PrimeIntellect (fp8)openrouter · inference 0.01 → 0.012 USD (+20.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
qwen/qwen3.5-9b via PrimeIntellect (bf16)openrouter · inference 0.018 → 0.02 USD (+11.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
openai/gpt-oss-20b via PrimeIntellect (fp4)openrouter · inference 0.007 → 0.006 USD (-14.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
openai/gpt-oss-120b via PrimeIntellect (fp4)openrouter · inference 0.033 → 0.043 USD (+30.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
openai/gpt-oss-120b via Mancer 2 (fp8)openrouter · inference 0.05 → 0.055 USD (+10.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
moonshotai/kimi-k3 via Morph (fp8)openrouter · inference 1.278 → 1.42 USD (+11.1%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
moonshotai/kimi-k2.6 via Inceptron (int4)openrouter · inference 0.6825 → 0.78 USD (+14.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
google/gemma-4-31b-it via PrimeIntellect (fp8)openrouter · inference 0.165 → 0.235 USD (+42.4%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
google/gemma-4-26b-a4b-it via PrimeIntellect (bf16)openrouter · inference 0.021 → 0.062 USD (+195.2%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
google/gemma-4-26b-a4b-it via NextBit (bf16)openrouter · inference 0.0675 → 0.0765 USD (+13.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
google/gemma-4-26b-a4b-it via Makora (unknown)openrouter · inference 0.07 → 0.08 USD (+14.3%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
google/gemma-4-26b-a4b-it via Darkbloom (unknown)openrouter · inference 0.024 → 0.04 USD (+66.7%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
deepseek/deepseek-v4.1-flash via Relace (fp4)openrouter · inference 0.035 → 0.3 USD (+757.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
deepseek/deepseek-v4.1-flash via PrimeIntellect (unknown)openrouter · inference 0.3 → 0.156 USD (-48.0%)per_1m_tokens_in openrouter-endpoints community cross-check not verified now
2026-11-03
after 2026-11-02
deepseek/deepseek-v4.1-flash via Mancer 2 (fp8)openrouter · inference 0.2 → 0.15 USD (-25.0%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
deepseek/deepseek-v4.1-flash-1017 via Wafer (mxfp4)openrouter · inference 0.13 → 0.16 USD (+23.1%)per_1m_tokens_in openrouter-endpoints community cross-check
2026-11-03
after 2026-11-02
deepseek/deepseek-v4.1-flash-1017 via StreamLake (fp8)openrouter · inference 0.12 → 0.15 USD (+25.0%)per_1m_tokens_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 2026-05-01, as of 2026-11-14T19:29:03+00:00, https://infrarabbit.com/prices/changes?since=2026-05-01&category=inference

All recent changes · largest moves per category (JSON)