tokenprice

LLM API price changes

Every change we observed on the official price lists, newest first. The date is the first fetch that showed the new price; the previous price was last seen at the time given in "previous seen".

Announced, not yet in force

FromModelPriceNowFrom thenChange
2026-12-01 Gemini 4 Argon Cache read · Standard $0.10 $0.20 +100%
2026-12-01 Gemini 4 Argon Input · Standard $2.00 $4.00 +100%
2026-12-01 Gemini 4 Argon Output · Standard $10.00 $20.00 +100%
2026-12-01 Gemini 4 Argon Cache read · Batch API $0.05 $0.10 +100%
2026-12-01 Gemini 4 Argon Input · Batch API $1.00 $2.00 +100%
2026-12-01 Gemini 4 Argon Output · Batch API $5.00 $10.00 +100%
2026-12-01 Gemini 4 Argon Cache read · Flex $0.05 $0.10 +100%
2026-12-01 Gemini 4 Argon Input · Flex $1.00 $2.00 +100%
2026-12-01 Gemini 4 Argon Output · Flex $5.00 $10.00 +100%
2026-12-01 Gemini 4 Argon Cache read · Priority $0.18 $0.36 +100%
2026-12-01 Gemini 4 Argon Input · Priority $3.60 $7.20 +100%
2026-12-01 Gemini 4 Argon Output · Priority $18.00 $36.00 +100%
2027-01-01 Gemini 3.6 Flash Cache read · Standard $0.075 $0.15 +100%
2027-01-01 Gemini 3.6 Flash Input · Standard $0.75 $1.50 +100%
2027-01-01 Gemini 3.6 Flash Output · Standard $3.75 $7.50 +100%
2027-01-01 Gemini 3.6 Flash Cache read · Batch API $0.0375 $0.075 +100%
2027-01-01 Gemini 3.6 Flash Input · Batch API $0.375 $0.75 +100%
2027-01-01 Gemini 3.6 Flash Output · Batch API $1.875 $3.75 +100%
2027-01-01 Gemini 3.6 Flash Cache read · Flex $0.0375 $0.075 +100%
2027-01-01 Gemini 3.6 Flash Input · Flex $0.375 $0.75 +100%
2027-01-01 Gemini 3.6 Flash Output · Flex $1.875 $3.75 +100%
2027-01-01 Gemini 3.6 Flash Cache read · Priority $0.135 $0.27 +100%
2027-01-01 Gemini 3.6 Flash Input · Priority $1.35 $2.70 +100%
2027-01-01 Gemini 3.6 Flash Output · Priority $6.75 $13.50 +100%
2027-01-01 Gemini 3.8 Flash Cache read · Standard $0.075 $0.15 +100%
2027-01-01 Gemini 3.8 Flash Input · Standard $0.75 $1.50 +100%
2027-01-01 Gemini 3.8 Flash Output · Standard $3.75 $7.50 +100%
2027-01-01 Gemini 3.8 Flash Cache read · Batch API $0.0375 $0.075 +100%
2027-01-01 Gemini 3.8 Flash Input · Batch API $0.375 $0.75 +100%
2027-01-01 Gemini 3.8 Flash Output · Batch API $1.875 $3.75 +100%
2027-01-01 Gemini 3.8 Flash Cache read · Flex $0.0375 $0.075 +100%
2027-01-01 Gemini 3.8 Flash Input · Flex $0.375 $0.75 +100%
2027-01-01 Gemini 3.8 Flash Output · Flex $1.875 $3.75 +100%
2027-01-01 Gemini 3.8 Flash Cache read · Priority $0.135 $0.27 +100%
2027-01-01 Gemini 3.8 Flash Input · Priority $1.35 $2.70 +100%
2027-01-01 Gemini 3.8 Flash Output · Priority $6.75 $13.50 +100%
2027-01-01 Gemini Robotics ER 2 Preview Cache read · Standard $0.10 $0.20 +100%
2027-01-01 Gemini Robotics ER 2 Preview Input · Standard $1.00 $2.00 +100%
2027-01-01 Gemini Robotics ER 2 Preview Audio input · Standard $1.00 $2.00 +100%
2027-01-01 Gemini Robotics ER 2 Preview Output · Standard $5.00 $10.00 +100%
2027-01-01 Gemini Robotics ER 2 Preview Cache read · Batch API $0.05 $0.10 +100%
2027-01-01 Gemini Robotics ER 2 Preview Input · Batch API $0.50 $1.00 +100%
2027-01-01 Gemini Robotics ER 2 Preview Audio input · Batch API $0.50 $1.00 +100%
2027-01-01 Gemini Robotics ER 2 Preview Output · Batch API $2.50 $5.00 +100%
2027-01-01 Gemini Robotics ER 2 Streaming Preview Input · Standard $1.00 $2.00 +100%
2027-01-01 Gemini Robotics ER 2 Streaming Preview Audio input · Standard $1.00 $2.00 +100%
2027-01-01 Gemini Robotics ER 2 Streaming Preview Output · Standard $5.00 $10.00 +100%

Observed changes

DateModelPriceOldNewChangePrevious seen
2026-11-01 DeepSeek V4 Pro 0813 Cache read · Standard new — $0.13 · source
2026-11-01 DeepSeek V4 Pro 0813 Context window · Standard new — 1,048,576 · source
2026-11-01 DeepSeek V4 Pro 0813 Input · Standard new — $1.32 · source
2026-11-01 DeepSeek V4 Pro 0813 Output · Standard new — $3.96 · source
2026-11-01 DeepSeek V4.1 Flash Cache read · Standard new — $0.006 · source
2026-11-01 DeepSeek V4.1 Flash Context window · Standard new — 1M · source
2026-11-01 DeepSeek V4.1 Flash Input · Standard new — $0.30 · source
2026-11-01 DeepSeek V4.1 Flash Output · Standard new — $1.20 · source
2026-11-01 DeepSeek V4.1 Flash 1017 Cache read · Standard new — $0.006 · source
2026-11-01 DeepSeek V4.1 Flash 1017 Context window · Standard new — 1M · source
2026-11-01 DeepSeek V4.1 Flash 1017 Input · Standard new — $0.30 · source
2026-11-01 DeepSeek V4.1 Flash 1017 Output · Standard new — $1.20 · source
2026-11-01 Muse Glimmer 30B Cache read · Standard new — $0.04 · source
2026-11-01 Muse Glimmer 30B Context window · Standard new — 131,072 · source
2026-11-01 Muse Glimmer 30B Input · Standard new — $0.35 · source
2026-11-01 Muse Glimmer 30B Output · Standard new — $1.50 · source
2026-11-01 Muse Spark Open 816B A42B Cache read · Standard new — $0.15 · source
2026-11-01 Muse Spark Open 816B A42B Context window · Standard new — 1,048,576 · source
2026-11-01 Muse Spark Open 816B A42B Input · Standard new — $1.25 · source
2026-11-01 Muse Spark Open 816B A42B Output · Standard new — $4.25 · source
2026-11-01 MiniMax M3.1 Flash Cache read · Standard new — $0.015 · source
2026-11-01 MiniMax M3.1 Flash Context window · Standard new — 1,048,576 · source
2026-11-01 MiniMax M3.1 Flash Input · Standard new — $0.15 · source
2026-11-01 MiniMax M3.1 Flash Output · Standard new — $0.60 · source
2026-11-01 Kimi K3 Cache read · Standard new — $0.30 · source
2026-11-01 Kimi K3 Context window · Standard new — 1,048,576 · source
2026-11-01 Kimi K3 Input · Standard new — $3.00 · source
2026-11-01 Kimi K3 Output · Standard new — $15.00 · source
2026-11-01 NVIDIA Nemotron 3.5 Super VL Cache read · Standard new — $0.02 · source
2026-11-01 NVIDIA Nemotron 3.5 Super VL Context window · Standard new — 262,144 · source
2026-11-01 NVIDIA Nemotron 3.5 Super VL Input · Standard new — $0.15 · source
2026-11-01 NVIDIA Nemotron 3.5 Super VL Output · Standard new — $0.50 · source
2026-11-01 GPT OSS 120B Context window · Standard 128K 131,072 +2% 2026-06-08 · source
2026-11-01 Ternary Bonsai 27B Context window · Standard new — 262,144 · source
2026-11-01 Ternary Bonsai 27B Input · Standard new — $0.00 · source
2026-11-01 Ternary Bonsai 27B Output · Standard new — $0.00 · source
2026-11-01 Qwen3.7 Max Cache read · Standard new — $0.50 · source
2026-11-01 Qwen3.7 Plus Context window · Standard new — 1M · source
2026-11-01 Qwen3.7 Plus Input · Standard new — $0.32 · source
2026-11-01 Qwen3.7 Plus Output · Standard new — $1.28 · source
2026-11-01 Qwen3.8 Flash Context window · Standard new — 1M · source
2026-11-01 Qwen3.8 Flash Input · Standard new — $0.15 · source
2026-11-01 Qwen3.8 Flash Output · Standard new — $0.47 · source
2026-11-01 Beam 1.0 501B A23B Cache read · Standard new — $0.04 · source
2026-11-01 Beam 1.0 501B A23B Context window · Standard new — 1,048,576 · source
2026-11-01 Beam 1.0 501B A23B Input · Standard new — $0.40 · source
2026-11-01 Beam 1.0 501B A23B Output · Standard new — $1.20 · source
2026-11-01 Tev1 4B Experimental Context window · Standard new — 32,768 · source
2026-11-01 Tev1 4B Experimental Input · Standard new — $0.042 · source
2026-11-01 Tev1 4B Experimental Output · Standard new — $0.00 · source
2026-11-01 GLM-5.2 Cache read · Standard new — $0.26 · source
2026-11-01 GLM-5.2 Context window · Standard new — 1,048,575 · source
2026-11-01 GLM-5.2 Input · Standard new — $1.40 · source
2026-11-01 GLM-5.2 Output · Standard new — $4.40 · source
2026-11-01 Z.ai GLM 5.3 Cache read · Standard new — $0.26 · source
2026-11-01 Z.ai GLM 5.3 Context window · Standard new — 1,048,575 · source
2026-11-01 Z.ai GLM 5.3 Input · Standard new — $1.40 · source
2026-11-01 Z.ai GLM 5.3 Output · Standard new — $4.40 · source
2026-11-01 Z.ai GLM 5.3 Flash Cache read · Standard new — $0.03 · source
2026-11-01 Z.ai GLM 5.3 Flash Context window · Standard new — 1,048,575 · source
2026-11-01 Z.ai GLM 5.3 Flash Input · Standard new — $0.15 · source
2026-11-01 Z.ai GLM 5.3 Flash Output · Standard new — $0.50 · source
2026-11-01 grok-4.5 Cache read · Batch API · prompts ≤ 200K tokens new — $0.24 · source
2026-11-01 grok-4.5 Cache read · Batch API · prompts > 200K tokens new — $0.48 · source
2026-11-01 grok-4.5 Input · Batch API · prompts ≤ 200K tokens new — $1.60 · source
2026-11-01 grok-4.5 Input · Batch API · prompts > 200K tokens new — $3.20 · source
2026-11-01 grok-4.5 Output · Batch API · prompts ≤ 200K tokens new — $4.80 · source
2026-11-01 grok-4.5 Output · Batch API · prompts > 200K tokens new — $9.60 · source
2026-11-01 grok-4.6 Cache read · Batch API · prompts ≤ 200K tokens new — $0.40 · source
2026-11-01 grok-4.6 Cache read · Batch API · prompts > 200K tokens new — $0.80 · source
2026-11-01 grok-4.6 Input · Batch API · prompts ≤ 200K tokens new — $1.60 · source
2026-11-01 grok-4.6 Input · Batch API · prompts > 200K tokens new — $3.20 · source
2026-11-01 grok-4.6 Output · Batch API · prompts ≤ 200K tokens new — $4.80 · source
2026-11-01 grok-4.6 Output · Batch API · prompts > 200K tokens new — $9.60 · source
2026-11-01 grok-4.7 Cache read · Batch API · prompts ≤ 200K tokens new — $0.40 · source
2026-11-01 grok-4.7 Cache read · Batch API · prompts > 200K tokens new — $0.80 · source
2026-11-01 grok-4.7 Input · Batch API · prompts ≤ 200K tokens new — $1.60 · source
2026-11-01 grok-4.7 Input · Batch API · prompts > 200K tokens new — $3.20 · source
2026-11-01 grok-4.7 Output · Batch API · prompts ≤ 200K tokens new — $4.80 · source
2026-11-01 grok-4.7 Output · Batch API · prompts > 200K tokens new — $9.60 · source
2026-11-01 Gemini 4 Argon Cache read · Batch API new — $0.05 · source
2026-11-01 Gemini 4 Argon Cache read · Flex new — $0.05 · source
2026-11-01 Gemini 4 Argon Cache read · Priority new — $0.18 · source
2026-11-01 Gemini 4 Argon Cache read · Standard new — $0.10 · source
2026-11-01 Gemini 4 Argon Input · Batch API new — $1.00 · source
2026-11-01 Gemini 4 Argon Input · Flex new — $1.00 · source
2026-11-01 Gemini 4 Argon Input · Priority new — $3.60 · source
2026-11-01 Gemini 4 Argon Input · Standard new — $2.00 · source
2026-11-01 Gemini 4 Argon Output · Batch API new — $5.00 · source
2026-11-01 Gemini 4 Argon Output · Flex new — $5.00 · source
2026-11-01 Gemini 4 Argon Output · Priority new — $18.00 · source
2026-11-01 Gemini 4 Argon Output · Standard new — $10.00 · source
2026-10-31 gpt-6-astra-law Cache read · Standard new — $1.00 · source
2026-10-31 gpt-6-astra-law Input · Standard new — $10.00 · source
2026-10-31 gpt-6-astra-law Output · Standard new — $50.00 · source
2026-10-31 gpt-6-rosalind Cache read · Standard · prompts ≤ 272K tokens new — $1.50 · source
2026-10-31 gpt-6-rosalind Cache read · Standard · prompts > 272K tokens new — $3.00 · source
2026-10-31 gpt-6-rosalind Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $37.50 · source
2026-10-31 gpt-6-rosalind Cache write (12 h) · Standard · prompts > 272K tokens new — $75.00 · source
2026-10-31 gpt-6-rosalind Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $18.75 · source
2026-10-31 gpt-6-rosalind Cache write (30 min) · Standard · prompts > 272K tokens new — $37.50 · source
2026-10-31 gpt-6-rosalind Input · Standard · prompts ≤ 272K tokens new — $15.00 · source
2026-10-31 gpt-6-rosalind Input · Standard · prompts > 272K tokens new — $30.00 · source
2026-10-31 gpt-6-rosalind Output · Standard · prompts ≤ 272K tokens new — $75.00 · source
2026-10-31 gpt-6-rosalind Output · Standard · prompts > 272K tokens new — $112.50 · source
2026-10-31 gpt-6.1-terra Cache read · Batch API · prompts ≤ 272K tokens new — $0.025 · source
2026-10-31 gpt-6.1-terra Cache read · Batch API · prompts > 272K tokens new — $0.05 · source
2026-10-31 gpt-6.1-terra Cache read · Fast mode · prompts ≤ 272K tokens new — $0.10 · source
2026-10-31 gpt-6.1-terra Cache read · Fast mode · prompts > 272K tokens new — $0.20 · source
2026-10-31 gpt-6.1-terra Cache read · Flex · prompts ≤ 272K tokens new — $0.025 · source
2026-10-31 gpt-6.1-terra Cache read · Flex · prompts > 272K tokens new — $0.05 · source
2026-10-31 gpt-6.1-terra Cache read · Standard · prompts ≤ 272K tokens new — $0.05 · source
2026-10-31 gpt-6.1-terra Cache read · Standard · prompts > 272K tokens new — $0.10 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $1.25 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Batch API · prompts > 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $5.00 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Fast mode · prompts > 272K tokens new — $10.00 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $1.25 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Flex · prompts > 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Cache write (12 h) · Standard · prompts > 272K tokens new — $5.00 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $0.625 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Batch API · prompts > 272K tokens new — $1.25 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Fast mode · prompts > 272K tokens new — $5.00 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $0.625 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Flex · prompts > 272K tokens new — $1.25 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $1.25 · source
2026-10-31 gpt-6.1-terra Cache write (30 min) · Standard · prompts > 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Input · Batch API · prompts ≤ 272K tokens new — $0.50 · source
2026-10-31 gpt-6.1-terra Input · Batch API · prompts > 272K tokens new — $1.00 · source
2026-10-31 gpt-6.1-terra Input · Fast mode · prompts ≤ 272K tokens new — $2.00 · source
2026-10-31 gpt-6.1-terra Input · Fast mode · prompts > 272K tokens new — $4.00 · source
2026-10-31 gpt-6.1-terra Input · Flex · prompts ≤ 272K tokens new — $0.50 · source
2026-10-31 gpt-6.1-terra Input · Flex · prompts > 272K tokens new — $1.00 · source
2026-10-31 gpt-6.1-terra Input · Standard · prompts ≤ 272K tokens new — $1.00 · source
2026-10-31 gpt-6.1-terra Input · Standard · prompts > 272K tokens new — $2.00 · source
2026-10-31 gpt-6.1-terra Output · Batch API · prompts ≤ 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Output · Batch API · prompts > 272K tokens new — $3.75 · source
2026-10-31 gpt-6.1-terra Output · Fast mode · prompts ≤ 272K tokens new — $10.00 · source
2026-10-31 gpt-6.1-terra Output · Fast mode · prompts > 272K tokens new — $15.00 · source
2026-10-31 gpt-6.1-terra Output · Flex · prompts ≤ 272K tokens new — $2.50 · source
2026-10-31 gpt-6.1-terra Output · Flex · prompts > 272K tokens new — $3.75 · source
2026-10-31 gpt-6.1-terra Output · Standard · prompts ≤ 272K tokens new — $5.00 · source
2026-10-31 gpt-6.1-terra Output · Standard · prompts > 272K tokens new — $7.50 · source
2026-10-21 babbage-002 Input · Batch API · prompts ≤ 272K tokens removed $0.20 — 2026-10-10 · source
2026-10-21 babbage-002 Input · Standard · prompts ≤ 272K tokens removed $0.40 — 2026-10-10 · source
2026-10-21 babbage-002 Output · Batch API · prompts ≤ 272K tokens removed $0.20 — 2026-10-10 · source
2026-10-21 babbage-002 Output · Standard · prompts ≤ 272K tokens removed $0.40 — 2026-10-10 · source
2026-10-21 davinci-002 Input · Batch API · prompts ≤ 272K tokens removed $1.00 — 2026-10-10 · source
2026-10-21 davinci-002 Input · Standard · prompts ≤ 272K tokens removed $2.00 — 2026-10-10 · source
2026-10-21 davinci-002 Output · Batch API · prompts ≤ 272K tokens removed $1.00 — 2026-10-10 · source
2026-10-21 davinci-002 Output · Standard · prompts ≤ 272K tokens removed $2.00 — 2026-10-10 · source
2026-10-21 gpt-3.5-turbo-1106 Input · Batch API · prompts ≤ 272K tokens removed $1.00 — 2026-10-10 · source
2026-10-21 gpt-3.5-turbo-1106 Input · Standard · prompts ≤ 272K tokens removed $1.00 — 2026-10-10 · source
2026-10-21 gpt-3.5-turbo-1106 Output · Batch API · prompts ≤ 272K tokens removed $2.00 — 2026-10-10 · source
2026-10-21 gpt-3.5-turbo-1106 Output · Standard · prompts ≤ 272K tokens removed $2.00 — 2026-10-10 · source
2026-10-21 gpt-3.5-turbo-instruct Input · Standard · prompts ≤ 272K tokens removed $1.50 — 2026-10-10 · source
2026-10-21 gpt-3.5-turbo-instruct Output · Standard · prompts ≤ 272K tokens removed $2.00 — 2026-10-10 · source
2026-10-21 gpt-5.6-cyber Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $31.25 · source
2026-10-21 gpt-5.6-cyber Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $15.625 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $0.25 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Batch API · prompts > 272K tokens new — $0.50 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $1.00 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Fast mode · prompts > 272K tokens new — $2.00 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $0.25 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Flex · prompts > 272K tokens new — $0.50 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $0.50 · source
2026-10-21 gpt-5.6-luna Cache write (12 h) · Standard · prompts > 272K tokens new — $1.00 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $0.125 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Batch API · prompts > 272K tokens new — $0.25 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $0.50 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Fast mode · prompts > 272K tokens new — $1.00 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $0.125 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Flex · prompts > 272K tokens new — $0.25 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $0.25 · source
2026-10-21 gpt-5.6-luna Cache write (30 min) · Standard · prompts > 272K tokens new — $0.50 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Batch API · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $20.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Fast mode · prompts > 272K tokens new — $40.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Flex · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-sol Cache write (12 h) · Standard · prompts > 272K tokens new — $20.00 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Batch API · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Fast mode · prompts > 272K tokens new — $20.00 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Flex · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-sol Cache write (30 min) · Standard · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Batch API · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Fast mode · prompts > 272K tokens new — $20.00 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Flex · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-terra Cache write (12 h) · Standard · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $1.25 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Batch API · prompts > 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Fast mode · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $1.25 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Flex · prompts > 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-5.6-terra Cache write (30 min) · Standard · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $12.50 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Batch API · prompts > 272K tokens new — $25.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $50.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Fast mode · prompts > 272K tokens new — $100.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $12.50 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Flex · prompts > 272K tokens new — $25.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $25.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Standard · prompts > 272K tokens new — $50.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Ultrafast · prompts ≤ 272K tokens new — $150.00 · source
2026-10-21 gpt-6-astra Cache write (12 h) · Ultrafast · prompts > 272K tokens new — $300.00 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $6.25 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Batch API · prompts > 272K tokens new — $12.50 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $25.00 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Fast mode · prompts > 272K tokens new — $50.00 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $6.25 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Flex · prompts > 272K tokens new — $12.50 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $12.50 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Standard · prompts > 272K tokens new — $25.00 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Ultrafast · prompts ≤ 272K tokens new — $75.00 · source
2026-10-21 gpt-6-astra Cache write (30 min) · Ultrafast · prompts > 272K tokens new — $150.00 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $0.125 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Batch API · prompts > 272K tokens new — $0.25 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $0.50 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Fast mode · prompts > 272K tokens new — $1.00 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $0.125 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Flex · prompts > 272K tokens new — $0.25 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $0.25 · source
2026-10-21 gpt-6-luna Cache write (12 h) · Standard · prompts > 272K tokens new — $0.50 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $0.0625 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Batch API · prompts > 272K tokens new — $0.125 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $0.25 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Fast mode · prompts > 272K tokens new — $0.50 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $0.0625 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Flex · prompts > 272K tokens new — $0.125 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $0.125 · source
2026-10-21 gpt-6-luna Cache write (30 min) · Standard · prompts > 272K tokens new — $0.25 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Batch API · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $10.00 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Fast mode · prompts > 272K tokens new — $20.00 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Flex · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-6-sol Cache write (12 h) · Standard · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $1.25 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Batch API · prompts > 272K tokens new — $2.50 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Fast mode · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $1.25 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Flex · prompts > 272K tokens new — $2.50 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-6-sol Cache write (30 min) · Standard · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Batch API · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Batch API · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Fast mode · prompts ≤ 272K tokens new — $10.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Fast mode · prompts > 272K tokens new — $20.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Flex · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Flex · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Standard · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Standard · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Ultrafast · prompts ≤ 272K tokens new — $30.00 · source
2026-10-21 gpt-6.1-sol Cache write (12 h) · Ultrafast · prompts > 272K tokens new — $60.00 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Batch API · prompts ≤ 272K tokens new — $1.25 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Batch API · prompts > 272K tokens new — $2.50 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Fast mode · prompts ≤ 272K tokens new — $5.00 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Fast mode · prompts > 272K tokens new — $10.00 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Flex · prompts ≤ 272K tokens new — $1.25 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Flex · prompts > 272K tokens new — $2.50 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Standard · prompts ≤ 272K tokens new — $2.50 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Standard · prompts > 272K tokens new — $5.00 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Ultrafast · prompts ≤ 272K tokens new — $15.00 · source
2026-10-21 gpt-6.1-sol Cache write (30 min) · Ultrafast · prompts > 272K tokens new — $30.00 · source
2026-10-10 gpt-6.1-sol Cache read · Ultrafast · prompts ≤ 272K tokens new — $0.60 · source
2026-10-10 gpt-6.1-sol Cache read · Ultrafast · prompts > 272K tokens new — $1.20 · source
2026-10-10 gpt-6.1-sol Input · Ultrafast · prompts ≤ 272K tokens new — $12.00 · source
2026-10-10 gpt-6.1-sol Input · Ultrafast · prompts > 272K tokens new — $24.00 · source
2026-10-10 gpt-6.1-sol Output · Ultrafast · prompts ≤ 272K tokens new — $60.00 · source
2026-10-10 gpt-6.1-sol Output · Ultrafast · prompts > 272K tokens new — $90.00 · source
2026-10-10 gpt-rosalind-discovery Cache read · Standard new — $0.50 · source
2026-10-10 gpt-rosalind-discovery Input · Standard new — $5.00 · source
2026-10-10 gpt-rosalind-discovery Output · Standard new — $25.00 · source
2026-10-10 gpt-rosalind-research Cache read · Standard new — $0.50 · source
2026-10-10 gpt-rosalind-research Input · Standard new — $5.00 · source
2026-10-10 gpt-rosalind-research Output · Standard new — $25.00 · source
2026-10-09 Claude Haiku 5.5 Cache read · Standard · prompts ≤ 100K tokens new — $0.01 · source
2026-10-09 Claude Haiku 5.5 Cache read · Standard · prompts > 100K tokens new — $0.05 · source
2026-10-09 Claude Haiku 5.5 Cache write (1 h) · Standard · prompts ≤ 100K tokens new — $0.20 · source
2026-10-09 Claude Haiku 5.5 Cache write (1 h) · Standard · prompts > 100K tokens new — $1.00 · source
2026-10-09 Claude Haiku 5.5 Cache write (5 min) · Standard · prompts ≤ 100K tokens new — $0.125 · source
2026-10-09 Claude Haiku 5.5 Cache write (5 min) · Standard · prompts > 100K tokens new — $0.625 · source
2026-10-09 Claude Haiku 5.5 Input · Batch API · prompts ≤ 100K tokens new — $0.05 · source
2026-10-09 Claude Haiku 5.5 Input · Batch API · prompts > 100K tokens new — $0.25 · source
2026-10-09 Claude Haiku 5.5 Input · Standard · prompts ≤ 100K tokens new — $0.10 · source
2026-10-09 Claude Haiku 5.5 Input · Standard · prompts > 100K tokens new — $0.50 · source
2026-10-09 Claude Haiku 5.5 Output · Batch API · prompts ≤ 100K tokens new — $0.25 · source
2026-10-09 Claude Haiku 5.5 Output · Batch API · prompts > 100K tokens new — $1.25 · source
2026-10-09 Claude Haiku 5.5 Output · Standard · prompts ≤ 100K tokens new — $0.50 · source
2026-10-09 Claude Haiku 5.5 Output · Standard · prompts > 100K tokens new — $2.50 · source
2026-10-09 Claude Sonnet 5.5 Cache read · Standard $0.20 $0.10 -50% 2026-10-06 · source
2026-10-09 grok-4.7 Cache read · Priority · prompts ≤ 200K tokens new — $1.00 · source
2026-10-09 grok-4.7 Cache read · Priority · prompts > 200K tokens new — $2.00 · source
2026-10-09 grok-4.7 Cache read · Standard · prompts ≤ 200K tokens new — $0.50 · source
2026-10-09 grok-4.7 Cache read · Standard · prompts > 200K tokens new — $1.00 · source
2026-10-09 grok-4.7 Context window · Standard new — 500K · source
2026-10-09 grok-4.7 Input · Priority · prompts ≤ 200K tokens new — $4.00 · source
2026-10-09 grok-4.7 Input · Priority · prompts > 200K tokens new — $8.00 · source
2026-10-09 grok-4.7 Input · Standard · prompts ≤ 200K tokens new — $2.00 · source
2026-10-09 grok-4.7 Input · Standard · prompts > 200K tokens new — $4.00 · source
2026-10-09 grok-4.7 Output · Priority · prompts ≤ 200K tokens new — $12.00 · source
2026-10-09 grok-4.7 Output · Priority · prompts > 200K tokens new — $24.00 · source
2026-10-09 grok-4.7 Output · Standard · prompts ≤ 200K tokens new — $6.00 · source
2026-10-09 grok-4.7 Output · Standard · prompts > 200K tokens new — $12.00 · source
2026-10-03 Claude Fable 5.1 Cache read · Standard new — $0.25 · source
2026-10-03 Claude Mythos 5.1 Cache read · Standard new — $0.25 · source
2026-10-03 Claude Opus 5.5 Cache read · Standard new — $0.20 · source
2026-10-03 Claude Opus 5.5 Cache write (1 h) · Standard new — $8.00 · source
2026-10-03 Claude Opus 5.5 Cache write (5 min) · Standard new — $5.00 · source
2026-10-03 Claude Opus 5.5 Input · Batch API new — $2.00 · source
2026-10-03 Claude Opus 5.5 Input · Fast mode new — $8.00 · source
2026-10-03 Claude Opus 5.5 Input · Standard new — $4.00 · source
2026-10-03 Claude Opus 5.5 Output · Batch API new — $10.00 · source
2026-10-03 Claude Opus 5.5 Output · Fast mode new — $40.00 · source
2026-10-03 Claude Opus 5.5 Output · Standard new — $20.00 · source
2026-10-03 Claude Sonnet 5.5 Cache read · Standard new — $0.20 · source
2026-10-03 Claude Sonnet 5.5 Cache write (1 h) · Standard new — $4.00 · source
2026-10-03 Claude Sonnet 5.5 Cache write (5 min) · Standard new — $2.50 · source
2026-10-03 Claude Sonnet 5.5 Input · Batch API new — $1.00 · source
2026-10-03 Claude Sonnet 5.5 Input · Standard new — $2.00 · source
2026-10-03 Claude Sonnet 5.5 Output · Batch API new — $5.00 · source
2026-10-03 Claude Sonnet 5.5 Output · Standard new — $10.00 · source
2026-09-24 Qwen/Qwen3.6-27B Context window · Standard removed 131,072 — 2026-09-17 · source
2026-09-24 Qwen/Qwen3.6-27B Input · Standard removed $0.60 — 2026-09-17 · source
2026-09-24 Qwen/Qwen3.6-27B Max output · Standard removed 16,384 — 2026-09-17 · source
2026-09-24 Qwen/Qwen3.6-27B Output · Standard removed $3.00 — 2026-09-17 · source
2026-09-24 Qwen/Qwen3.8-27B Context window · Standard 131,042 131,072 +0% 2026-09-17 · source
2026-09-12 Qwen/Qwen3.8-27B Context window · Standard new — 131,042 · source
2026-09-12 Qwen/Qwen3.8-27B Input · Standard new — $0.80 · source
2026-09-12 Qwen/Qwen3.8-27B Max output · Standard new — 16,384 · source
2026-09-12 Qwen/Qwen3.8-27B Output · Standard new — $4.00 · source
2026-09-12 Claude Fable 5 Cache read · Standard new — $1.00 · source
2026-09-12 Claude Fable 5.1 Cache write (1 h) · Standard new — $20.00 · source
2026-09-12 Claude Fable 5.1 Cache write (5 min) · Standard new — $12.50 · source
2026-09-12 Claude Fable 5.1 Input · Batch API new — $5.00 · source
2026-09-12 Claude Fable 5.1 Input · Standard new — $10.00 · source
2026-09-12 Claude Fable 5.1 Output · Batch API new — $25.00 · source
2026-09-12 Claude Fable 5.1 Output · Standard new — $50.00 · source
2026-09-12 Claude Haiku 3.5 Cache read · Standard new — $0.08 · source
2026-09-12 Claude Haiku 4.5 Cache read · Standard new — $0.10 · source
2026-09-12 Claude Mythos 5 Cache read · Standard new — $1.00 · source
2026-09-12 Claude Mythos 5.1 Cache write (1 h) · Standard new — $20.00 · source
2026-09-12 Claude Mythos 5.1 Cache write (5 min) · Standard new — $12.50 · source
2026-09-12 Claude Mythos 5.1 Input · Batch API new — $5.00 · source
2026-09-12 Claude Mythos 5.1 Input · Standard new — $10.00 · source
2026-09-12 Claude Mythos 5.1 Output · Batch API new — $25.00 · source
2026-09-12 Claude Mythos 5.1 Output · Standard new — $50.00 · source
2026-09-12 Claude Opus 4 Cache read · Standard new — $1.50 · source
2026-09-12 Claude Opus 4.1 Cache read · Standard new — $1.50 · source
2026-09-12 Claude Opus 4.5 Cache read · Standard new — $0.50 · source
2026-09-12 Claude Opus 4.6 Cache read · Standard new — $0.50 · source
2026-09-12 Claude Opus 4.6 Input · Fast mode removed $30.00 — 2026-06-11 · source
2026-09-12 Claude Opus 4.6 Output · Fast mode removed $150.00 — 2026-06-11 · source
2026-09-12 Claude Opus 4.7 Cache read · Standard new — $0.50 · source
2026-09-12 Claude Opus 4.7 Input · Fast mode removed $30.00 — 2026-06-11 · source
2026-09-12 Claude Opus 4.7 Output · Fast mode removed $150.00 — 2026-06-11 · source
2026-09-12 Claude Opus 4.8 Cache read · Standard new — $0.50 · source
2026-09-12 Claude Opus 5 Cache read · Standard new — $0.50 · source
2026-09-12 Claude Opus 5 Cache write (1 h) · Standard new — $10.00 · source
2026-09-12 Claude Opus 5 Cache write (5 min) · Standard new — $6.25 · source
2026-09-12 Claude Opus 5 Input · Batch API new — $2.50 · source
2026-09-12 Claude Opus 5 Input · Fast mode new — $10.00 · source
2026-09-12 Claude Opus 5 Input · Standard new — $5.00 · source
2026-09-12 Claude Opus 5 Output · Batch API new — $12.50 · source
2026-09-12 Claude Opus 5 Output · Fast mode new — $50.00 · source
2026-09-12 Claude Opus 5 Output · Standard new — $25.00 · source
2026-09-12 Claude Sonnet 4 Cache read · Standard new — $0.30 · source
2026-09-12 Claude Sonnet 4.5 Cache read · Standard new — $0.30 · source
2026-09-12 Claude Sonnet 4.6 Cache read · Standard new — $0.30 · source
2026-09-12 Claude Sonnet 5 Cache read · Standard new — $0.20 · source
2026-09-12 Claude Sonnet 5 Cache write (1 h) · Standard new — $4.00 · source
2026-09-12 Claude Sonnet 5 Cache write (5 min) · Standard new — $2.50 · source
2026-09-12 Claude Sonnet 5 Input · Batch API new — $1.00 · source
2026-09-12 Claude Sonnet 5 Input · Standard new — $2.00 · source
2026-09-12 Claude Sonnet 5 Output · Batch API new — $5.00 · source
2026-09-12 Claude Sonnet 5 Output · Standard new — $10.00 · source
2026-08-21 Llama 3.1 8B Context window · Standard removed 131,072 — 2026-08-09 · source
2026-08-21 Llama 3.1 8B Input · Standard removed $0.05 — 2026-08-09 · source
2026-08-21 Llama 3.1 8B Max output · Standard removed 131,072 — 2026-08-09 · source
2026-08-21 Llama 3.1 8B Output · Standard removed $0.08 — 2026-08-09 · source
2026-08-21 Llama 3.3 70B Context window · Standard removed 131,072 — 2026-08-09 · source
2026-08-21 Llama 3.3 70B Input · Standard removed $0.59 — 2026-08-09 · source
2026-08-21 Llama 3.3 70B Max output · Standard removed 32,768 — 2026-08-09 · source
2026-08-21 Llama 3.3 70B Output · Standard removed $0.79 — 2026-08-09 · source
2026-07-24 Qwen/Qwen3.6-27B Max output · Standard 32,768 16,384 -50% 2026-07-18 · source
2026-07-18 Llama 4 Scout 17B 16E Context window · Standard removed 131,072 — 2026-06-21 · source
2026-07-18 Llama 4 Scout 17B 16E Input · Standard removed $0.11 — 2026-06-21 · source
2026-07-18 Llama 4 Scout 17B 16E Max output · Standard removed 8,192 — 2026-06-21 · source
2026-07-18 Llama 4 Scout 17B 16E Output · Standard removed $0.34 — 2026-06-21 · source
2026-07-18 Qwen3-32B Context window · Standard removed 131,072 — 2026-06-21 · source
2026-07-18 Qwen3-32B Input · Standard removed $0.29 — 2026-06-21 · source
2026-07-18 Qwen3-32B Max output · Standard removed 40,960 — 2026-06-21 · source
2026-07-18 Qwen3-32B Output · Standard removed $0.59 — 2026-06-21 · source
2026-06-21 Qwen/Qwen3.6-27B Context window · Standard new — 131,072 · source
2026-06-21 Qwen/Qwen3.6-27B Input · Standard new — $0.60 · source
2026-06-21 Qwen/Qwen3.6-27B Max output · Standard new — 32,768 · source
2026-06-21 Qwen/Qwen3.6-27B Output · Standard new — $3.00 · source
2026-06-08 Llama 3.3 70B Instruct Turbo Input · Standard $0.88 $1.04 +18% 2026-05-16 · source
2026-06-08 Llama 3.3 70B Instruct Turbo Output · Standard $0.88 $1.04 +18% 2026-05-16 · source
2026-06-08 Meta Llama 3.3 70B Instruct Turbo Context window · Standard removed 131,072 — 2026-05-16 · source
2026-06-08 Meta Llama 3.3 70B Instruct Turbo Input · Standard removed $0.88 — 2026-05-16 · source
2026-06-08 Meta Llama 3.3 70B Instruct Turbo Output · Standard removed $0.88 — 2026-05-16 · source
2026-06-08 Meta Llama 3 8B Instruct Lite Input · Standard $0.10 $0.14 +40% 2026-05-16 · source
2026-06-08 Meta Llama 3 8B Instruct Lite Output · Standard $0.10 $0.14 +40% 2026-05-16 · source
2026-06-08 Kimi K2.5 Context window · Standard removed 262,144 — 2026-05-16 · source
2026-06-08 Kimi K2.5 Input · Standard removed $0.50 — 2026-05-16 · source
2026-06-08 Kimi K2.5 Output · Standard removed $2.80 — 2026-05-16 · source
2026-06-08 Nemotron 3 Ultra 550B A55B Cache read · Standard new — $0.20 · source
2026-06-08 Nemotron 3 Ultra 550B A55B Context window · Standard new — 512.3K · source
2026-06-08 Nemotron 3 Ultra 550B A55B Input · Standard new — $0.60 · source
2026-06-08 Nemotron 3 Ultra 550B A55B Output · Standard new — $3.60 · source
2026-06-08 Qwen3-Coder 480B-A35B Instruct Context window · Standard removed 256K — 2026-05-16 · source
2026-06-08 Qwen3-Coder 480B-A35B Instruct Input · Standard removed $2.00 — 2026-05-16 · source
2026-06-08 Qwen3-Coder 480B-A35B Instruct Output · Standard removed $2.00 — 2026-05-16 · source
2026-06-08 Qwen3.5 9B Input · Standard $0.10 $0.17 +70% 2026-05-16 · source
2026-06-08 Qwen3.5 9B Output · Standard $0.15 $0.25 +67% 2026-05-16 · source
2026-06-08 Qwen3.7 Max Input · Standard new — $2.50 · source
2026-06-08 Qwen3.7 Max Output · Standard new — $7.50 · source
2026-04-03 Kimi K2 0905 Context window · Standard removed 262,144 — 2026-02-27 · source
2026-04-03 Kimi K2 0905 Input · Standard removed $1.00 — 2026-02-27 · source
2026-04-03 Kimi K2 0905 Max output · Standard removed 16,384 — 2026-02-27 · source
2026-04-03 Kimi K2 0905 Output · Standard removed $3.00 — 2026-02-27 · source
2026-02-27 Llama 4 Maverick 17B 128E Context window · Standard removed 131,072 — 2025-12-22 · source
2026-02-27 Llama 4 Maverick 17B 128E Input · Standard removed $0.20 — 2025-12-22 · source
2026-02-27 Llama 4 Maverick 17B 128E Max output · Standard removed 8,192 — 2025-12-22 · source
2026-02-27 Llama 4 Maverick 17B 128E Output · Standard removed $0.60 — 2025-12-22 · source
2026-02-27 Llama Guard 4 12B Context window · Standard removed 131,072 — 2025-12-22 · source
2026-02-27 Llama Guard 4 12B Input · Standard removed $0.20 — 2025-12-22 · source
2026-02-27 Llama Guard 4 12B Max output · Standard removed 1,024 — 2025-12-22 · source
2026-02-27 Llama Guard 4 12B Output · Standard removed $0.20 — 2025-12-22 · source
2025-11-03 Safety GPT OSS 20B Context window · Standard new — 131,072 · source
2025-11-03 Safety GPT OSS 20B Input · Standard new — $0.075 · source
2025-11-03 Safety GPT OSS 20B Max output · Standard new — 65,536 · source
2025-11-03 Safety GPT OSS 20B Output · Standard new — $0.30 · source