llmledger: price changes and retirements

28 October 2026: 3 price changes, 21 models added

2026-10-28T00:00:00Z

Price changes (3)

databricks/databricks-openjev-qwen35-4b: cache write $0.0000 → $0.0420 (likely), cache read $0.0000 → $0.0420 (likely), input $0.0000 → $0.0420 (likely), input dbu none → $0.60, output dbu none → $0.0000 per 1M 017e08a
gpt-5-nano: input priority $2.50 → none per 1M 4b0aa0f
gpt-5-nano-2025-08-07: input priority $2.50 → none per 1M 4b0aa0f

Models added (21)

aiand/deepseek-ai/deepseek-v4-flash f6f49d1
aiand/deepseek-ai/deepseek-v4-pro f6f49d1
aiand/deepseek-ai/deepseek-v4.1-flash f6f49d1
aiand/google/gemma-4-31b-it f6f49d1
aiand/moonshotai/kimi-k2.7-code f6f49d1
aiand/moonshotai/kimi-k3 f6f49d1
aiand/motif-technologies/motif-3 f6f49d1
aiand/openai/gpt-oss-120b f6f49d1
aiand/qwen/qwen3.6-27b f6f49d1
aiand/qwen/qwen3.8-27b f6f49d1
aiand/zai-org/glm-5.2 f6f49d1
aiand/zai-org/glm-5.3 f6f49d1
aiand/zai-org/glm-5.3-flash f6f49d1
morph/morph-dsv41flash 696ff61
morph/morph-dsv41flash-1017 696ff61
morph/morph-dsv41flash-abliterated 696ff61
morph/morph-dsv4flash 696ff61
morph/morph-glm53-744b 696ff61
morph/morph-glm53flash 696ff61
morph/morph-kimik3 696ff61
morph/morph-kimik3-fast 696ff61

27 October 2026: 4 retirement dates, 10 models added

2026-10-27T00:00:00Z

Retirement dates (4)

gemini-3.1-flash-lite-image: retirement date None 3d92124
together_ai/MiniMaxAI/MiniMax-M3: retirement date 2026-11-06 4846d9c
together_ai/thinkingmachines/Inkling: retirement date 2026-11-06 4846d9c
vertex_ai/gemini-3.1-flash-lite-image: retirement date None 3d92124

Models added (10)

abliteration/abliterated-model b1f40b0
abliteration/abliterated-model-large b1f40b0
abliteration/abliterated-model-large-flash b1f40b0
abliteration/abliterated-model-large-v2 b1f40b0
bedrock_mantle/openai.gpt-6.1-terra 189ab85
refuseless/deepseek-v4.1-flash-abliterated c905cd0
refuseless/deepseek-v4.1-flash-fast c905cd0
refuseless/glm-5.3-abliterated c905cd0
refuseless/glm-5.3-flash-abliterated c905cd0
refuseless/minimax-m3.1-flash c905cd0

26 October 2026: 7 price changes, 7 models added

2026-10-26T00:00:00Z

Price changes (7)

gpt-5.6-luna: cache creation input token cost above 12hr above 272k tokens batches none → $0.50, cache creation input token cost above 12hr batches none → $0.25 per 1M c69e82f
gpt-5.6-sol: cache creation input token cost above 12hr above 272k tokens batches none → $10.00, cache creation input token cost above 12hr batches none → $5.00 per 1M c69e82f
gpt-5.6-terra: cache creation input token cost above 12hr above 272k tokens batches none → $5.00, cache creation input token cost above 12hr batches none → $2.50 per 1M c69e82f
gpt-6-astra: cache creation input token cost above 12hr above 272k tokens batches none → $25.00, cache creation input token cost above 12hr above 272k tokens ultrafast none → $300.00, cache creation input token cost above 12hr batches none → $12.50, cache creation input token cost above 12hr ultrafast none → $150.00 per 1M c69e82f
gpt-6-luna: cache creation input token cost above 12hr above 272k tokens batches none → $0.25, cache creation input token cost above 12hr batches none → $0.12 per 1M c69e82f
gpt-6-sol: cache creation input token cost above 12hr above 272k tokens batches none → $5.00, cache creation input token cost above 12hr batches none → $2.50 per 1M c69e82f
gpt-6.1-sol: cache creation input token cost above 12hr above 272k tokens batches none → $5.00, cache creation input token cost above 12hr above 272k tokens ultrafast none → $60.00, cache creation input token cost above 12hr batches none → $2.50, cache creation input token cost above 12hr ultrafast none → $30.00 per 1M c69e82f

Models added (7)

baseten/decision-models/baseten-elephant-9b-latest 7689606
baseten/decision-models/baseten-mammoth-27b-latest 7689606
chatgpt/gpt-6.1-terra 1c022d1
github_copilot/gpt-6.1-terra c843cee
global.openai.gpt-6.1-terra 52c11bf
gpt-6.1-terra 1c022d1
us.openai.gpt-6.1-terra 52c11bf

25 October 2026: 3 models added

2026-10-25T00:00:00Z

Models added (3)

cerebras/llama-3.1-70b 2fa6f22
cerebras/llama-3.1-8b 2fa6f22
mistral/zai-glm-5-3-flash de5dc5b

24 October 2026: 15 price changes, 1 retirement date, 44 models added

2026-10-24T00:00:00Z

Price changes (15)

gemini-2.5-flash-native-audio-preview-12-2025: input cost per video token none → $3.00 per 1M fac7459
gemini/gemini-2.5-flash: cache read input audio token cost batches none → $0.1000, cache read input audio token cost flex none → $0.1000, cache read input audio token cost priority none → $0.18, input cost per audio token flex none → $0.50 per 1M dc0237c
gemini/gemini-2.5-flash-lite: cache read input audio token cost batches none → $0.0300, cache read input audio token cost flex none → $0.0300, cache read input audio token cost priority none → $0.0540, input cost per audio token flex none → $0.15 per 1M dc0237c
gemini/gemini-2.5-flash-native-audio-preview-12-2025: input cost per video token none → $3.00 per 1M fac7459
gemini/gemini-3-flash-preview: cache read input audio token cost batches none → $0.1000, cache read input audio token cost flex none → $0.1000, cache read input audio token cost priority none → $0.18, input cost per audio token flex none → $0.50 per 1M dc0237c
gemini/gemini-3.1-flash-lite: cache read input audio token cost batches none → $0.0250, cache read input audio token cost flex none → $0.0250, cache read input audio token cost priority none → $0.0900, input cost per audio token flex none → $0.25 per 1M dc0237c
gpt-5.6: cache creation input token cost above 12hr none → $10.00, cache creation input token cost above 12hr above 272k tokens none → $20.00, cache creation input token cost above 12hr above 272k tokens flex none → $10.00, cache creation input token cost above 12hr above 272k tokens priority none → $40.00, cache creation input token cost above 12hr flex none → $5.00, cache creation input token cost above 12hr priority none → $20.00 per 1M 4559230
gpt-5.6-cyber: cache creation input token cost above 12hr none → $31.25 per 1M 287abaf
gpt-5.6-luna: cache creation input token cost above 12hr none → $0.50, cache creation input token cost above 12hr above 272k tokens none → $1.00, cache creation input token cost above 12hr above 272k tokens flex none → $0.50, cache creation input token cost above 12hr above 272k tokens priority none → $2.00, cache creation input token cost above 12hr flex none → $0.25, cache creation input token cost above 12hr priority none → $1.00 per 1M 4559230
gpt-5.6-sol: cache creation input token cost above 12hr none → $10.00, cache creation input token cost above 12hr above 272k tokens none → $20.00, cache creation input token cost above 12hr above 272k tokens flex none → $10.00, cache creation input token cost above 12hr above 272k tokens priority none → $40.00, cache creation input token cost above 12hr flex none → $5.00, cache creation input token cost above 12hr priority none → $20.00 per 1M 4559230
gpt-5.6-terra: cache creation input token cost above 12hr none → $5.00, cache creation input token cost above 12hr above 272k tokens none → $10.00, cache creation input token cost above 12hr above 272k tokens flex none → $5.00, cache creation input token cost above 12hr above 272k tokens priority none → $20.00, cache creation input token cost above 12hr flex none → $2.50, cache creation input token cost above 12hr priority none → $10.00 per 1M 4559230
gpt-6-astra: cache creation input token cost above 12hr none → $25.00, cache creation input token cost above 12hr above 272k tokens none → $50.00, cache creation input token cost above 12hr above 272k tokens flex none → $25.00, cache creation input token cost above 12hr above 272k tokens priority none → $100.00, cache creation input token cost above 12hr flex none → $12.50, cache creation input token cost above 12hr priority none → $50.00 per 1M 4559230
gpt-6-luna: cache creation input token cost above 12hr none → $0.25, cache creation input token cost above 12hr above 272k tokens none → $0.50, cache creation input token cost above 12hr above 272k tokens flex none → $0.25, cache creation input token cost above 12hr above 272k tokens priority none → $1.00, cache creation input token cost above 12hr flex none → $0.12, cache creation input token cost above 12hr priority none → $0.50 per 1M 4559230
gpt-6-sol: cache creation input token cost above 12hr none → $5.00, cache creation input token cost above 12hr above 272k tokens none → $10.00, cache creation input token cost above 12hr above 272k tokens flex none → $5.00, cache creation input token cost above 12hr above 272k tokens priority none → $20.00, cache creation input token cost above 12hr flex none → $2.50, cache creation input token cost above 12hr priority none → $10.00 per 1M 4559230
gpt-6.1-sol: cache creation input token cost above 12hr none → $5.00, cache creation input token cost above 12hr above 272k tokens none → $10.00, cache creation input token cost above 12hr above 272k tokens flex none → $5.00, cache creation input token cost above 12hr above 272k tokens priority none → $20.00, cache creation input token cost above 12hr flex none → $2.50, cache creation input token cost above 12hr priority none → $10.00 per 1M 4559230

Retirement dates (1)

github_copilot/claude-opus-4.8-fast: retirement date 2026-11-16 015096a

Models added (44)

bedrock/claude_platform/claude-fable-5 5603724
bedrock/claude_platform/claude-fable-5-1 5603724
bedrock/claude_platform/claude-haiku-4-5 5603724
bedrock/claude_platform/claude-haiku-5-5 5603724
bedrock/claude_platform/claude-opus-4-5 5603724
bedrock/claude_platform/claude-opus-4-6 5603724
bedrock/claude_platform/claude-opus-4-7 5603724
bedrock/claude_platform/claude-opus-4-8 5603724
bedrock/claude_platform/claude-opus-5 5603724
bedrock/claude_platform/claude-opus-5-5 5603724
bedrock/claude_platform/claude-sonnet-4-5 5603724
bedrock/claude_platform/claude-sonnet-4-6 5603724
bedrock/claude_platform/claude-sonnet-5 5603724
bedrock/claude_platform/claude-sonnet-5-5 5603724
opencode_go/beam-free e2686b0
opencode_go/claude-haiku-5-5 e2686b0
opencode_go/deepseek-v4-pro e2686b0
opencode_go/deepseek-v4.1-flash e2686b0
opencode_go/gemini-4-argon e2686b0
opencode_go/glm-5.2 e2686b0
opencode_go/glm-5.3 e2686b0
opencode_go/glm-5.3-flash e2686b0
opencode_go/gpt-5.6-luna e2686b0
opencode_go/gpt-6-luna e2686b0
opencode_go/grok-4.7 e2686b0
opencode_go/hy3 e2686b0
opencode_go/hy4-preview e2686b0
opencode_go/kimi-k2.7-code e2686b0
opencode_go/kimi-k3 e2686b0
opencode_go/kimi-k3.1-pro e2686b0
opencode_go/longcat-2.0 e2686b0
opencode_go/longcat-2.5-preview-free e2686b0
opencode_go/mimo-v2.5 e2686b0
opencode_go/mimo-v2.5-pro e2686b0
opencode_go/mimo-v2.6-flash e2686b0
opencode_go/mimo-v2.6-pro e2686b0
opencode_go/minimax-m3 e2686b0
opencode_go/minimax-m3.1-flash e2686b0
opencode_go/muse-spark-1.2-contributor e2686b0
opencode_go/muse-spark-1.3-contributor e2686b0
opencode_go/qwen3.7-plus e2686b0
opencode_go/qwen3.8-flash e2686b0
opencode_go/qwen3.8-max e2686b0
opencode_go/step-5-preview e2686b0

23 October 2026: 5 price changes, 6 retirement dates, 16 models added

2026-10-23T00:00:00Z

Price changes (5)

elevenlabs/eleven_multilingual_v2: input cost per character $180.00 → $80.00 per 1M f3d53a9
elevenlabs/eleven_v3: input cost per character $180.00 → $80.00 per 1M f3d53a9
gpt-6-luna: cache creation input token cost above 272k tokens decisions $0.20 → $0.25, cache creation input token cost decisions $0.1000 → $0.12, cache read input token cost above 272k tokens decisions $0.20 → $0.0200 (likely), cache read input token cost decisions $0.1000 → $0.0100 (likely) per 1M 82a4ef4
vertex_ai/meta/llama-4-maverick-17b-16e-instruct-maas: input batches none → $0.17, output batches none → $0.57 per 1M 8fa875f
vertex_ai/meta/llama-4-scout-17b-128e-instruct-maas: input batches none → $0.12, output batches none → $0.35 per 1M 8fa875f

Retirement dates (6)

azure_ai/Phi-4: retirement date 2027-01-17 f3d53a9
azure_ai/Phi-4-mini-instruct: retirement date 2027-01-17 f3d53a9
azure_ai/Phi-4-mini-reasoning: retirement date 2027-01-17 f3d53a9
azure_ai/Phi-4-multimodal-instruct: retirement date 2027-01-17 f3d53a9
azure_ai/Phi-4-reasoning: retirement date 2027-01-17 f3d53a9
vertex_ai/veo-2.0-generate-001: retirement date 2026-06-30 5adb0ed

Models added (16)

elevenlabs/eleven_flash_v2 f3d53a9
elevenlabs/eleven_flash_v2_5 f3d53a9
elevenlabs/eleven_turbo_v2 f3d53a9
elevenlabs/eleven_turbo_v2_5 f3d53a9
elevenlabs/eleven_v3_conversational f3d53a9
elevenlabs/eleven_v4 f3d53a9
elevenlabs/eleven_v4_turbo f3d53a9
mistral/voxtral-mini-transcribe-3 f3d53a9
mistral/voxtral-mini-transcribe-3-0 f3d53a9
mistral/voxtral-mini-transcribe-realtime-3 f3d53a9
mistral/voxtral-mini-transcribe-realtime-3-0 f3d53a9
mistral/voxtral-mini-tts-3 f3d53a9
mistral/voxtral-mini-tts-3-0 f3d53a9
mistral/voxtral-small-transcribe-3 f3d53a9
mistral/voxtral-small-transcribe-3-0 f3d53a9
together_ai/MiniMaxAI/MiniMax-M3.1-Flash f3d53a9

21 October 2026: 2 price changes, 3 models added

2026-10-21T00:00:00Z

Price changes (2)

baseten/reflection/Beam-1.0: cache read $0.13 → $0.0400 (likely), input $1.30 → $0.40 (likely), output $4.30 → $1.20 (likely) per 1M 1fcbb03
fireworks_ai/accounts/fireworks/models/muse-spark-open: cache read input token cost priority none → $0.22, input priority none → $1.88, output priority none → $6.38 per 1M 159b5b2

Models added (3)

azure_ai/MAI-Code-1.1-Flash 4ecc5fd
wandb/reflection/Beam-1.0-501B-A23B 5e1e66d
wandb/zai-org/GLM-5.3 5e1e66d

20 October 2026: 5 price changes, 26 retirement dates, 17 models added

2026-10-20T00:00:00Z

Price changes (5)

dashscope/qwen3.7-max: cache write none → $3.12, explicit cache read input token cost none → $0.25 per 1M 3b2cc34
gemini-nano-banana-2.1: cache read input token cost flex $0.0750 → none, input flex $0.75 → none, output flex $3.75 → none per 1M 8e3ce6d
qwen_ai_platform/qwen3.7-max: cache write none → $3.12, explicit cache read input token cost none → $0.25 per 1M 3b2cc34
qwencloud/qwen3.7-max: cache write none → $3.12, explicit cache read input token cost none → $0.25 per 1M 3b2cc34
vertex_ai/gemini-nano-banana-2.1: cache read input token cost flex $0.0750 → none, input flex $0.75 → none, output flex $3.75 → none per 1M 8e3ce6d

Retirement dates (26)

eu.twelvelabs.pegasus-1-2-v1:0: retirement date 2027-03-22 ca329a7
fireworks_ai/accounts/fireworks/models/gpt-oss-120b: retirement date 2026-11-07 c9d081b
fireworks_ai/accounts/fireworks/models/inkling: retirement date 2026-11-07 c9d081b
fireworks_ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4: retirement date 2026-11-07 c9d081b
fireworks_ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b: retirement date 2026-11-07 c9d081b
fireworks_ai/accounts/fireworks/routers/glm-5p3-flash-us: retirement date 2026-11-07 dc9c31e
fireworks_ai/glm-5p3-flash-us: retirement date 2026-11-07 dc9c31e
fireworks_ai/gpt-oss-120b: retirement date 2026-11-07 c9d081b
fireworks_ai/nemotron-3-ultra-nvfp4: retirement date 2026-11-07 c9d081b
fireworks_ai/nemotron-lightning-3p5-30b-a3b: retirement date 2026-11-07 c9d081b
github_copilot/gemini-3.7-flash: retirement date 2026-10-19 6edbc4b
github_copilot/gpt-4.1: retirement date 2026-06-01 fad3140
github_copilot/gpt-4.1-2025-04-14: retirement date 2026-06-01 fad3140
github_copilot/gpt-5-mini: retirement date 2026-10-19 6edbc4b
github_copilot/gpt-5.4: retirement date 2026-10-19 6edbc4b
github_copilot/gpt-5.4-mini: retirement date 2026-10-19 6edbc4b
github_copilot/gpt-5.5: retirement date 2026-10-19 6edbc4b
github_copilot/grok-4.5: retirement date 2026-10-19 6edbc4b
global.twelvelabs.pegasus-1-2-v1:0: retirement date 2027-03-22 ca329a7
twelvelabs.pegasus-1-2-v1:0: retirement date 2027-03-22 ca329a7
us.twelvelabs.pegasus-1-2-v1:0: retirement date 2027-03-22 ca329a7
us.writer.palmyra-x4-v1:0: retirement date 2027-03-09 ca329a7
us.writer.palmyra-x5-v1:0: retirement date 2027-03-21 ca329a7
vertex_ai/gemini-3.8-live: retirement date None ece1627
writer.palmyra-x4-v1:0: retirement date 2027-03-09 ca329a7
writer.palmyra-x5-v1:0: retirement date 2027-03-21 ca329a7

Models added (17)

azure/eu/gpt-4o 4818b76
azure/eu/gpt-4o-mini 4818b76
azure/eu/o1 4818b76
azure/eu/o3 4818b76
azure/eu/o3-mini 4818b76
azure/eu/o4-mini 4818b76
azure/us/gpt-4o 4818b76
azure/us/gpt-4o-mini 4818b76
azure/us/o1 4818b76
azure/us/o3 4818b76
azure/us/o3-mini 4818b76
azure/us/o4-mini 4818b76
cloudflare/@cf/cloudflare/clairic 9fbeebc
cloudflare/clairic 9fbeebc
fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017-us 5c836d6
volcengine/doubao-seed-2-1-lite-260915 4818b76
volcengine/doubao-seed-2-1-pro-260915 4818b76

19 October 2026: 2 price changes, 19 retirement dates, 5 models added

2026-10-19T00:00:00Z

Price changes (2)

azure/container: code interpreter cost per session $30,000.00 → $33,000.00 per 1M 1a77147
fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash: cache read none → $0.0150, input none → $0.15, output none → $0.60 per 1M 714d84a

Retirement dates (19)

baseten/MiniMaxAI/MiniMax-M2.5: retirement date 2026-10-16 3eeee3e
baseten/deepseek-ai/DeepSeek-V3-0324: retirement date 2026-10-16 3eeee3e
baseten/deepseek-ai/DeepSeek-V3.1: retirement date 2026-10-16 3eeee3e
baseten/deepseek-ai/DeepSeek-V4-Pro: retirement date 2026-10-16 3eeee3e
baseten/moonshotai/Kimi-K2-Instruct-0905: retirement date 2026-10-16 3eeee3e
baseten/moonshotai/Kimi-K2-Thinking: retirement date 2026-10-16 3eeee3e
baseten/moonshotai/Kimi-K2.5: retirement date 2026-10-16 3eeee3e
baseten/moonshotai/Kimi-K2.6: retirement date 2026-10-16 3eeee3e
baseten/moonshotai/Kimi-K2.7-Code: retirement date 2026-10-16 3eeee3e
baseten/nvidia/Nemotron-120B-A12B: retirement date 2026-10-16 3eeee3e
baseten/thinkingmachines/inkling: retirement date 2026-10-16 3eeee3e
baseten/thinkingmachines/inkling-small: retirement date 2026-10-16 3eeee3e
baseten/zai-org/GLM-4.6: retirement date 2026-10-16 3eeee3e
baseten/zai-org/GLM-4.7: retirement date 2026-10-16 3eeee3e
baseten/zai-org/GLM-5: retirement date 2026-10-16 3eeee3e
gemini-3.8-flash: retirement date None 581b7d1
github_copilot/claude-opus-4.8: retirement date 2026-11-16 0197b96
vertex_ai/gemini-3.8-flash: retirement date None 581b7d1
vertex_ai/gemini-4-argon: retirement date None b2f0f4d

Models added (5)

deepseek/search 9bafafc
fireworks_ai/accounts/fireworks/models/minimax-m3p1-flash ce0dbe6
meta/muse-image-1.0 748c973
meta/sam-3.1 6e14825
together_ai/deepseek-ai/DeepSeek-V4.1-Flash-1017 d07e3c5

18 October 2026: 1 price change, 12 retirement dates, 10 models added

2026-10-18T00:00:00Z

Price changes (1)

github_copilot/claude-opus-4.8-fast: cache write none → $12.50, cache read none → $1.00, input none → $10.00, output none → $50.00 per 1M cfee0ff

Retirement dates (12)

eu.meta.llama3-2-1b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
eu.meta.llama3-2-3b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
meta.llama3-1-405b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
meta.llama3-2-11b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
meta.llama3-2-1b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
meta.llama3-2-3b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
meta.llama3-2-90b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
us.meta.llama3-1-405b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
us.meta.llama3-2-11b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
us.meta.llama3-2-1b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
us.meta.llama3-2-3b-instruct-v1:0: retirement date 2026-07-07 6c68c2c
us.meta.llama3-2-90b-instruct-v1:0: retirement date 2026-07-07 6c68c2c

Models added (10)

baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017 065b8a8
baseten/deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast 065b8a8
databricks/system.ai.deepseek-v4-flash-0731 75faaea
databricks/system.ai.kimi-k3 75faaea
fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash-1017 df71873
github_copilot/claude-sonnet-4.6 cfee0ff
github_copilot/gpt-5.4-nano cfee0ff
github_copilot/grok-4.5 cfee0ff
github_copilot/grok-4.6 cfee0ff
github_copilot/grok-4.7 cfee0ff

17 October 2026: 21 price changes, 7 retirement dates, 13 models added

2026-10-17T00:00:00Z

Price changes (21)

github_copilot/claude-fable-5: cache write none → $12.50, cache read none → $1.00, input none → $10.00, output none → $50.00 per 1M 3ade828
github_copilot/claude-fable-5.1: cache write none → $12.50, cache read none → $0.25, input none → $10.00, output none → $50.00 per 1M 3ade828
github_copilot/claude-opus-4.8: cache write none → $6.25, cache read none → $0.50, input none → $5.00, output none → $25.00 per 1M 3ade828
github_copilot/claude-opus-5: cache write none → $6.25, cache read none → $0.50, input none → $5.00, output none → $25.00 per 1M 3ade828
github_copilot/claude-opus-5.5: cache write none → $5.00, cache read none → $0.20, input none → $4.00, output none → $20.00 per 1M 3ade828
github_copilot/claude-sonnet-5: cache write none → $2.50, cache read none → $0.20, input none → $2.00, output none → $10.00 per 1M 3ade828
github_copilot/claude-sonnet-5.5: cache write none → $2.50, cache read none → $0.1000, input none → $2.00, output none → $10.00 per 1M 3ade828
github_copilot/gemini-3.7-flash: cache read none → $0.0750, input none → $0.75, output none → $3.75 per 1M 3ade828
github_copilot/gemini-3.8-flash: cache read none → $0.0750, input none → $0.75, output none → $3.75 per 1M 3ade828
github_copilot/gpt-5.4: cache read none → $0.25, cache read input token cost above 272k tokens none → $0.50, input none → $2.50, input above 272k tokens none → $5.00, output none → $15.00, output above 272k tokens none → $22.50 per 1M 3ade828
github_copilot/gpt-5.4-mini: cache read none → $0.0750, input none → $0.75, output none → $4.50 per 1M 3ade828
github_copilot/gpt-5.5: cache read none → $0.50, cache read input token cost above 272k tokens none → $1.00, input none → $5.00, input above 272k tokens none → $10.00, output none → $30.00, output above 272k tokens none → $45.00 per 1M 3ade828
github_copilot/gpt-5.6-luna: cache write none → $0.25, cache creation input token cost above 200k tokens none → $0.50, cache read none → $0.0200, cache read input token cost above 200k tokens none → $0.0400, input none → $0.20, input above 200k tokens none → $0.40, output none → $1.20, output above 200k tokens none → $1.80 per 1M 3ade828
github_copilot/gpt-5.6-sol: cache write none → $5.00, cache creation input token cost above 272k tokens none → $10.00, cache read none → $0.40, cache read input token cost above 272k tokens none → $0.80, input none → $4.00, input above 272k tokens none → $8.00, output none → $20.00, output above 272k tokens none → $30.00 per 1M 3ade828
github_copilot/gpt-5.6-terra: cache write none → $2.50, cache creation input token cost above 272k tokens none → $5.00, cache read none → $0.20, cache read input token cost above 272k tokens none → $0.40, input none → $2.00, input above 272k tokens none → $4.00, output none → $12.00, output above 272k tokens none → $18.00 per 1M 3ade828
github_copilot/gpt-6-astra: cache write none → $12.50, cache creation input token cost above 272k tokens none → $25.00, cache read none → $1.00, cache read input token cost above 272k tokens none → $2.00, input none → $10.00, input above 272k tokens none → $20.00, output none → $50.00, output above 272k tokens none → $75.00 per 1M 3ade828
github_copilot/gpt-6-luna: cache write none → $0.12, cache creation input token cost above 272k tokens none → $0.25, cache read none → $0.0100, cache read input token cost above 272k tokens none → $0.0200, input none → $0.1000, input above 272k tokens none → $0.20, output none → $0.50, output above 272k tokens none → $0.75 per 1M 3ade828
github_copilot/gpt-6-sol: cache write none → $2.50, cache creation input token cost above 272k tokens none → $5.00, cache read none → $0.20, cache read input token cost above 272k tokens none → $0.40, input none → $2.00, input above 272k tokens none → $4.00, output none → $10.00, output above 272k tokens none → $15.00 per 1M 3ade828
github_copilot/gpt-6.1-sol: cache write none → $2.50, cache creation input token cost above 272k tokens none → $5.00, cache read none → $0.1000, cache read input token cost above 272k tokens none → $0.20, input none → $2.00, input above 272k tokens none → $4.00, output none → $10.00, output above 272k tokens none → $15.00 per 1M 3ade828
github_copilot/kimi-k3: cache read none → $0.30, input none → $3.00, output none → $15.00 per 1M 3ade828
github_copilot/mai-code-1.1-flash: cache read none → $0.0200, input none → $0.20, output none → $1.20 per 1M 3ade828

Retirement dates (7)

azure_ai/ministral-3b: retirement date 2026-12-09 d81472f
azure_ai/mistral-medium-2505: retirement date 2026-12-09 d81472f
azure_ai/mistral-small-2503: retirement date 2026-12-09 d81472f
gemini-3.8-flash: retirement date 2027-09-02 d81472f
vertex_ai/gemini-3.8-flash: retirement date 2027-09-02 d81472f
vertex_ai/gemini-3.8-live: retirement date 2027-09-25 d81472f
vertex_ai/gemini-4-argon: retirement date 2027-10-13 d81472f

Models added (13)

deepinfra/deepseek-ai/DeepSeek-V4.1-Flash dd8b285
deepinfra/deepseek-ai/DeepSeek-V4.1-Flash-1017 dd8b285
nace/drex-latest 6d0d0bb
nace/drex-v1.0 6d0d0bb
nace/drex-v1.5 6d0d0bb
nace/drex-v2.0 6d0d0bb
openinfer/@oi/GLM-5.3-Flash e2295b5
openinfer/@oi/Qwen3.5-27B e2295b5
openinfer/@oi/Qwen3.5-9B e2295b5
perplexity/pplx-decider-flash-latest d81472f
perplexity/pplx-decider-flash-v1.2 d81472f
perplexity/pplx-decider-latest d81472f
perplexity/pplx-decider-v1.2 d81472f

16 October 2026: 73 price changes, 2 retirement dates, 10 models added

2026-10-16T00:00:00Z

Price changes (73)

amazon.nova-2-lite-v1:0: cache read input token cost priority none → $0.13, input batches none → $0.15, input priority none → $0.52, output batches none → $1.25, output priority none → $4.38 per 1M 87f9597
amazon.nova-2-pro-preview-20251202-v1:0: input batches none → $0.62, input priority none → $2.19, output batches none → $5.00, output priority none → $17.50 per 1M 87f9597
amazon.nova-lite-v1:0: input batches none → $0.0300, output batches none → $0.12 per 1M 87f9597
amazon.nova-micro-v1:0: input batches none → $0.0175, output batches none → $0.0700 per 1M 87f9597
amazon.nova-premier-v1:0: cache read input token cost priority none → $1.09, input batches none → $1.25, input priority none → $4.38, output batches none → $6.25, output priority none → $21.88 per 1M 87f9597
amazon.nova-pro-v1:0: cache read input token cost priority none → $0.35, input batches none → $0.40, input priority none → $1.40, output batches none → $1.60, output priority none → $5.60 per 1M 87f9597
bedrock_mantle/deepseek.v3.1: input batches none → $0.29, input priority none → $1.02, output batches none → $0.84, output priority none → $2.94 per 1M 87f9597
bedrock_mantle/google.gemma-4-26b-a4b: input batches none → $0.0650, input priority none → $0.23, output batches none → $0.20, output priority none → $0.70 per 1M 87f9597
bedrock_mantle/google.gemma-4-31b: input batches none → $0.0700, input priority none → $0.24, output batches none → $0.20, output priority none → $0.70 per 1M 87f9597
bedrock_mantle/google.gemma-4-e2b: input batches none → $0.0200, input priority none → $0.0700, output batches none → $0.0400, output priority none → $0.14 per 1M 87f9597
bedrock_mantle/moonshotai.kimi-k2-thinking: input batches none → $0.30, input priority none → $1.05, output batches none → $1.25, output priority none → $4.38 per 1M 87f9597
bedrock_mantle/openai.gpt-oss-120b: input batches none → $0.0750, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
bedrock_mantle/openai.gpt-oss-20b: input batches none → $0.0350, input priority none → $0.12, output batches none → $0.15, output priority none → $0.52 per 1M 87f9597
bedrock_mantle/openai.gpt-oss-safeguard-120b: input batches none → $0.0700, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
bedrock_mantle/openai.gpt-oss-safeguard-20b: input batches none → $0.0300, input priority none → $0.12, output batches none → $0.1000, output priority none → $0.35 per 1M 87f9597
bedrock_mantle/qwen.qwen3-235b-a22b-2507: input batches none → $0.11, input priority none → $0.39, output batches none → $0.44, output priority none → $1.54 per 1M 87f9597
bedrock_mantle/qwen.qwen3-32b: input batches none → $0.0750, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct: input batches none → $0.0750, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct: input batches none → $0.22, input priority none → $0.79, output batches none → $0.90, output priority none → $3.15 per 1M 87f9597
bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct: input batches none → $0.0700, input priority none → $0.26, output batches none → $0.60, output priority none → $2.10 per 1M 87f9597
bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct: input batches none → $0.26, input priority none → $0.93, output batches none → $1.33, output priority none → $4.66 per 1M 87f9597
bedrock_mantle/xai.grok-4.3: cache read input token cost batches none → $0.1000, input batches none → $0.62, output batches none → $1.25 per 1M 87f9597
deepseek.v3.2: input batches none → $0.31, input priority none → $1.08, output batches none → $0.93, output priority none → $3.24 per 1M 87f9597
gemini-3-flash-preview: cache read input token cost flex $0.0500 → none per 1M e74e4e5
gemini-3.1-pro-preview: cache read input token cost flex $0.20 → none per 1M e74e4e5
global.amazon.nova-2-lite-v1:0: cache read input token cost priority none → $0.13, input batches none → $0.15, input priority none → $0.52, output batches none → $1.25, output priority none → $4.38 per 1M 87f9597
google.gemma-3-12b-it: input batches none → $0.0500, input priority none → $0.16, output batches none → $0.15, output priority none → $0.51 per 1M 87f9597
google.gemma-3-27b-it: input batches none → $0.12, input priority none → $0.40, output batches none → $0.19, output priority none → $0.67 per 1M 87f9597
google.gemma-3-4b-it: input batches none → $0.0200, input priority none → $0.0700, output batches none → $0.0400, output priority none → $0.14 per 1M 87f9597
meta.llama3-1-70b-instruct-v1:0: input batches none → $0.36, output batches none → $0.36 per 1M 87f9597
meta.llama3-1-8b-instruct-v1:0: input batches none → $0.11, output batches none → $0.11 per 1M 87f9597
meta.llama3-3-70b-instruct-v1:0: input batches none → $0.36, output batches none → $0.36 per 1M 87f9597
minimax.minimax-m2: input batches none → $0.15, input priority none → $0.52, output batches none → $0.60, output priority none → $2.10 per 1M 87f9597
minimax.minimax-m2.1: input batches none → $0.15, input priority none → $0.52, output batches none → $0.60, output priority none → $2.10 per 1M 87f9597
minimax.minimax-m2.5: input batches none → $0.15, input priority none → $0.52, output batches none → $0.60, output priority none → $2.10 per 1M 87f9597
mistral.devstral-2-123b: input batches none → $0.20, input priority none → $0.70, output batches none → $1.00, output priority none → $3.50 per 1M 87f9597
mistral.magistral-small-2509: input batches none → $0.25, input priority none → $0.88, output batches none → $0.75, output priority none → $2.63 per 1M 87f9597
mistral.ministral-3-14b-instruct: input batches none → $0.1000, input priority none → $0.35, output batches none → $0.1000, output priority none → $0.35 per 1M 87f9597
mistral.ministral-3-3b-instruct: input batches none → $0.0500, input priority none → $0.17, output batches none → $0.0500, output priority none → $0.17 per 1M 87f9597
mistral.ministral-3-8b-instruct: input batches none → $0.0700, input priority none → $0.26, output batches none → $0.0700, output priority none → $0.26 per 1M 87f9597
mistral.mistral-large-3-675b-instruct: input batches none → $0.25, input priority none → $0.88, output batches none → $0.75, output priority none → $2.63 per 1M 87f9597
mistral.voxtral-mini-3b-2507: input batches none → $0.0200, input priority none → $0.0700, output batches none → $0.0200, output priority none → $0.0700 per 1M 87f9597
mistral.voxtral-small-24b-2507: input batches none → $0.0500, input priority none → $0.17, output batches none → $0.15, output priority none → $0.52 per 1M 87f9597
moonshot.kimi-k2-thinking: input batches none → $0.30, input priority none → $1.05, output batches none → $1.25, output priority none → $4.38 per 1M 87f9597
moonshotai.kimi-k2.5: input batches none → $0.30, input priority none → $1.05, output batches none → $1.50, output priority none → $5.25 per 1M 87f9597
nvidia.nemotron-nano-12b-v2: input batches none → $0.1000, input priority none → $0.35, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
nvidia.nemotron-nano-3-30b: input batches none → $0.0300, input priority none → $0.11, output batches none → $0.12, output priority none → $0.42 per 1M 87f9597
nvidia.nemotron-nano-9b-v2: input batches none → $0.0300, input priority none → $0.11, output batches none → $0.12, output priority none → $0.40 per 1M 87f9597
nvidia.nemotron-super-3-120b: input batches none → $0.0750, input priority none → $0.26, output batches none → $0.33, output priority none → $1.14 per 1M 87f9597
openai.gpt-oss-120b-1:0: input batches none → $0.0750, output batches none → $0.30 per 1M 87f9597
openai.gpt-oss-20b-1:0: input batches none → $0.0350, output batches none → $0.15 per 1M 87f9597
openai.gpt-oss-safeguard-120b: input batches none → $0.0700, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
openai.gpt-oss-safeguard-20b: input batches none → $0.0300, input priority none → $0.12, output batches none → $0.1000, output priority none → $0.35 per 1M 87f9597
qwen.qwen3-32b-v1:0: input batches none → $0.0750, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
qwen.qwen3-coder-30b-a3b-v1:0: input batches none → $0.0750, input priority none → $0.26, output batches none → $0.30, output priority none → $1.05 per 1M 87f9597
qwen.qwen3-coder-next: input batches none → $0.25, input priority none → $0.88, output batches none → $0.60, output priority none → $2.10 per 1M 87f9597
qwen.qwen3-vl-235b-a22b: input batches none → $0.26, input priority none → $0.93, output batches none → $1.33, output priority none → $4.66 per 1M 87f9597
us.amazon.nova-2-lite-v1:0: cache read input token cost priority none → $0.14, input batches none → $0.17, input priority none → $0.58, output batches none → $1.38, output priority none → $4.81 per 1M 87f9597
us.amazon.nova-2-pro-preview-20251202-v1:0: input batches none → $0.69, input priority none → $2.41, output batches none → $5.50, output priority none → $19.25 per 1M 87f9597
us.amazon.nova-lite-v1:0: input batches none → $0.0300, output batches none → $0.12 per 1M 87f9597
and 13 more on the page

Retirement dates (2)

github_copilot/claude-opus-5: retirement date 2026-11-16 464bb5a
github_copilot/gpt-5.6-terra: retirement date 2026-11-16 464bb5a

Models added (10)

baseten/meta-models/muse-spark-open 6c9c3a9
baseten/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B 6c9c3a9
baseten/reflection/Beam-1.0 1c317e3
nebius/reflection/beam 1c317e3
together_ai/reflection/Beam-1.0-501B-A23B 78372b4
volcengine/doubao-seedance-2-0-260128 f81e657
volcengine/doubao-seedance-2-0-fast-260128 f81e657
volcengine/doubao-seedance-2-0-mini-260615 f81e657
volcengine/doubao-seedance-2-5-260628 f81e657
wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B 123e207

15 October 2026: 8 price changes, 13 retirement dates, 71 models added

2026-10-15T00:00:00Z

Price changes (8)

agentcore/search: input cost per query $0.0000 → $7,000.00 (likely) per 1M 4d52918
openai.gpt-oss-120b-1:0: input flex none → $0.0750, input priority none → $0.26, output flex none → $0.30, output priority none → $1.05 per 1M a741f34
openai.gpt-oss-20b-1:0: input flex none → $0.0350, input priority none → $0.12, output flex none → $0.15, output priority none → $0.52 per 1M a741f34
sail/deepseek-ai/DeepSeek-V4.1-Flash: input $0.15 → $0.0900, input balanced $0.12 → $0.0700, input flex $0.0800 → $0.0500, output $0.60 → $0.30, output balanced $0.48 → $0.22, output flex $0.30 → $0.15 per 1M 53cd1d4
vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas: cache read $0.0300 → $0.0000 (reverted), input $0.30 → $0.0000 (reverted), output $1.20 → $0.0000 (reverted) per 1M ad83e3d
xai/grok-voice-2.0: input cost per text message none → $4,000.00 per 1M 53cd1d4
xai/grok-voice-3.0: input cost per text message none → $4,000.00 per 1M 53cd1d4
xai/grok-voice-latest: input cost per text message none → $4,000.00 per 1M 53cd1d4

Retirement dates (13)

azure/gpt-chat-latest: retirement date 2027-05-18 53cd1d4
azure/us/gpt-chat-latest: retirement date 2027-05-18 53cd1d4
azure_ai/gpt-chat-latest: retirement date 2027-05-18 53cd1d4
ft:gpt-4.1-2025-04-14: retirement date 2027-01-14 53cd1d4
ft:gpt-4.1-mini-2025-04-14: retirement date 2027-01-14 53cd1d4
ft:gpt-4o-2024-08-06: retirement date 2027-01-14 53cd1d4
ft:gpt-4o-2024-11-20: retirement date 2027-01-14 53cd1d4
ft:gpt-4o-mini-2024-07-18: retirement date 2027-01-14 53cd1d4
gpt-4.1-2025-04-14: retirement date 2027-01-14 53cd1d4
gpt-4.1-mini-2025-04-14: retirement date 2027-01-14 53cd1d4
gpt-4o-2024-08-06: retirement date 2027-01-14 53cd1d4
gpt-4o-2024-11-20: retirement date 2027-01-14 53cd1d4
gpt-4o-mini-2024-07-18: retirement date 2027-01-14 53cd1d4

Models added (71)

azure_ai/claude-opus-5-5-fast 67fab67
fireworks_ai/accounts/fireworks/models/muse-spark-open 5bd6c0a
gpt-5.5-cyber-preview 5bd6c0a
inferenceapis/MiniMaxAI/MiniMax-M3 fd84e97
inferenceapis/Qwen/Qwen3-VL-235B-A22B-Instruct fd84e97
inferenceapis/Qwen/Qwen3.8-Flash fd84e97
inferenceapis/deepseek-ai/DeepSeek-V3 fd84e97
inferenceapis/deepseek-ai/DeepSeek-V4-Flash fd84e97
inferenceapis/deepseek-ai/DeepSeek-V4-Flash-0731 fd84e97
inferenceapis/deepseek-ai/DeepSeek-V4-Pro fd84e97
inferenceapis/deepseek-ai/DeepSeek-V4-Pro-0813 fd84e97
inferenceapis/deepseek-ai/DeepSeek-V4.1-Flash fd84e97
inferenceapis/deepseek-chat fd84e97
inferenceapis/deepseek-flash fd84e97
inferenceapis/deepseek-reasoner fd84e97
inferenceapis/deepseek-v3 fd84e97
inferenceapis/deepseek-v4-flash fd84e97
inferenceapis/deepseek-v4-pro fd84e97
inferenceapis/deepseek-v4.1-flash fd84e97
inferenceapis/glm-5.3 fd84e97
inferenceapis/glm-5.3-flash fd84e97
inferenceapis/gpt-oss-120b fd84e97
inferenceapis/gpt-oss-20b fd84e97
inferenceapis/kimi-k2.7-code fd84e97
inferenceapis/llama-3.1-8b-instant fd84e97
inferenceapis/llama-3.3-70b fd84e97
inferenceapis/llama-3.3-70b-instruct fd84e97
inferenceapis/llama-3.3-70b-versatile fd84e97
inferenceapis/meta-llama/Llama-3.3-70B-Instruct fd84e97
inferenceapis/meta-llama/Llama-3.3-70B-Instruct-Turbo fd84e97
inferenceapis/minimax-m3 fd84e97
inferenceapis/moonshotai/Kimi-K2.7-Code fd84e97
inferenceapis/openai/gpt-oss-120b fd84e97
inferenceapis/openai/gpt-oss-20b fd84e97
inferenceapis/qwen3-vl fd84e97
inferenceapis/qwen3-vl-235b fd84e97
inferenceapis/qwen3.8-flash fd84e97
inferenceapis/zai-org/GLM-5.3 fd84e97
inferenceapis/zai-org/GLM-5.3-Flash fd84e97
jp.amazon.nova-2-lite-v1:0 f14475e
minimax/MiniMax-H3 71e508b
minimax/MiniMax-H3-Max 71e508b
oci/openai.gpt-oss-120b 68759a2
oci/openai.gpt-oss-20b 68759a2
oci/xai.grok-4.20-0309-non-reasoning 68759a2
oci/xai.grok-4.20-0309-reasoning 68759a2
oci/xai.grok-4.20-non-reasoning 68759a2
oci/xai.grok-4.20-reasoning 68759a2
scx-ai/DeepSeek-V4.1-flash 4428c4c
scx-ai/GLM-5.3 4428c4c
scx-ai/Kimi-K3 4428c4c
together_ai/meta-models/Muse-Spark-Open-816B-A42B 5bd6c0a
together_ai/nvidia/NVIDIA-Nemotron-3.5-Super-VL b211ac8
typesafe/jev-1.14.0 9d72bae
us.stability.stable-conservative-upscale-v1:0 5bd6c0a
us.stability.stable-creative-upscale-v1:0 5bd6c0a
us.stability.stable-fast-upscale-v1:0 5bd6c0a
us.stability.stable-image-control-sketch-v1:0 5bd6c0a
us.stability.stable-image-control-structure-v1:0 5bd6c0a
us.stability.stable-image-erase-object-v1:0 5bd6c0a
and 11 more on the page

14 October 2026: 2 price changes, 2 retirement dates, 33 models added

2026-10-14T00:00:00Z

Price changes (2)

gemini-nano-banana-2.1: cache read input token cost flex none → $0.0750, input flex none → $0.75, output flex none → $3.75 per 1M 01cec8f
vertex_ai/gemini-nano-banana-2.1: cache read input token cost flex none → $0.0750, input flex none → $0.75, output flex none → $3.75 per 1M 01cec8f

Retirement dates (2)

gemini-2.0-flash-exp-image-generation: retirement date 2025-11-14 0d67ccc
gemini/gemini-2.0-flash-exp-image-generation: retirement date 2025-11-14 0d67ccc

Models added (33)

dashscope/happyhorse-1.0-i2v 4f3cb48
dashscope/happyhorse-1.0-r2v 4f3cb48
dashscope/happyhorse-1.0-t2v 4f3cb48
dashscope/happyhorse-1.1-i2v 4f3cb48
dashscope/happyhorse-1.1-r2v 4f3cb48
dashscope/happyhorse-1.1-t2v 4f3cb48
dashscope/wan2.7-i2v 4f3cb48
dashscope/wan2.7-r2v 4f3cb48
dashscope/wan2.7-t2v 4f3cb48
dashscope/wan3.0-video 4f3cb48
dashscope/wan3.0-video-prime 4f3cb48
qwen_ai_platform/happyhorse-1.0-i2v 4f3cb48
qwen_ai_platform/happyhorse-1.0-r2v 4f3cb48
qwen_ai_platform/happyhorse-1.0-t2v 4f3cb48
qwen_ai_platform/happyhorse-1.1-i2v 4f3cb48
qwen_ai_platform/happyhorse-1.1-r2v 4f3cb48
qwen_ai_platform/happyhorse-1.1-t2v 4f3cb48
qwen_ai_platform/wan2.7-i2v 4f3cb48
qwen_ai_platform/wan2.7-r2v 4f3cb48
qwen_ai_platform/wan2.7-t2v 4f3cb48
qwen_ai_platform/wan3.0-video 4f3cb48
qwen_ai_platform/wan3.0-video-prime 4f3cb48
qwencloud/happyhorse-1.0-i2v 4f3cb48
qwencloud/happyhorse-1.0-r2v 4f3cb48
qwencloud/happyhorse-1.0-t2v 4f3cb48
qwencloud/happyhorse-1.1-i2v 4f3cb48
qwencloud/happyhorse-1.1-r2v 4f3cb48
qwencloud/happyhorse-1.1-t2v 4f3cb48
qwencloud/wan2.7-i2v 4f3cb48
qwencloud/wan2.7-r2v 4f3cb48
qwencloud/wan2.7-t2v 4f3cb48
qwencloud/wan3.0-video 4f3cb48
qwencloud/wan3.0-video-prime 4f3cb48