Changes
New and retired models, pricing transitions and incidents since 2026-09-08 10:58 UTC.
New models
50- Claude Haiku 5.5anthropic1.0M
- Claude Haiku 5.5 (batch)anthropicbatch1.0M
- Nano Banana 2.1google66K
- Mistral Large 4mistralai524K
- Ling 3.1 Flashinclusionai262K
- Switchyardnvidia1.0M
- Apodex 1.1 Mini (free)apodexfree262K
- Pareto 26.10 Previewunbiased1.0M
- GPT-6.1 Sol Proopenai1.1M
- GPT-6.1 Solopenai1.1M
- Claude Sonnet 5.5anthropic1.0M
- Claude Sonnet 5.5 (batch)anthropicbatch1.0M
- Jev Routertypesafe1.0M
- Perceptron Mk1.5perceptron37K
- Ember-1fireworks1.0M
- GLM 5.3 Primez-ai1.0M
- Qwen3.8 Max Primeqwen1.0M
- Aion 3.5 Miniaion-labs262K
- Aion 3.5aion-labs262K
- Solar Mini 4upstage524K
Retired models
31- KAT-Coder-Pro V2.5kwaipilotlast seen 2026-10-06 03:23 UTC
- Qwen3.8 27B (free)qwenlast seen 2026-10-05 03:23 UTC
- Space Bunny Alphastealthlast seen 2026-10-05 03:23 UTC
- GPT-6.1 Sol Pro (batch)openailast seen 2026-09-30 03:23 UTC
- GPT-6.1 Sol (batch)openailast seen 2026-09-30 03:23 UTC
- R1 Distill Llama 70Bdeepseeklast seen 2026-09-28 03:23 UTC
- Ling 3.0 Flash Fin (free)inclusionailast seen 2026-09-28 03:23 UTC
- GLM 5.2 (free)z-ailast seen 2026-09-25 03:23 UTC
- Claude 3 Haikuanthropiclast seen 2026-09-25 03:23 UTC
- Nex-N2.5-Mini (free)nex-agilast seen 2026-09-25 03:23 UTC
- Nex-N2.5-Pro (free)nex-agilast seen 2026-09-25 03:23 UTC
- Ling 3.0 Flash VL (free)inclusionailast seen 2026-09-23 03:23 UTC
- GLM 5.2 (batch)z-ailast seen 2026-09-22 03:23 UTC
- KAT-Coder-Pro V2kwaipilotlast seen 2026-09-22 03:23 UTC
- DeepSeek V4 Pro 0813 (batch)deepseeklast seen 2026-09-22 03:23 UTC
- Muse Glimmer 30B (batch)metalast seen 2026-09-22 03:23 UTC
- DeepSeek V4 Flash 0731 (batch)deepseeklast seen 2026-09-22 03:23 UTC
- DeepSeek V4 Flash Vision Exp (batch)deepseeklast seen 2026-09-22 03:23 UTC
- Inkling (batch)thinkingmachineslast seen 2026-09-21 03:23 UTC
- MiniMax M3 (batch)minimaxlast seen 2026-09-21 03:23 UTC
Price changes
200- Kimi K3Waferwafer$0.550 → $0.470 / $15.002026-10-08 10:55 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.006 → $0.005 / $1.28cache read $0.006 → $0.0052026-10-08 10:55 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.006 → $0.005 / $0.351cache read $0.006 → $0.0052026-10-08 10:55 UTC
- GLM 5.2Waferwafer$0.210 → $0.190 / $4.30cache read $0.200 → $0.1802026-10-08 10:50 UTC
- GLM 5.3Io Netio-net/fp8$1.30 → $1.15 / $4.402026-10-08 10:50 UTC
- Kimi K3Waferwafer$0.800 → $0.550 / $15.002026-10-08 10:50 UTC
- DeepSeek V4 Flash 0423Relacerelace/fp4$0.007 → $0.006 / $1.28cache read $0.007 → $0.0062026-10-08 10:50 UTC
- GLM 5.3 FlashInferenceNetinference-net/fp4$0.080 → $0.070 / $0.5002026-10-08 10:45 UTC
- GLM 5.3 FlashRekareka$0.100 → $0.060 / $0.500 → $1.00cache read $0.030 → $0.0402026-10-08 10:45 UTC
- GLM 5.3 FlashOpenInferenceopen-inference/fp4$0.032 / $2.28 → $2.512026-10-08 10:45 UTC
- DeepSeek V4 Pro 0813Waferwafer$0.175 → $0.150 / $3.40cache read $0.170 → $0.1402026-10-08 10:45 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.006 / $0.390 → $0.3512026-10-08 10:45 UTC
- DeepSeek V4 Flash 0731OpenInferenceopen-inference/fp4$0.006 → $0.005 / $0.390 → $0.351cache read $0.006 → $0.0052026-10-08 10:45 UTC
- GLM 5.3 FlashMorphmorph/fp8$0.176 → $0.182 / $0.5002026-10-08 10:40 UTC
- DeepSeek V4.1 FlashInferenceNetinference-net/fp8$0.105 → $0.120 / $0.6002026-10-08 10:40 UTC
- Kimi K3Waferwafer$0.470 → $0.800 / $15.002026-10-08 10:35 UTC
- DeepSeek V4 Flash 0731Relacerelace/fp4$0.008 → $0.006 / $1.28cache read $0.008 → $0.0062026-10-08 10:35 UTC
- DeepSeek V4 Flash 0423Waferwafer$0.053 → $0.063 / $0.1702026-10-08 10:35 UTC
- DeepSeek V4 Flash 0423OpenInferenceopen-inference/fp4$0.008 → $0.006 / $0.390cache read $0.008 → $0.0062026-10-08 10:35 UTC
- DeepSeek V4.1 FlashRelacerelace$0.035 → $0.035 / $1.002026-10-08 10:25 UTC
Incidents
200- Qwen3 VL 30B A3B InstructSiliconFlowsiliconflow/fp8open · 2026-10-08 10:50 UTC
- Qwen3.5 397B A17BDigitalOceandigitaloceanopen · 2026-10-08 10:50 UTC
- GLM 5.3 FlashMorphmorph/fp8open · 2026-10-08 10:50 UTC
- GLM 5.2Nebiusnebius/fp4open · 2026-10-08 10:50 UTC
- Qwen3.5-122B-A10BAlibabaalibabaopen · 2026-10-08 10:45 UTC
- Hy4 previewSiliconFlowsiliconflow/fp8open · 2026-10-08 10:45 UTC
- Qwen3 Next 80B A3B InstructNovitanovita/bf16open · 2026-10-08 10:35 UTC
- Gemma 4 26B A4B Googlegoogle-vertex/globalopen · 2026-10-08 10:30 UTC
- Kimi K3DeepInfradeepinfra/mxfp4open · 2026-10-08 10:30 UTC
- GLM 5.3 FlashFriendlifriendliopen · 2026-10-08 10:25 UTC
- Gemma 4 31BSambaNovasambanovaopen · 2026-10-08 10:20 UTC
- Mistral NemoNovitanovita/fp8open · 2026-10-08 10:20 UTC
- DeepSeek V4.1 FlashFireworksfireworks/usopen · 2026-10-08 10:20 UTC
- Gemma 4 31BNovitanovita/bf16open · 2026-10-08 10:15 UTC
- Qwen3 Coder 480B A35BVenicevenice/fp8open · 2026-10-08 10:15 UTC
- Qwen3.5 397B A17BAtlasCloudatlas-cloud/fp8open · 2026-10-08 10:15 UTC
- Grok 4.20 Multi-AgentxAIxaiopen · 2026-10-08 10:15 UTC
- Qwen3.6 27BPhalaphalaopen · 2026-10-08 10:15 UTC
- Muse Spark 1.3Metametaopen · 2026-10-08 10:15 UTC
- DeepSeek V4 Flash 0423Mancer 2mancer/fp8open · 2026-10-08 10:05 UTC
Full archive: /incidents has 200 in this window.