Catalog changes on 31 October 2026
231 new models, 919 additions, 227 price changes, 55 removals, 48 fully delisted, 2 context changes across 12 gateways.
New models (231)
- Phi 4 Multimodal arrived, first seen on NanoGPT
- Phi 4 Mini arrived, first seen on NanoGPT
- OrcaCyber Zero 1.5 arrived, first seen on NanoGPT
- weaver arrived, first seen on Experiential Labs
- unslopnemo-12b arrived, first seen on Experiential Labs
- ui-tars-1.5-7b arrived, first seen on Experiential Labs
- sonar-reasoning-pro arrived, first seen on Experiential Labs
- sonar-pro-search arrived, first seen on Experiential Labs
- sonar-pro arrived, first seen on Experiential Labs
- seed-2.0-mini arrived, first seen on Experiential Labs
- seed-2.0-lite arrived, first seen on Experiential Labs
- seed-1.6-flash arrived, first seen on Experiential Labs
- qwen3.5-plus-20260420 arrived, first seen on Experiential Labs
- qwen3.5-plus-02-15 arrived, first seen on Experiential Labs
- qwen3.5-flash-02-23 arrived, first seen on Experiential Labs
- qwen3-8b arrived, first seen on Experiential Labs
- qwen2.5-vl-72b-instruct arrived, first seen on Experiential Labs
- phi-4 arrived, first seen on Experiential Labs
- nova-premier-v1 arrived, first seen on Experiential Labs
- nova-2-lite-v1 arrived, first seen on Experiential Labs
- mixtral-8x22b-instruct arrived, first seen on Experiential Labs
- magnum-v4-72b arrived, first seen on Experiential Labs
- ernie-4.5-vl-424b-a47b arrived, first seen on Experiential Labs
- dolphin-mistral-24b-venice-edition arrived, first seen on Experiential Labs
- command-r7b-12-2024 arrived, first seen on Experiential Labs
- command-r-plus-08-2024 arrived, first seen on Experiential Labs
- command-r-08-2024 arrived, first seen on Experiential Labs
- claude-sonnet-latest arrived, first seen on Experiential Labs
- claude-opus-latest arrived, first seen on Experiential Labs
- claude-haiku-latest arrived, first seen on Experiential Labs
- claude-fable-latest arrived, first seen on Experiential Labs
- aion-rp-llama-3.1-8b arrived, first seen on Experiential Labs
- Mistral Large 4 arrived, first seen on SayGM
- wonder-3.5 arrived, first seen on Cheaper Inference
- wizardlm-2-8x22b arrived, first seen on Cheaper Inference
- whisper-large-v3-turbo arrived, first seen on Cheaper Inference
- whisper-large-v3 arrived, first seen on Cheaper Inference
- whisper-1 arrived, first seen on Cheaper Inference
- wan-v3.0-video-prime arrived, first seen on Cheaper Inference
- wan-v3.0-video arrived, first seen on Cheaper Inference
- wan-v2.7-t2v arrived, first seen on Cheaper Inference
- wan-v2.7-r2v arrived, first seen on Cheaper Inference
- wan-v2.6-t2v arrived, first seen on Cheaper Inference
- wan-v2.6-r2v-flash arrived, first seen on Cheaper Inference
- wan-v2.6-r2v arrived, first seen on Cheaper Inference
- wan-v2.6-i2v-flash arrived, first seen on Cheaper Inference
- wan-v2.6-i2v arrived, first seen on Cheaper Inference
- wan-v2.5-t2v-preview arrived, first seen on Cheaper Inference
- voxtral-small-transcribe-3 arrived, first seen on Cheaper Inference
- voxtral-mini-tts-3 arrived, first seen on Cheaper Inference
- voxtral-mini-transcribe-3 arrived, first seen on Cheaper Inference
- veo-3.1-lite-generate-001 arrived, first seen on Cheaper Inference
- veo-3.1-generate-001 arrived, first seen on Cheaper Inference
- veo-3.1-fast-generate-001 arrived, first seen on Cheaper Inference
- veo-3.0-generate-001 arrived, first seen on Cheaper Inference
- veo-3.0-fast-generate-001 arrived, first seen on Cheaper Inference
- transcribe-1 arrived, first seen on Cheaper Inference
- toast-1 arrived, first seen on Cheaper Inference
- titan-embed-text-v2 arrived, first seen on Cheaper Inference
- sound-effects-v2 arrived, first seen on Cheaper Inference
- seedance-v1.5-pro arrived, first seen on Cheaper Inference
- seedance-v1.0-pro-fast arrived, first seen on Cheaper Inference
- seedance-v1.0-pro arrived, first seen on Cheaper Inference
- seed-2.1-turbo arrived on 2 gateways at once
- seed-2.0-code arrived on 2 gateways at once
- seed-1.8 arrived, first seen on Cheaper Inference
- seed-1.6 arrived on 2 gateways at once
- scribe-v2-realtime arrived, first seen on Cheaper Inference
- scribe-v2 arrived, first seen on Cheaper Inference
- schematron-v2-turbo arrived, first seen on Cheaper Inference
- schematron-v2-small arrived, first seen on Cheaper Inference
- s2.1-pro arrived, first seen on Cheaper Inference
- s2-pro arrived, first seen on Cheaper Inference
- s1 arrived, first seen on Cheaper Inference
- rerank-v5-pro arrived, first seen on Cheaper Inference
- rerank-v5-fast arrived, first seen on Cheaper Inference
- rerank-v4-pro arrived, first seen on Cheaper Inference
- rerank-v4-fast arrived, first seen on Cheaper Inference
- rerank-v3.5 arrived, first seen on Cheaper Inference
- qwen3.8-max-prime arrived, first seen on Cheaper Inference
- qwen3.8-max-0902 arrived on 2 gateways at once
- qwen3-vl-30b-a3b-thinking arrived, first seen on Cheaper Inference
- qwen3-vl-235b-a22b-thinking arrived, first seen on Cheaper Inference
- qwen3-next-80b-a3b-thinking arrived on 2 gateways at once
- qwen3-next-80b-a3b-instruct arrived, first seen on Cheaper Inference
- qwen3-embedding-4b arrived, first seen on Cheaper Inference
- qwen3-coder-30b-a3b-instruct arrived, first seen on Cheaper Inference
- qwen3-coder arrived, first seen on Cheaper Inference
- qwen3-235b-a22b-thinking-2507 arrived, first seen on Cheaper Inference
- qwen3-235b-a22b-2507 arrived, first seen on Cheaper Inference
- pplx-embed-v1-4b arrived, first seen on Cheaper Inference
- pplx-embed-v1-0.6b arrived, first seen on Cheaper Inference
- pplx-decider-v1.2 arrived, first seen on Cheaper Inference
- pplx-decider-flash-v1.2 arrived, first seen on Cheaper Inference
- music-v2.5 arrived, first seen on Cheaper Inference
- music-v2 arrived, first seen on Cheaper Inference
- moondream3.1-9b-a2b arrived, first seen on Cheaper Inference
- mercury-coder-small arrived on 2 gateways at once
- mercury-2 arrived on 3 gateways at once
- ling-3.1-flash-1019 arrived, first seen on Cheaper Inference
- ling-3.0-flash-sante arrived on 2 gateways at once
- ling-3.0-flash-fin arrived on 2 gateways at once
- laya-free arrived, first seen on Cheaper Inference
- laya arrived, first seen on Cheaper Inference
- joey-1 arrived, first seen on Cheaper Inference
- glimpse arrived, first seen on Cheaper Inference
- flux-pro-1.1-ultra arrived, first seen on Cheaper Inference
- flux-pro-1.1 arrived, first seen on Cheaper Inference
- flux-pro-1.0-fill arrived, first seen on Cheaper Inference
- flux-kontext-pro arrived, first seen on Cheaper Inference
- flux-kontext-max arrived, first seen on Cheaper Inference
- flux-3-video arrived, first seen on Cheaper Inference
- flux-3-image-klein arrived, first seen on Cheaper Inference
- flux-3-image arrived, first seen on Cheaper Inference
- flux-2-pro arrived, first seen on Cheaper Inference
- flux-2-max arrived, first seen on Cheaper Inference
- flux-2-klein-9b arrived, first seen on Cheaper Inference
- flux-2-klein-4b arrived, first seen on Cheaper Inference
- flux-2-flex arrived, first seen on Cheaper Inference
- embed-v5.0-pro arrived, first seen on Cheaper Inference
- embed-v5.0-fast arrived, first seen on Cheaper Inference
- embed-v4.0 arrived, first seen on Cheaper Inference
- command-a-plus arrived, first seen on Cheaper Inference
- claude-sonnet-5.5-batch arrived, first seen on Cheaper Inference
- claude-sonnet-5-batch arrived, first seen on Cheaper Inference
- claude-sonnet-4.6-batch arrived, first seen on Cheaper Inference
- claude-sonnet-4.5-batch arrived, first seen on Cheaper Inference
- claude-opus-5.5-fast arrived, first seen on Cheaper Inference
- claude-opus-5.5-batch arrived, first seen on Cheaper Inference
- claude-opus-5-fast arrived, first seen on Cheaper Inference
- claude-opus-5-batch arrived, first seen on Cheaper Inference
- claude-opus-4.8-fast arrived, first seen on Cheaper Inference
- claude-opus-4.8-batch arrived, first seen on Cheaper Inference
- claude-opus-4.7-batch arrived, first seen on Cheaper Inference
- claude-opus-4.6-batch arrived, first seen on Cheaper Inference
- claude-opus-4.5-batch arrived, first seen on Cheaper Inference
- claude-haiku-5.5-batch arrived, first seen on Cheaper Inference
- claude-haiku-4.5-batch arrived, first seen on Cheaper Inference
- claude-fable-5.1-batch arrived, first seen on Cheaper Inference
- claude-fable-5-batch arrived, first seen on Cheaper Inference
- bge-large-en-v1.5 arrived, first seen on Cheaper Inference
- bge-base-en-v1.5 arrived, first seen on Cheaper Inference
- PrismML Bonsai 2 27B arrived, first seen on Darkbloom
- TTS-1 HD arrived on 2 gateways at once
- TTS-1 arrived on 2 gateways at once
- Text Multilingual Embedding 002 arrived on 2 gateways at once
- Text Embedding Ada 002 arrived on 2 gateways at once
- Text Embedding 3 Small arrived on 2 gateways at once
- Text Embedding 3 Large arrived on 2 gateways at once
- Text Embedding 005 arrived on 2 gateways at once
- Sonar arrived on 3 gateways at once
- Seedream 5.0 Pro arrived on 2 gateways at once
- Seedream 5.0 Lite arrived on 2 gateways at once
- Seedream 4.5 arrived on 2 gateways at once
- Seedream 4.0 arrived on 2 gateways at once
- Seedance 2.5 arrived on 2 gateways at once
- Seedance 2.0 Mini arrived on 2 gateways at once
- Seedance 2.0 Fast arrived on 2 gateways at once
- Seedance 2.0 arrived on 2 gateways at once
- Qwen3.8 2.4T A95B arrived on 3 gateways at once
- Qwen3.6 35B A3B arrived on 4 gateways at once
- Qwen3 VL 30B A3B Instruct arrived on 2 gateways at once
- Qwen3 VL 235B A22B Instruct arrived on 2 gateways at once
- Qwen3 Reranker 8B arrived, first seen on LLM Gateway
- Qwen3 Embedding 8B arrived on 2 gateways at once
- Qwen3 Embedding 0.6B arrived on 2 gateways at once
- Qwen3 30B A3B arrived on 3 gateways at once
- Qwen Image 3.0 Pro arrived, first seen on LLM Gateway
- Muse Image 1.0 arrived on 2 gateways at once
- Ling 3.0 Flash VL arrived on 3 gateways at once
- Ling 3.0 Flash arrived on 3 gateways at once
- Claude Sonnet 4.5 (2025-09-29) arrived, first seen on LLM Gateway
- Claude Opus 4.5 arrived, first seen on LLM Gateway
- Claude Haiku 4.5 (2025-10-01) arrived, first seen on LLM Gateway
- BGE-M3 arrived on 2 gateways at once
- QwQ 32B arrived, first seen on Concentrate
- Qwen3.8 Omni Flash arrived on 3 gateways at once
- Qwen3.8 Max arrived on 4 gateways at once
- Qwen3.8 27B arrived on 5 gateways at once
- Qwen3.7 Plus arrived on 4 gateways at once
- Qwen3.7 Max arrived on 4 gateways at once
- Qwen3.7 Flash arrived on 4 gateways at once
- Qwen3.6 Plus arrived on 4 gateways at once
- Qwen3.6 Flash arrived on 3 gateways at once
- Qwen3.6 27B arrived on 4 gateways at once
- Qwen3.5 Plus arrived on 2 gateways at once
- Qwen3.5 Flash arrived on 2 gateways at once
- Qwen3.5 9B arrived on 5 gateways at once
- Qwen3.5 397B A17B arrived on 3 gateways at once
- Qwen3.5 35B A3B arrived on 5 gateways at once
- Qwen3.5 27B arrived on 4 gateways at once
- Qwen3.5 122B A10B arrived on 4 gateways at once
- Qwen3 VL 235B A22B arrived, first seen on Concentrate
- Qwen3 Next 80B A3B arrived, first seen on Concentrate
- Qwen3 Max Thinking arrived on 2 gateways at once
- Qwen3 Max arrived, first seen on Concentrate
- Qwen3 Coder Next arrived on 2 gateways at once
- Qwen3 Coder Flash arrived on 3 gateways at once
- Qwen3 Coder 30B A3B arrived on 2 gateways at once
- Qwen3 32B arrived on 3 gateways at once
- Qwen3 14B arrived on 3 gateways at once
- Amazon Nova Pro arrived on 2 gateways at once
- Amazon Nova Micro arrived on 2 gateways at once
- Amazon Nova Lite arrived on 2 gateways at once
- Amazon Nova 2 Lite arrived on 2 gateways at once
- Muse Wonder arrived, first seen on Concentrate
- Muse Spark 1.3 Contributor arrived on 4 gateways at once
- Muse Spark 1.2 Contributor arrived on 4 gateways at once
- Mercury 3 arrived on 3 gateways at once
- Mercury 2.5 arrived on 2 gateways at once
- Mammoth 1 arrived on 2 gateways at once
- Jamba 1.5 Mini arrived, first seen on Concentrate
- Jamba 1.5 Large arrived, first seen on Concentrate
- Elephant 1 arrived on 2 gateways at once
- Command A arrived on 3 gateways at once
- Claude Opus 4.5 arrived on 3 gateways at once
- Claude Opus 4.1 arrived, first seen on Concentrate
- jev-1.14 arrived, first seen on OrcaRouter
- Muse Wonder arrived on 4 gateways at once
- Muse Spark 1.3 arrived on 5 gateways at once
- Muse Spark 1.2 arrived on 5 gateways at once
- Muse Spark 1.1 arrived on 5 gateways at once
- Claude Sonnet 4.6 arrived on 5 gateways at once
- Claude Sonnet 4.5 arrived on 5 gateways at once
- Claude Opus 4.6 arrived on 5 gateways at once
- Claude Haiku 5.5 arrived on 5 gateways at once
- Claude Haiku 4.5 arrived on 5 gateways at once
- Claude Fable 5.1 arrived on 5 gateways at once
- Claude Fable 5 arrived on 5 gateways at once
- mistral-large-4-0-8 arrived, first seen on Cloudflare AI Gateway
- Ling 3.1 Flash 1019 arrived on 2 gateways at once
Added (919)
- Isoquant added glm-5.3-flash
- Isoquant added deepseek-v4.1-flash-1017
- NanoGPT added Phi 4 Multimodal
- NanoGPT added Phi 4 Mini
- NanoGPT added OrcaCyber Zero 1.5
- NanoGPT added MiniMax M1
- NanoGPT added Mercury Coder Small
- NanoGPT added Mercury 2
- NanoGPT added LongCat 2.0
- NanoGPT added Gemma 4 12B Instruct
- NanoGPT added Gemini 3 Pro Image
- NanoGPT added Gemini 2.5 Pro Preview 0605
- NanoGPT added Gemini 2.5 Pro Preview 0506
- NanoGPT added Gemini 2.5 Pro Preview 0325
- NanoGPT added Gemini 2.5 Pro Experimental 0325
- NanoGPT added Gemini 2.5 Pro
- NanoGPT added Gemini 2.5 Flash Preview (09/2025)
- NanoGPT added Gemini 2.5 Flash 0520 Thinking
- NanoGPT added Gemini 2.5 Flash 0520
- NanoGPT added Gemini 2.5 Flash Preview
- NanoGPT added Gemini 2.5 Flash Lite Preview (09/2025)
- NanoGPT added Gemini 2.5 Flash Lite Preview
- NanoGPT added Gemini 2.5 Flash Lite
- NanoGPT added Gemini 2.5 Flash
- NanoGPT added DeepSeek Chat 0324
- NanoGPT added DeepSeek V3/Deepseek Chat
- NanoGPT added Celeris 1
- Experiential Labs added glm-latest
- Experiential Labs added glm-5v-turbo
- Experiential Labs added glm-5.3-uncensored
- Experiential Labs added glm-5.3-flash-uncensored
- Experiential Labs added glm-5.3-flash
- Experiential Labs added glm-5.3
- Experiential Labs added glm-5.2
- Experiential Labs added glm-5.1
- Experiential Labs added glm-5-turbo
- Experiential Labs added glm-5
- Experiential Labs added glm-4.7-flash
- Experiential Labs added glm-4.7
- Experiential Labs added glm-4.6v
- Experiential Labs added mimo-v2.6-pro-ultraspeed
- Experiential Labs added mimo-v2.6-pro
- Experiential Labs added grok-latest
- Experiential Labs added grok-code-fast-1
- Experiential Labs added grok-build-0.1
- Experiential Labs added grok-4.7
- Experiential Labs added grok-4.6
- Experiential Labs added grok-4.5
- Experiential Labs added grok-4.3
- Experiential Labs added grok-4.20-non-reasoning
- Experiential Labs added grok-4.20-multi-agent
- Experiential Labs added grok-4.20
- Experiential Labs added grok-4
- Experiential Labs added weaver
- Experiential Labs added solar-pro4
- Experiential Labs added solar-pro-3
- Experiential Labs added unslopnemo-12b
- Experiential Labs added remm-slerp-l2-13b
- Experiential Labs added ui-tars-1.5-7b
- Experiential Labs added inkling-small
- Experiential Labs added inkling
- Experiential Labs added skyfall-36b-v2
- Experiential Labs added cydonia-24b-v4.1
- Experiential Labs added hy4-preview
- Experiential Labs added hy3-preview
- Experiential Labs added hy3
- Experiential Labs added hy-mt2-7b
- Experiential Labs added hy-mt2-30b-a3b
- Experiential Labs added hy-mt2-1.8b
- Experiential Labs added hunyuan-a13b-instruct
- Experiential Labs added step-3.5-flash
- Experiential Labs added sonar-reasoning-pro
- Experiential Labs added sonar-pro-search
- Experiential Labs added sonar-pro
- Experiential Labs added sonar
- Experiential Labs added seed-2.1-turbo
- Experiential Labs added seed-2.0-mini
- Experiential Labs added seed-2.0-lite
- Experiential Labs added seed-2.0-code
- Experiential Labs added seed-1.6-flash
- Experiential Labs added seed-1.6
- Experiential Labs added fugu-ultra-v2
- Experiential Labs added fugu-ultra
- Experiential Labs added fugu-max
- Experiential Labs added relace-search
- Experiential Labs added relace-apply-3
- Experiential Labs added qwen3.8-max-0902
- Experiential Labs added qwen3.8-max
- Experiential Labs added qwen3.8-flash
- Experiential Labs added qwen3.8-27b
- Experiential Labs added qwen3.8-2.4t-a95b
- Experiential Labs added qwen3.7-plus
- Experiential Labs added qwen3.7-max
- Experiential Labs added qwen3.7-flash
- Experiential Labs added qwen3.6-plus
- Experiential Labs added qwen3.6-flash
- Experiential Labs added qwen3.6-35b-a3b
- Experiential Labs added qwen3.6-27b
- Experiential Labs added qwen3.5-plus-20260420
- Experiential Labs added qwen3.5-plus-02-15
- Experiential Labs added qwen3.5-flash-02-23
- Experiential Labs added qwen3.5-9b
- Experiential Labs added qwen3.5-397b-a17b
- Experiential Labs added qwen3.5-35b-a3b
- Experiential Labs added qwen3.5-27b
- Experiential Labs added qwen3.5-122b-a10b
- Experiential Labs added qwen3-next-80b-a3b-thinking
- Experiential Labs added qwen3-coder-flash
- Experiential Labs added qwen3-8b
- Experiential Labs added qwen3-32b
- Experiential Labs added qwen3-30b-a3b
- Experiential Labs added qwen3-14b
- Experiential Labs added qwen2.5-vl-72b-instruct
- Experiential Labs added qwen-plus
- Experiential Labs added laguna-xs-2.1
- Experiential Labs added laguna-s-2.1
- Experiential Labs added phi-4
- Experiential Labs added perceptron-mk1
- Experiential Labs added o4-mini-high
- Experiential Labs added o4-mini
- Experiential Labs added o3-mini-high
- Experiential Labs added o3-mini
- Experiential Labs added gpt-oss-safeguard-20b
- Experiential Labs added gpt-oss-20b
- Experiential Labs added gpt-oss-120b
- Experiential Labs added gpt-mini-latest
- Experiential Labs added gpt-latest
- Experiential Labs added gpt-chat-latest
- Experiential Labs added gpt-6.1-sol
- Experiential Labs added gpt-6-sol
- Experiential Labs added gpt-6-luna
- Experiential Labs added gpt-6-astra
- Experiential Labs added gpt-5.6-terra
- Experiential Labs added gpt-5.6-sol
- Experiential Labs added gpt-5.6-luna
- Experiential Labs added gpt-5.5-pro
- Experiential Labs added gpt-5.5
- Experiential Labs added gpt-5.4-pro
- Experiential Labs added gpt-5.4-nano
- Experiential Labs added gpt-5.4-mini
- Experiential Labs added gpt-5.4
- Experiential Labs added gpt-5.3-codex
- Experiential Labs added gpt-5.2-codex
- Experiential Labs added gpt-5.2
- Experiential Labs added gpt-5.1-codex-mini
- Experiential Labs added gpt-5.1-codex-max
- Experiential Labs added gpt-5.1-codex
- Experiential Labs added gpt-5.1
- Experiential Labs added gpt-5-nano
- Experiential Labs added gpt-5-mini
- Experiential Labs added gpt-5
- Experiential Labs added gpt-4o-mini
- Experiential Labs added gpt-4o
- Experiential Labs added gpt-4.1-nano
- Experiential Labs added gpt-4.1-mini
- Experiential Labs added gpt-4.1
- Experiential Labs added gpt-4-turbo
- Experiential Labs added gpt-3.5-turbo-16k
- Experiential Labs added gpt-3.5-turbo-0613
- Experiential Labs added nemotron-3.5-lightning
- Experiential Labs added nemotron-3-ultra-550b-a55b
- Experiential Labs added nemotron-3-super-120b-a12b
- Experiential Labs added nemotron-3-nano-30b-a3b
- Experiential Labs added nova-premier-v1
- Experiential Labs added nova-2-lite-v1
- Experiential Labs added hermes-4-405b
- Experiential Labs added hermes-3-llama-3.1-70b
- Experiential Labs added hermes-3-llama-3.1-405b
- Experiential Labs added muse-wonder-1.0
- Experiential Labs added muse-spark-1.3-contributor
- Experiential Labs added muse-spark-1.3
- Experiential Labs added muse-spark-1.2-contributor
- Experiential Labs added muse-spark-1.2
- Experiential Labs added muse-spark-1.1
- Experiential Labs added morph-v3-large
- Experiential Labs added morph-v3-fast
- Experiential Labs added kimi-latest
- Experiential Labs added kimi-k3
- Experiential Labs added kimi-k2.7-code
- Experiential Labs added kimi-k2.6
- Experiential Labs added kimi-k2.5
- Experiential Labs added kimi-k2-thinking
- Experiential Labs added kimi-k2-0905
- Experiential Labs added mixtral-8x22b-instruct
- Experiential Labs added mistral-small-3.2-24b-instruct
- Experiential Labs added mistral-small-3.1-24b-instruct
- Experiential Labs added mistral-small-2603
- Experiential Labs added mistral-saba
- Experiential Labs added mistral-nemo
- Experiential Labs added mistral-medium-3.5
- Experiential Labs added mistral-medium-3.1
- Experiential Labs added mistral-medium-3
- Experiential Labs added mistral-large-4
- Experiential Labs added mistral-large-3
- Experiential Labs added mistral-large-2407
- Experiential Labs added mistral-large
- Experiential Labs added ministral-3-8b-instruct
- Experiential Labs added ministral-14b-2512
- Experiential Labs added codestral-2508
- Experiential Labs added minimax-m3
- Experiential Labs added minimax-m2.5
- Experiential Labs added minimax-m2.1
- Experiential Labs added minimax-m2-her
- Experiential Labs added minimax-m2
- Experiential Labs added minimax-m1
- Experiential Labs added minimax-01
- Experiential Labs added llama-guard-4-12b
- Experiential Labs added llama-4-scout
- Experiential Labs added llama-4-maverick
- Experiential Labs added llama-3.3-70b-instruct
- Experiential Labs added llama-3.1-70b-instruct
- Experiential Labs added mercury-3
- Experiential Labs added mercury-2
- Experiential Labs added longcat-2.0
- Experiential Labs added magnum-v4-72b
- Experiential Labs added ling-3.1-flash
- Experiential Labs added ling-3.0-flash-vl
- Experiential Labs added ling-3.0-flash-sante
- Experiential Labs added ling-3.0-flash-fin
- Experiential Labs added ling-3.0-flash
- Experiential Labs added gemma-4-31b-it
- Experiential Labs added gemma-4-26b-a4b-it
- Experiential Labs added gemma-3-4b-it
- Experiential Labs added gemma-3-27b-it
- Experiential Labs added gemma-3-12b-it
- Experiential Labs added gemma-2-27b-it
- Experiential Labs added gemini-pro-latest
- Experiential Labs added gemini-flash-latest
- Experiential Labs added gemini-4-argon
- Experiential Labs added gemini-3.8-flash
- Experiential Labs added gemini-3.7-flash
- Experiential Labs added gemini-3.6-flash
- Experiential Labs added gemini-3.5-flash-lite
- Experiential Labs added gemini-3.5-flash
- Experiential Labs added gemini-3.1-pro-preview-customtools
- Experiential Labs added gemini-3.1-pro-preview
- Experiential Labs added gemini-3.1-flash-lite-image
- Experiential Labs added gemini-3.1-flash-lite
- Experiential Labs added gemini-3.1-flash-image
- Experiential Labs added gemini-3-pro-image
- Experiential Labs added gemini-3-flash-preview
- Experiential Labs added gemini-2.5-pro-preview
- Experiential Labs added gemini-2.5-pro
- Experiential Labs added gemini-2.5-flash-lite
- Experiential Labs added gemini-2.5-flash-image
- Experiential Labs added gemini-2.5-flash
- Experiential Labs added ernie-4.5-vl-424b-a47b
- Experiential Labs added dolphin-mistral-24b-venice-edition
- Experiential Labs added deepseek-v4.1-flash-uncensored
- Experiential Labs added deepseek-v4.1-flash-1017
- Experiential Labs added deepseek-v4.1-flash
- Experiential Labs added deepseek-v4-pro-0813
- Experiential Labs added deepseek-v4-pro
- Experiential Labs added deepseek-v4-flash-latest
- Experiential Labs added deepseek-v4-flash-0731
- Experiential Labs added deepseek-v4-flash
- Experiential Labs added deepseek-v3.2-speciale
- Experiential Labs added deepseek-v3.2-exp
- Experiential Labs added deepseek-v3.2
- Experiential Labs added deepseek-r1-0528
- Experiential Labs added deepseek-r1
- Experiential Labs added command-r7b-12-2024
- Experiential Labs added command-r-plus-08-2024
- Experiential Labs added command-r-08-2024
- Experiential Labs added command-a
- Experiential Labs added claude-sonnet-latest
- Experiential Labs added claude-sonnet-5.5
- Experiential Labs added claude-sonnet-5
- Experiential Labs added claude-sonnet-4.6
- Experiential Labs added claude-sonnet-4.5
- Experiential Labs added claude-opus-latest
- Experiential Labs added claude-opus-5.5
- Experiential Labs added claude-opus-5
- Experiential Labs added claude-opus-4.8
- Experiential Labs added claude-opus-4.7
- Experiential Labs added claude-opus-4.6
- Experiential Labs added claude-opus-4.5
- Experiential Labs added claude-haiku-latest
- Experiential Labs added claude-haiku-5.5
- Experiential Labs added claude-haiku-4.5
- Experiential Labs added claude-fable-latest
- Experiential Labs added claude-fable-5.1
- Experiential Labs added claude-fable-5
- Experiential Labs added aion-rp-llama-3.1-8b
- Experiential Labs added aion-3.0-mini
- Experiential Labs added aion-3.0
- Experiential Labs added aion-2.0
- SayGM added GLM-5.3-Flash
- SayGM added GLM-5.3
- SayGM added GLM-5.2
- SayGM added MiMo-V2.6-Pro-UltraSpeed
- SayGM added Qwen3.8-27B
- SayGM added Qwen3.6-35B-A3B
- SayGM added gpt-oss-20b
- SayGM added GPT-6.1 Terra
- SayGM added GPT-6.1 Sol
- SayGM added GPT-6 Sol
- SayGM added GPT-6 Luna
- SayGM added GPT-6 Astra
- SayGM added GPT-5.6 Terra
- SayGM added GPT-5.6 Sol
- SayGM added GPT-5.6 Luna
- SayGM added GPT-5.5 Pro
- SayGM added GPT-5.5
- SayGM added GPT-5.4 nano
- SayGM added GPT-5.4 mini
- SayGM added GPT-5.4
- SayGM added kimi-k3
- SayGM added Mistral Large 4
- SayGM added Mistral Large 4
- SayGM added Mistral Large 4
- SayGM added DeepSeek-V4.1-Flash-1017
- SayGM added DeepSeek-V4.1-Flash
- SayGM added DeepSeek-V4-Flash-0731
- Cheaper Inference added glm-5v-turbo
- Cheaper Inference added glm-5.3-flashx
- Cheaper Inference added glm-5.3-flash
- Cheaper Inference added glm-5.3-fast
- Cheaper Inference added glm-5.3
- Cheaper Inference added glm-5.2-fast
- Cheaper Inference added glm-5.2
- Cheaper Inference added glm-5.1
- Cheaper Inference added glm-5-turbo
- Cheaper Inference added glm-5
- Cheaper Inference added glm-4.7-flashx
- Cheaper Inference added glm-4.7-flash
- Cheaper Inference added glm-4.7
- Cheaper Inference added glm-4.6v
- Cheaper Inference added glm-4.6
- Cheaper Inference added glm-4.5v
- Cheaper Inference added glm-4.5-air
- Cheaper Inference added glm-4.5
- Cheaper Inference added autoglm-phone-9b-multilingual
- Cheaper Inference added mimo-v2.6-pro-ultraspeed
- Cheaper Inference added mimo-v2.6-pro
- Cheaper Inference added mimo-v2.5-pro
- Cheaper Inference added mimo-v2.5
- Cheaper Inference added grok-voice-think-fast-2.0
- Cheaper Inference added grok-voice-3.0
- Cheaper Inference added grok-tts
- Cheaper Inference added grok-stt
- Cheaper Inference added grok-imagine-video-1.5-lite
- Cheaper Inference added grok-imagine-video-1.5
- Cheaper Inference added grok-imagine-video
- Cheaper Inference added grok-imagine-image-2.0
- Cheaper Inference added grok-imagine-image
- Cheaper Inference added grok-code-fast-1
- Cheaper Inference added grok-build-0.1
- Cheaper Inference added grok-4.7
- Cheaper Inference added grok-4.6
- Cheaper Inference added grok-4.5
- Cheaper Inference added grok-4.3-batch
- Cheaper Inference added grok-4.3
- Cheaper Inference added grok-4.20-reasoning-beta
- Cheaper Inference added grok-4.20-reasoning-batch
- Cheaper Inference added grok-4.20-reasoning
- Cheaper Inference added grok-4.20-non-reasoning-beta
- Cheaper Inference added grok-4.20-non-reasoning-batch
- Cheaper Inference added grok-4.20-non-reasoning
- Cheaper Inference added grok-4.20-multi-agent-beta
- Cheaper Inference added grok-4.20-multi-agent-batch
- Cheaper Inference added grok-4.20-multi-agent
- Cheaper Inference added grok-4.1-fast-reasoning
- Cheaper Inference added grok-4.1-fast-non-reasoning
- Cheaper Inference added grok-4
- Cheaper Inference added wonder-3.5
- Cheaper Inference added wizardlm-2-8x22b
- Cheaper Inference added whisper-large-v3-turbo
- Cheaper Inference added whisper-large-v3
- Cheaper Inference added whisper-1
- Cheaper Inference added wan-v3.0-video-prime
- Cheaper Inference added wan-v3.0-video
- Cheaper Inference added wan-v2.7-t2v
- Cheaper Inference added wan-v2.7-r2v
- Cheaper Inference added wan-v2.6-t2v
- Cheaper Inference added wan-v2.6-r2v-flash
- Cheaper Inference added wan-v2.6-r2v
- Cheaper Inference added wan-v2.6-i2v-flash
- Cheaper Inference added wan-v2.6-i2v
- Cheaper Inference added wan-v2.5-t2v-preview
- Cheaper Inference added voyage-law-2
- Cheaper Inference added voyage-finance-2
- Cheaper Inference added voyage-code-3
- Cheaper Inference added voyage-code-2
- Cheaper Inference added voyage-4-lite
- Cheaper Inference added voyage-4-large
- Cheaper Inference added voyage-4
- Cheaper Inference added voyage-3.5-lite
- Cheaper Inference added voyage-3.5
- Cheaper Inference added voyage-3-large
- Cheaper Inference added rerank-3-lite
- Cheaper Inference added rerank-3
- Cheaper Inference added rerank-2.5-lite
- Cheaper Inference added rerank-2.5
- Cheaper Inference added voxtral-small-transcribe-3
- Cheaper Inference added voxtral-mini-tts-3
- Cheaper Inference added voxtral-mini-transcribe-3
- Cheaper Inference added veo-3.1-lite-generate-001
- Cheaper Inference added veo-3.1-generate-001
- Cheaper Inference added veo-3.1-fast-generate-001
- Cheaper Inference added veo-3.0-generate-001
- Cheaper Inference added veo-3.0-fast-generate-001
- Cheaper Inference added pareto-26.9
- Cheaper Inference added jev-1.13.0
- Cheaper Inference added jev
- Cheaper Inference added tts-1-hd
- Cheaper Inference added tts-1
- Cheaper Inference added transcribe-1
- Cheaper Inference added starlight-precise-2.6
- Cheaper Inference added proteus
- Cheaper Inference added toast-1
- Cheaper Inference added titan-embed-text-v2
- Cheaper Inference added inkling-small
- Cheaper Inference added inkling
- Cheaper Inference added text-multilingual-embedding-002
- Cheaper Inference added text-embedding-ada-002
- Cheaper Inference added text-embedding-3-small
- Cheaper Inference added text-embedding-3-large
- Cheaper Inference added text-embedding-005
- Cheaper Inference added hy4-preview
- Cheaper Inference added hy3
- Cheaper Inference added hy-mt2-pro
- Cheaper Inference added hy-mt2-plus
- Cheaper Inference added hy-mt2-lite
- Cheaper Inference added glyph-cluster
- Cheaper Inference added sound-effects-v2
- Cheaper Inference added sonar
- Cheaper Inference added seedream-5.0-pro
- Cheaper Inference added seedream-5.0-lite
- Cheaper Inference added seedream-4.5
- Cheaper Inference added seedream-4.0
- Cheaper Inference added seedance-v1.5-pro
- Cheaper Inference added seedance-v1.0-pro-fast
- Cheaper Inference added seedance-v1.0-pro
- Cheaper Inference added seedance-2.5
- Cheaper Inference added seedance-2.0-mini
- Cheaper Inference added seedance-2.0-fast
- Cheaper Inference added seedance-2.0
- Cheaper Inference added seed-2.1-turbo
- Cheaper Inference added seed-2.0-code
- Cheaper Inference added seed-1.8
- Cheaper Inference added seed-1.6
- Cheaper Inference added scribe-v2-realtime
- Cheaper Inference added scribe-v2
- Cheaper Inference added schematron-v2-turbo
- Cheaper Inference added schematron-v2-small
- Cheaper Inference added scaledown-summarize-1
- Cheaper Inference added scaledown-extract-1
- Cheaper Inference added scaledown-classify-1
- Cheaper Inference added l3-8b-stheno-v3.2
- Cheaper Inference added namazu
- Cheaper Inference added fugu-ultra-v2
- Cheaper Inference added fugu-ultra
- Cheaper Inference added fugu-max
- Cheaper Inference added s2.1-pro
- Cheaper Inference added s2-pro
- Cheaper Inference added s1
- Cheaper Inference added rerank-v5-pro
- Cheaper Inference added rerank-v5-fast
- Cheaper Inference added rerank-v4-pro
- Cheaper Inference added rerank-v4-fast
- Cheaper Inference added rerank-v3.5
- Cheaper Inference added beam-free
- Cheaper Inference added beam
- Cheaper Inference added recraft-v4.1-utility-pro
- Cheaper Inference added recraft-v4.1-utility
- Cheaper Inference added recraft-v4.1-pro
- Cheaper Inference added recraft-v4.1-flash
- Cheaper Inference added recraft-v4.1
- Cheaper Inference added recraft-v4-pro
- Cheaper Inference added recraft-v4
- Cheaper Inference added recraft-v3
- Cheaper Inference added recraft-v2
- Cheaper Inference added qwen3.8-omni-flash
- Cheaper Inference added qwen3.8-max-prime
- Cheaper Inference added qwen3.8-max-0902
- Cheaper Inference added qwen3.8-max
- Cheaper Inference added qwen3.8-flash
- Cheaper Inference added qwen3.8-27b
- Cheaper Inference added qwen3.8-2.4t-a95b
- Cheaper Inference added qwen3.7-plus
- Cheaper Inference added qwen3.7-max
- Cheaper Inference added qwen3.7-flash
- Cheaper Inference added qwen3.6-plus
- Cheaper Inference added qwen3.6-35b-a3b
- Cheaper Inference added qwen3.6-27b
- Cheaper Inference added qwen3.5-plus
- Cheaper Inference added qwen3.5-flash
- Cheaper Inference added qwen3.5-9b
- Cheaper Inference added qwen3.5-397b-a17b
- Cheaper Inference added qwen3.5-35b-a3b
- Cheaper Inference added qwen3.5-27b
- Cheaper Inference added qwen3.5-122b-a10b
- Cheaper Inference added qwen3-vl-30b-a3b-thinking
- Cheaper Inference added qwen3-vl-30b-a3b-instruct
- Cheaper Inference added qwen3-vl-235b-a22b-thinking
- Cheaper Inference added qwen3-vl-235b-a22b-instruct
- Cheaper Inference added qwen3-next-80b-a3b-thinking
- Cheaper Inference added qwen3-next-80b-a3b-instruct
- Cheaper Inference added qwen3-max-thinking
- Cheaper Inference added qwen3-embedding-8b
- Cheaper Inference added qwen3-embedding-4b
- Cheaper Inference added qwen3-embedding-0.6b
- Cheaper Inference added qwen3-coder-next
- Cheaper Inference added qwen3-coder-30b-a3b-instruct
- Cheaper Inference added qwen3-coder-30b-a3b
- Cheaper Inference added qwen3-coder
- Cheaper Inference added qwen3-30b-a3b
- Cheaper Inference added qwen3-235b-a22b-thinking-2507
- Cheaper Inference added qwen3-235b-a22b-2507
- Cheaper Inference added arrow-2-telos
- Cheaper Inference added arrow-2
- Cheaper Inference added flux-fast-schnell
- Cheaper Inference added pplx-embed-v1-4b
- Cheaper Inference added pplx-embed-v1-0.6b
- Cheaper Inference added pplx-decider-v1.2
- Cheaper Inference added pplx-decider-flash-v1.2
- Cheaper Inference added laguna-s-2.1
- Cheaper Inference added particle-1
- Cheaper Inference added o4-mini
- Cheaper Inference added o3-pro
- Cheaper Inference added o3-mini
- Cheaper Inference added o3-fast
- Cheaper Inference added gpt-transcribe
- Cheaper Inference added gpt-realtime-whisper
- Cheaper Inference added gpt-realtime-mini
- Cheaper Inference added gpt-realtime-2.1
- Cheaper Inference added gpt-realtime-2
- Cheaper Inference added gpt-realtime-1.5
- Cheaper Inference added gpt-oss-safeguard-20b
- Cheaper Inference added gpt-oss-safeguard-120b
- Cheaper Inference added gpt-oss-20b
- Cheaper Inference added gpt-oss-120b
- Cheaper Inference added gpt-live-transcribe
- Cheaper Inference added gpt-live-1
- Cheaper Inference added gpt-image-2.5-sunburst
- Cheaper Inference added gpt-image-2.5-flare
- Cheaper Inference added gpt-image-2
- Cheaper Inference added gpt-image-1.5
- Cheaper Inference added gpt-image-1-mini
- Cheaper Inference added gpt-6.1-terra-pro
- Cheaper Inference added gpt-6.1-terra-fast
- Cheaper Inference added gpt-6.1-terra
- Cheaper Inference added gpt-6.1-sol-fast
- Cheaper Inference added gpt-6.1-sol-batch
- Cheaper Inference added gpt-6.1-sol
- Cheaper Inference added gpt-6-sol-pro
- Cheaper Inference added gpt-6-sol-fast
- Cheaper Inference added gpt-6-sol-batch
- Cheaper Inference added gpt-6-sol
- Cheaper Inference added gpt-6-luna-fast
- Cheaper Inference added gpt-6-luna-decisions
- Cheaper Inference added gpt-6-luna-batch
- Cheaper Inference added gpt-6-luna
- Cheaper Inference added gpt-6-astra-fast
- Cheaper Inference added gpt-6-astra-batch
- Cheaper Inference added gpt-6-astra
- Cheaper Inference added gpt-5.6-terra-pro
- Cheaper Inference added gpt-5.6-terra-fast
- Cheaper Inference added gpt-5.6-terra-batch
- Cheaper Inference added gpt-5.6-terra
- Cheaper Inference added gpt-5.6-sol-pro
- Cheaper Inference added gpt-5.6-sol-fast
- Cheaper Inference added gpt-5.6-sol-batch
- Cheaper Inference added gpt-5.6-sol
- Cheaper Inference added gpt-5.6-luna-pro
- Cheaper Inference added gpt-5.6-luna-fast
- Cheaper Inference added gpt-5.6-luna-batch
- Cheaper Inference added gpt-5.6-luna
- Cheaper Inference added gpt-5.5-pro-batch
- Cheaper Inference added gpt-5.5-pro
- Cheaper Inference added gpt-5.5-fast
- Cheaper Inference added gpt-5.5-batch
- Cheaper Inference added gpt-5.5
- Cheaper Inference added gpt-5.4-pro
- Cheaper Inference added gpt-5.4-nano-batch
- Cheaper Inference added gpt-5.4-nano
- Cheaper Inference added gpt-5.4-mini-fast
- Cheaper Inference added gpt-5.4-mini-batch
- Cheaper Inference added gpt-5.4-mini
- Cheaper Inference added gpt-5.4-fast
- Cheaper Inference added gpt-5.4-batch
- Cheaper Inference added gpt-5.4
- Cheaper Inference added gpt-5.3-codex-fast
- Cheaper Inference added gpt-5.3-codex
- Cheaper Inference added gpt-5.2-pro
- Cheaper Inference added gpt-5.2-fast
- Cheaper Inference added gpt-5.2-codex
- Cheaper Inference added gpt-5.2-batch
- Cheaper Inference added gpt-5.2
- Cheaper Inference added gpt-5.1-thinking-fast
- Cheaper Inference added gpt-5.1-thinking
- Cheaper Inference added gpt-5.1-codex-mini
- Cheaper Inference added gpt-5.1-codex-max
- Cheaper Inference added gpt-5.1-codex
- Cheaper Inference added gpt-5.1
- Cheaper Inference added gpt-5-pro-batch
- Cheaper Inference added gpt-5-pro
- Cheaper Inference added gpt-5-nano-batch
- Cheaper Inference added gpt-5-nano
- Cheaper Inference added gpt-5-mini-fast
- Cheaper Inference added gpt-5-mini-batch
- Cheaper Inference added gpt-5-mini
- Cheaper Inference added gpt-5-image-mini
- Cheaper Inference added gpt-5-fast
- Cheaper Inference added gpt-5-codex
- Cheaper Inference added gpt-5-batch
- Cheaper Inference added gpt-5
- Cheaper Inference added gpt-4o-transcribe
- Cheaper Inference added gpt-4o-mini-transcribe
- Cheaper Inference added gpt-4o-mini-fast
- Cheaper Inference added gpt-4o-mini-batch
- Cheaper Inference added gpt-4o-mini
- Cheaper Inference added gpt-4o-fast
- Cheaper Inference added gpt-4o-batch
- Cheaper Inference added gpt-4o
- Cheaper Inference added gpt-4.1-nano
- Cheaper Inference added gpt-4.1-mini-fast
- Cheaper Inference added gpt-4.1-mini-batch
- Cheaper Inference added gpt-4.1-mini
- Cheaper Inference added gpt-4.1-fast
- Cheaper Inference added gpt-4.1-batch
- Cheaper Inference added gpt-4.1
- Cheaper Inference added nemotron-nano-9b-v2
- Cheaper Inference added nemotron-nano-12b-v2-vl
- Cheaper Inference added nemotron-3.5-super-vl
- Cheaper Inference added nemotron-3.5-lightning-free
- Cheaper Inference added nemotron-3.5-lightning
- Cheaper Inference added nemotron-3-ultra-550b-a55b
- Cheaper Inference added nemotron-3-super-120b-a12b
- Cheaper Inference added nemotron-3-nano-30b-a3b
- Cheaper Inference added nova-pro
- Cheaper Inference added nova-micro
- Cheaper Inference added nova-lite
- Cheaper Inference added nova-2-lite
- Cheaper Inference added music-v2.5
- Cheaper Inference added music-v2
- Cheaper Inference added muse-wonder-1.0
- Cheaper Inference added muse-spark-1.3-contributor
- Cheaper Inference added muse-spark-1.3
- Cheaper Inference added muse-spark-1.2-contributor
- Cheaper Inference added muse-spark-1.2
- Cheaper Inference added muse-spark-1.1
- Cheaper Inference added muse-image-1.0
- Cheaper Inference added muse-glimmer-30b
- Cheaper Inference added morph-v3-large
- Cheaper Inference added morph-v3-fast
- Cheaper Inference added kimi-k3.1-pro-highspeed
- Cheaper Inference added kimi-k3.1-pro
- Cheaper Inference added kimi-k3-fast
- Cheaper Inference added kimi-k3
- Cheaper Inference added kimi-k2.7-code-highspeed
- Cheaper Inference added kimi-k2.7-code
- Cheaper Inference added kimi-k2.6
- Cheaper Inference added kimi-k2.5
- Cheaper Inference added kimi-k2-thinking
- Cheaper Inference added kimi-k2-0905
- Cheaper Inference added kimi-k2
- Cheaper Inference added moondream3.1-9b-a2b
- Cheaper Inference added moondream3.1-9b-a2b
- Cheaper Inference added mistral-small-3.2-24b-instruct
- Cheaper Inference added mistral-small
- Cheaper Inference added mistral-nemo
- Cheaper Inference added mistral-medium-3.5
- Cheaper Inference added mistral-large-4
- Cheaper Inference added mistral-large-3
- Cheaper Inference added mistral-large
- Cheaper Inference added mistral-embed
- Cheaper Inference added ministral-8b
- Cheaper Inference added ministral-3b
- Cheaper Inference added ministral-14b
- Cheaper Inference added devstral-2-123b
- Cheaper Inference added codestral-embed
- Cheaper Inference added codestral
- Cheaper Inference added minimax-m1-80k
- Cheaper Inference added minimax-m3.1-flash
- Cheaper Inference added minimax-m3
- Cheaper Inference added minimax-m2.7-highspeed
- Cheaper Inference added minimax-m2.7
- Cheaper Inference added minimax-m2.5-highspeed
- Cheaper Inference added minimax-m2.5
- Cheaper Inference added minimax-m2.1-lightning
- Cheaper Inference added minimax-m2.1
- Cheaper Inference added minimax-m2
- Cheaper Inference added minimax-h3-max
- Cheaper Inference added minimax-h3
- Cheaper Inference added microsoft-decision-1
- Cheaper Inference added mai-voice-2.1-flash
- Cheaper Inference added mai-voice-2.1
- Cheaper Inference added mai-voice-2-flash
- Cheaper Inference added mai-voice-2
- Cheaper Inference added mai-transcribe-2-streaming
- Cheaper Inference added mai-transcribe-2
- Cheaper Inference added mai-image-2.6-flash
- Cheaper Inference added mai-image-2.6
- Cheaper Inference added llama-4-scout
- Cheaper Inference added llama-4-maverick
- Cheaper Inference added llama-3.3-70b
- Cheaper Inference added llama-3.2-3b-instruct
- Cheaper Inference added llama-3.1-70b
- Cheaper Inference added mercury-coder-small
- Cheaper Inference added mercury-3
- Cheaper Inference added mercury-2.5
- Cheaper Inference added mercury-2
- Cheaper Inference added longcat-2.5-preview
- Cheaper Inference added mammoth-1
- Cheaper Inference added d1-ultra
- Cheaper Inference added d1
- Cheaper Inference added ling-3.1-flash-1019
- Cheaper Inference added ling-3.1-flash
- Cheaper Inference added ling-3.0-flash-vl
- Cheaper Inference added ling-3.0-flash-sante
- Cheaper Inference added ling-3.0-flash-fin
- Cheaper Inference added ling-3.0-flash
- Cheaper Inference added laya-free
- Cheaper Inference added laya
- Cheaper Inference added kling-v3.0-t2v
- Cheaper Inference added kling-v3.0-motion-control
- Cheaper Inference added kling-v3.0-i2v
- Cheaper Inference added kling-v2.6-t2v
- Cheaper Inference added kling-v2.6-motion-control
- Cheaper Inference added kling-v2.6-i2v
- Cheaper Inference added kling-v2.5-turbo-t2v
- Cheaper Inference added kling-v2.5-turbo-i2v
- Cheaper Inference added joey-1
- Cheaper Inference added interfaze-beta
- Cheaper Inference added ling-3.1-flash-1019
- Cheaper Inference added heygen-video-1
- Cheaper Inference added gemma-4-31b-it
- Cheaper Inference added gemma-4-26b-a4b-it
- Cheaper Inference added gemma-3-4b-it
- Cheaper Inference added gemma-3-27b-it
- Cheaper Inference added gemma-3-12b-it
- Cheaper Inference added gemini-omni-flash-preview
- Cheaper Inference added gemini-nano-banana-2.1
- Cheaper Inference added gemini-embedding-2
- Cheaper Inference added gemini-embedding-001
- Cheaper Inference added gemini-4-argon
- Cheaper Inference added gemini-3.8-live-extended-thinking
- Cheaper Inference added gemini-3.8-live
- Cheaper Inference added gemini-3.8-flash-tts
- Cheaper Inference added gemini-3.8-flash-lite-tts
- Cheaper Inference added gemini-3.8-flash
- Cheaper Inference added gemini-3.7-flash-batch
- Cheaper Inference added gemini-3.7-flash
- Cheaper Inference added gemini-3.6-flash-batch
- Cheaper Inference added gemini-3.6-flash
- Cheaper Inference added gemini-3.5-transcribe-live
- Cheaper Inference added gemini-3.5-transcribe
- Cheaper Inference added gemini-3.5-flash-lite-batch
- Cheaper Inference added gemini-3.5-flash-lite
- Cheaper Inference added gemini-3.5-flash-batch
- Cheaper Inference added gemini-3.5-flash
- Cheaper Inference added gemini-3.1-pro-preview-batch
- Cheaper Inference added gemini-3.1-pro-preview
- Cheaper Inference added gemini-3.1-flash-lite-image
- Cheaper Inference added gemini-3.1-flash-lite-batch
- Cheaper Inference added gemini-3.1-flash-lite
- Cheaper Inference added gemini-3.1-flash-image
- Cheaper Inference added gemini-3-pro-image
- Cheaper Inference added gemini-3-flash-batch
- Cheaper Inference added gemini-3-flash
- Cheaper Inference added gemini-2.5-pro-preview-06-05
- Cheaper Inference added gemini-2.5-pro-batch
- Cheaper Inference added gemini-2.5-pro
- Cheaper Inference added gemini-2.5-flash-lite-batch
- Cheaper Inference added gemini-2.5-flash-lite
- Cheaper Inference added gemini-2.5-flash-image
- Cheaper Inference added gemini-2.5-flash-batch
- Cheaper Inference added gemini-2.5-flash
- Cheaper Inference added glimpse
- Cheaper Inference added flux-pro-1.1-ultra
- Cheaper Inference added flux-pro-1.1
- Cheaper Inference added flux-pro-1.0-fill
- Cheaper Inference added flux-kontext-pro
- Cheaper Inference added flux-kontext-max
- Cheaper Inference added flux-3-video
- Cheaper Inference added flux-3-image-klein
- Cheaper Inference added flux-3-image
- Cheaper Inference added flux-2-pro
- Cheaper Inference added flux-2-max
- Cheaper Inference added flux-2-klein-9b
- Cheaper Inference added flux-2-klein-4b
- Cheaper Inference added flux-2-flex
- Cheaper Inference added drama-3
- Cheaper Inference added embed-v5.0-pro
- Cheaper Inference added embed-v5.0-fast
- Cheaper Inference added embed-v4.0
- Cheaper Inference added eleven-v4-turbo
- Cheaper Inference added eleven-v4
- Cheaper Inference added eleven-v3-conversational
- Cheaper Inference added eleven-v3
- Cheaper Inference added eleven-realtime-v1-mini
- Cheaper Inference added eleven-realtime-v1-max
- Cheaper Inference added eleven-multilingual-v2
- Cheaper Inference added eleven-flash-v2.5
- Cheaper Inference added eleven-flash-v2
- Cheaper Inference added elephant-1
- Cheaper Inference added deepseek-v4.1-flash-fast
- Cheaper Inference added deepseek-v4.1-flash-1017-fast
- Cheaper Inference added deepseek-v4.1-flash-1017
- Cheaper Inference added deepseek-v4.1-flash
- Cheaper Inference added deepseek-v4-pro-0813
- Cheaper Inference added deepseek-v4-pro
- Cheaper Inference added deepseek-v4-flash-vision-exp
- Cheaper Inference added deepseek-v4-flash-0731
- Cheaper Inference added deepseek-v4-flash
- Cheaper Inference added deepseek-v3.2-thinking
- Cheaper Inference added deepseek-v3.2
- Cheaper Inference added deepseek-v3.1
- Cheaper Inference added deepseek-v3
- Cheaper Inference added deepseek-r1-turbo
- Cheaper Inference added deepseek-r1-0528
- Cheaper Inference added deepseek-r1
- Cheaper Inference added command-a-plus
- Cheaper Inference added command-a
- Cheaper Inference added claude-sonnet-5.5-batch
- Cheaper Inference added claude-sonnet-5.5
- Cheaper Inference added claude-sonnet-5-batch
- Cheaper Inference added claude-sonnet-5
- Cheaper Inference added claude-sonnet-4.6-batch
- Cheaper Inference added claude-sonnet-4.6
- Cheaper Inference added claude-sonnet-4.5-batch
- Cheaper Inference added claude-sonnet-4.5
- Cheaper Inference added claude-opus-5.5-fast
- Cheaper Inference added claude-opus-5.5-batch
- Cheaper Inference added claude-opus-5.5
- Cheaper Inference added claude-opus-5-fast
- Cheaper Inference added claude-opus-5-batch
- Cheaper Inference added claude-opus-5
- Cheaper Inference added claude-opus-4.8-fast
- Cheaper Inference added claude-opus-4.8-batch
- Cheaper Inference added claude-opus-4.8
- Cheaper Inference added claude-opus-4.7-batch
- Cheaper Inference added claude-opus-4.7
- Cheaper Inference added claude-opus-4.6-batch
- Cheaper Inference added claude-opus-4.6
- Cheaper Inference added claude-opus-4.5-batch
- Cheaper Inference added claude-opus-4.5
- Cheaper Inference added claude-haiku-5.5-batch
- Cheaper Inference added claude-haiku-5.5
- Cheaper Inference added claude-haiku-4.5-batch
- Cheaper Inference added claude-haiku-4.5
- Cheaper Inference added claude-fable-5.1-batch
- Cheaper Inference added claude-fable-5.1
- Cheaper Inference added claude-fable-5-batch
- Cheaper Inference added claude-fable-5
- Cheaper Inference added apex
- Cheaper Inference added bge-m3
- Cheaper Inference added bge-large-en-v1.5
- Cheaper Inference added bge-base-en-v1.5
- Cheaper Inference added aion-3.5-mini
- Cheaper Inference added aion-3.5
- Cheaper Inference added aion-3.0-mini
- Cheaper Inference added aion-3.0
- Darkbloom added Z.ai: GLM-5.3-Flash
- Darkbloom added PrismML Bonsai 2 27B
- Darkbloom added Qwen 3.5 9B
- Darkbloom added Qwen3.5 35B A3B
- Darkbloom added GPT-OSS 20B
- LLM Gateway added GLM-5V Turbo
- LLM Gateway added GLM-5.3 FlashX
- LLM Gateway added GLM-5.3 Flash
- LLM Gateway added GLM 5.3 Fast
- LLM Gateway added GLM-5.3
- LLM Gateway added GLM-5.2 Turbo
- LLM Gateway added GLM-5.2
- LLM Gateway added GLM-5.1
- LLM Gateway added GLM-5 Turbo
- LLM Gateway added GLM-5
- LLM Gateway added GLM-4.7 FlashX
- LLM Gateway added GLM-4.7
- LLM Gateway added GLM-4.6V
- LLM Gateway added GLM-4.6
- LLM Gateway added GLM-4.5V
- LLM Gateway added GLM-4.5 Air
- LLM Gateway added GLM-4.5
- LLM Gateway added MiMo V2.6 Pro
- LLM Gateway added Grok Voice 3.0
- LLM Gateway added Grok Imagine Video 1.5 Preview
- LLM Gateway added Grok Imagine Video 1.5 Lite
- LLM Gateway added Grok Imagine Video 1.5
- LLM Gateway added Grok Imagine Image 2.0
- LLM Gateway added Grok Imagine Image
- LLM Gateway added Grok Build 0.1
- LLM Gateway added Grok 4.7
- LLM Gateway added Grok 4.6
- LLM Gateway added Grok 4.5
- LLM Gateway added Grok 4.3
- LLM Gateway added Grok 4.1 Fast Reasoning
- LLM Gateway added Grok 4.20 Reasoning
- LLM Gateway added Grok 4.20 Non-Reasoning
- LLM Gateway added Grok 4
- LLM Gateway added TTS-1 HD
- LLM Gateway added TTS-1
- LLM Gateway added Text Multilingual Embedding 002
- LLM Gateway added Text Embedding Ada 002
- LLM Gateway added Text Embedding 3 Small
- LLM Gateway added Text Embedding 3 Large
- LLM Gateway added Text Embedding 005
- LLM Gateway added Hy4 Preview
- LLM Gateway added Hy3
- LLM Gateway added Hy-MT2 Plus
- LLM Gateway added Sonar
- LLM Gateway added Seedream 5.0 Pro
- LLM Gateway added Seedream 5.0 Lite
- LLM Gateway added Seedream 4.5
- LLM Gateway added Seedream 4.0
- LLM Gateway added Seedance 2.5
- LLM Gateway added Seedance 2.0 Mini
- LLM Gateway added Seedance 2.0 Fast
- LLM Gateway added Seedance 2.0
- LLM Gateway added Fugu Ultra
- LLM Gateway added Fugu Max
- LLM Gateway added Qwen3.8 Omni Flash
- LLM Gateway added Qwen3.8 Max
- LLM Gateway added Qwen3.8 27B
- LLM Gateway added Qwen3.8 2.4T A95B
- LLM Gateway added Qwen3.7 Plus
Price changes (227)
- NanoGPT cut input 51.1% to $0.086 and output 9.3% to $1.40 on GLM 5.2 Thinking
- NanoGPT cut input 51.1% to $0.086 and output 9.3% to $1.40 on GLM 5.2
- NanoGPT cut input 32.4% to $0.050 and raised output 37.6% to $0.150 on Qwen3.5 9B
- NanoGPT cut input 78.7% to $0.010 and output 78.9% to $0.030 on Gemma 4 26B A4B Thinking
- NanoGPT cut input 78.7% to $0.010 and output 78.9% to $0.030 on Gemma 4 26B A4B
- NanoGPT cut input 75.6% to $0.022 and output 23.2% to $0.192 on DeepSeek V4.1 Flash Thinking
- NanoGPT cut input 75.6% to $0.022 and output 23.2% to $0.192 on DeepSeek V4.1 Flash
- SayGM raised input 26% to $1.30 and output 26% to $5.19 on o3
- SayGM cut input 2% to $1.70 and output 2% to $8.48 on kimi-k3
- SayGM cut input 10% to $0.649 and output 10% to $3.24 on GPT-6.1 Terra
- SayGM raised input 2.4% to $1.24 and output 2.4% to $6.18 on GPT-6.1 Sol
- SayGM raised input 2.4% to $1.24 and output 2.4% to $6.18 on GPT-6 Sol
- SayGM raised input 2.4% to $0.062 and output 2.4% to $0.309 on GPT-6 Luna
- SayGM raised input 2.4% to $6.18 and output 2.4% to $30.90 on GPT-6 Astra
- SayGM raised input 2.4% to $1.24 and output 2.4% to $7.42 on GPT-5.6 Terra
- SayGM raised input 2.4% to $2.47 and output 2.4% to $12.36 on GPT-5.6 Sol
- SayGM raised input 2.4% to $0.124 and output 2.4% to $0.742 on GPT-5.6 Luna
- SayGM raised input 26% to $19.47 and output 26% to $117 on GPT-5.5 Pro
- SayGM raised input 20% to $3.09 and output 20% to $18.54 on GPT-5.5
- SayGM raised input 20% to $0.124 and output 20% to $0.772 on GPT-5.4 nano
- SayGM raised input 20% to $0.464 and output 20% to $2.78 on GPT-5.4 mini
- SayGM raised input 20% to $1.54 and output 20% to $9.27 on GPT-5.4
- SayGM cut input 24.1% to $0.097 and output 24.1% to $0.324 on GLM-5.3-Flash
- SayGM cut input 3% to $0.684 and output 3% to $2.15 on GLM-5.2
- SayGM cut input 50% to $0.023 and output 50% to $0.068 on DeepSeek-V4-Flash-0731
- Cheaper Inference cut input 15.6% to $0.091 and output 15.6% to $0.182 on mimo-v2.6-flash
- Cheaper Inference cut input 5.9% to $80.00 on venice-whisper-large-v3
- Cheaper Inference raised input 6.2% to $0.345 and output 6.2% to $1.38 on venice-uncensored-role-play
- Cheaper Inference cut input 23.5% to $0.027 on jev-1.14.0
- Cheaper Inference cut input 12.5% to $150 on tts-gemini-3-1-flash
- Cheaper Inference raised input 30.8% to $0.043 on scaledown-classify-1
- Cheaper Inference cut input 23.5% to $0.098 and output 23.5% to $0.305 on qwen3.8-omni-flash
- Cheaper Inference cut input 23.5% to $2.60 and output 23.5% to $7.80 on qwen3.8-max-prime
- Cheaper Inference raised input 19.4% to $1.67 and output 19.4% to $5.01 on qwen3.8-max
- Cheaper Inference raised input 30.8% to $0.128 and output 30.8% to $0.400 on qwen3.8-flash
- Cheaper Inference raised input 7.6% to $1.70 and output 7.6% to $5.10 on qwen3.8-2.4t-a95b
- Cheaper Inference raised input 18.5% to $0.308 and output 18.5% to $1.23 on qwen3.7-plus
- Cheaper Inference cut input 19.8% to $0.019 and output 19.8% to $0.085 on qwen3.7-flash
- Cheaper Inference cut input 23.5% to $0.065 and output 23.5% to $0.098 on qwen3.5-9b
- Cheaper Inference cut input 23.5% to $0.260 and output 23.5% to $2.08 on qwen3.5-122b-a10b
- Cheaper Inference cut input 6.7% to $0.098 and output 6.7% to $0.780 on qwen3-next-80b-a3b-instruct
- Cheaper Inference cut input 23.5% to $0.078 and output 23.5% to $0.325 on qwen3-30b-a3b
- Cheaper Inference cut input 19.8% to $0.149 and output 19.8% to $1.50 on qwen3-235b-a22b-thinking-2507
- Cheaper Inference cut input 23.5% to $0.078 and output 23.5% to $0.325 on qwen-3-30b
- Cheaper Inference cut input 23.5% to $0.052 and output 23.5% to $0.130 on qwen-3-14b
- Cheaper Inference raised input 26% to $0.102 and output 26% to $0.409 on particle-1
- Cheaper Inference cut input 23.5% to $1.63 and output 23.5% to $4.88 on pareto-26.9
- Cheaper Inference raised input 30.8% to $85.00 on whisper-1
- Cheaper Inference raised input 30.8% to $25.50 on tts-1-hd
- Cheaper Inference raised input 30.8% to $12.75 on tts-1
- Cheaper Inference raised input 30.8% to $0.017 on text-embedding-3-small
- Cheaper Inference raised input 30.8% to $1.70 and output 30.8% to $6.80 on o3
- Cheaper Inference raised input 30.8% to $12.75 and output 30.8% to $51.00 on o1
- Cheaper Inference raised input 30.8% to $17.00 and output 30.8% to $68.00 on o3-pro
- Cheaper Inference raised input 30.8% to $0.935 and output 30.8% to $3.74 on o3-mini
- Cheaper Inference raised input 30.8% to $2.98 and output 30.8% to $11.90 on o3-fast
- Cheaper Inference cut input 11% to $0.130 and output 11% to $0.325 on nemotron-3.5-super-vl
- Cheaper Inference cut input 13.6% to $0.333 and output 13.6% to $1.67 on nemotron-3-ultra-550b-a55b
- Cheaper Inference raised input 30.8% to $0.765 and output 30.8% to $1.61 on morph-v3-large
- Cheaper Inference raised input 30.8% to $0.680 and output 30.8% to $1.02 on morph-v3-fast
- Cheaper Inference raised input 30.8% to $56.67 on voxtral-small-transcribe-3
- Cheaper Inference raised input 30.8% to $13.60 on voxtral-mini-tts-3
- Cheaper Inference raised input 30.8% to $49.59 on voxtral-mini-transcribe-3
- Cheaper Inference cut input 9.4% to $0.098 and output 9.4% to $0.390 on mistral-small
- Cheaper Inference raised input 10.4% to $0.128 and output 10.4% to $0.128 on ministral-8b
- Cheaper Inference cut input 23.5% to $0.065 and output 23.5% to $0.065 on ministral-3b
- Cheaper Inference cut input 13.3% to $0.098 and output 13.3% to $0.390 on minimax-m3.1-flash
- Cheaper Inference cut input 23.5% to $0.390 and output 23.5% to $1.56 on minimax-m2.7-highspeed
- Cheaper Inference cut input 23.5% to $2.83 and output 23.5% to $5.66 on mimo-v2.6-pro-ultraspeed
- Cheaper Inference cut input 13.7% to $0.300 and output 13.7% to $0.600 on mimo-v2.6-pro
- Cheaper Inference cut input 18.8% to $0.091 and output 18.8% to $0.182 on mimo-v2.5
- Cheaper Inference cut input 23.5% to $0.813 and output 23.5% to $2.76 on muse-spark-open
- Cheaper Inference cut input 23.5% to $0.813 and output 23.5% to $2.76 on muse-spark-1.3
- Cheaper Inference cut input 2.8% to $0.065 and output 2.8% to $0.130 on muse-spark-1.2-contributor
- Cheaper Inference cut input 23.5% to $0.813 and output 23.5% to $2.76 on muse-spark-1.2
- Cheaper Inference cut input 23.5% to $0.813 and output 23.5% to $2.76 on muse-spark-1.1
- Cheaper Inference cut input 23.5% to $0.228 and output 23.5% to $0.975 on muse-glimmer-30b
- Cheaper Inference raised input 30.8% to $23.61 on mai-transcribe-2
- Cheaper Inference raised input 30.8% to $1.49 and output 30.8% to $16.15 on mai-image-2.6-flash
- Cheaper Inference cut input 23.5% to $0.065 and output 23.5% to $0.195 on llama-4-scout
- Cheaper Inference cut input 23.5% to $0.122 and output 23.5% to $0.390 on llama-4-maverick
- Cheaper Inference cut input 23.5% to $0.065 and output 23.5% to $0.208 on llama-3.3-70b
- Cheaper Inference cut input 22.1% to $0.033 and output 22.1% to $0.214 on llama-3.2-3b-instruct
- Cheaper Inference raised input 30.8% to $0.289 and output 30.8% to $0.332 on llama-3.1-70b
- Cheaper Inference cut input 23.5% to $0.033 and output 23.5% to $0.455 on lfm2.5-24b-a2b
- Cheaper Inference raised input 30.8% to $0.076 and output 30.8% to $0.153 on laguna-s-2.1
- Cheaper Inference raised input 2.1% to $1.70 and output 2.1% to $8.50 on kimi-k3.1-pro
- Cheaper Inference raised input 30.8% to $3.83 and output 30.8% to $19.13 on kimi-k3-fast
- Cheaper Inference raised input 30.8% to $1.61 and output 30.8% to $6.80 on kimi-k2.7-code-highspeed
- Cheaper Inference cut input 18.6% to $0.618 and output 18.6% to $2.60 on kimi-k2.6
- Cheaper Inference raised input 30.8% to $0.400 and output 30.8% to $1.70 on kimi-k2-thinking
- Cheaper Inference cut input 9.4% to $0.439 and output 9.4% to $1.77 on kimi-k2
- Cheaper Inference cut input 23.5% to $0.027 on jev-1.13.0
- Cheaper Inference raised input 30.8% to $1.27 and output 30.8% to $2.98 on interfaze-beta
- Cheaper Inference raised input 30.8% to $0.025 and output 30.8% to $0.128 on schematron-v2-turbo
- Cheaper Inference raised input 30.8% to $0.043 and output 30.8% to $0.196 on schematron-v2-small
- Cheaper Inference cut input 23.5% to $0.026 and output 23.5% to $0.098 on mercury-2.5
- Cheaper Inference raised input 4.4% to $0.170 and output 4.4% to $0.509 on mercury-2
- Cheaper Inference raised input 30.8% to $0.037 and output 30.8% to $0.150 on hy-mt2-lite
- Cheaper Inference raised input 30.8% to $12.75 on grok-tts
- Cheaper Inference cut input 9.6% to $0.650 and output 9.6% to $1.30 on grok-build-0.1
- Cheaper Inference cut input 23.2% to $1.31 and output 23.2% to $3.92 on grok-4.7
- Cheaper Inference cut input 23.5% to $1.30 and output 23.5% to $3.90 on grok-4.6
- Cheaper Inference cut input 22% to $1.33 and output 22% to $3.98 on grok-4.5
- Cheaper Inference cut input 23.5% to $0.813 and output 23.5% to $1.63 on grok-4.20-reasoning-beta
- Cheaper Inference cut input 23.3% to $0.813 and output 23.3% to $1.63 on grok-4.20-non-reasoning
- Cheaper Inference cut input 22.6% to $0.813 and output 22.6% to $1.63 on grok-4.20-multi-agent-beta
- Cheaper Inference cut input 21.8% to $0.130 and output 21.8% to $0.325 on grok-4.1-fast-reasoning
- Cheaper Inference cut input 7.1% to $0.130 and output 7.1% to $0.325 on grok-4.1-fast-non-reasoning
- Cheaper Inference raised input 30.8% to $241 on gpt-live-transcribe
- Cheaper Inference raised input 30.8% to $4.25 and output 30.8% to $25.50 on gpt-image-2.5-sunburst
- Cheaper Inference raised input 30.8% to $1.70 and output 30.8% to $6.80 on gpt-image-1-mini
- Cheaper Inference cut input 23.5% to $0.650 and output 23.5% to $3.25 on gpt-6.1-terra-pro
- Cheaper Inference raised input 25.4% to $0.815 and output 25.4% to $4.08 on gpt-6.1-terra
- Cheaper Inference raised input 30.8% to $3.40 and output 30.8% to $17.00 on gpt-6.1-sol-fast
- Cheaper Inference raised input 2.2% to $1.33 and output 2.2% to $6.64 on gpt-6.1-sol
- Cheaper Inference cut input 23.5% to $1.30 and output 23.5% to $6.50 on gpt-6-sol-pro
- Cheaper Inference raised input 30.8% to $3.40 and output 30.8% to $17.00 on gpt-6-sol-fast
- Cheaper Inference raised input 10.6% to $1.44 and output 10.6% to $7.19 on gpt-6-sol
- Cheaper Inference raised input 30.8% to $0.170 and output 30.8% to $0.850 on gpt-6-luna-fast
- Cheaper Inference raised input 30.8% to $17.00 and output 30.8% to $85.00 on gpt-6-astra-fast
- Cheaper Inference cut input 23.5% to $1.30 and output 23.5% to $7.80 on gpt-5.6-terra-pro
- Cheaper Inference raised input 30.8% to $3.40 and output 30.8% to $20.40 on gpt-5.6-terra-fast
- Cheaper Inference cut input 34.2% to $0.878 and output 34.2% to $5.27 on gpt-5.6-terra
- Cheaper Inference cut input 8.1% to $1.30 and output 8.1% to $6.50 on gpt-5.6-sol-pro
- Cheaper Inference raised input 30.8% to $6.80 and output 30.8% to $34.00 on gpt-5.6-sol-fast
- Cheaper Inference raised input 34.7% to $2.77 and output 34.7% to $13.83 on gpt-5.6-sol
- Cheaper Inference cut input 23.5% to $0.130 and output 23.5% to $0.780 on gpt-5.6-luna-pro
- Cheaper Inference raised input 30.8% to $0.340 and output 30.8% to $2.04 on gpt-5.6-luna-fast
- Cheaper Inference raised input 51.3% to $0.165 and output 51.3% to $0.991 on gpt-5.6-luna
- Cheaper Inference raised input 30.8% to $10.63 and output 30.8% to $63.75 on gpt-5.5-fast
- Cheaper Inference cut input 23.5% to $19.50 and output 23.5% to $117 on gpt-5.4-pro
- Cheaper Inference raised input 30.8% to $1.27 and output 30.8% to $7.65 on gpt-5.4-mini-fast
- Cheaper Inference raised input 30.8% to $4.25 and output 30.8% to $25.50 on gpt-5.4-fast
- Cheaper Inference raised input 30.8% to $2.98 and output 30.8% to $23.80 on gpt-5.3-codex-fast
- Cheaper Inference cut input 12.7% to $1.14 and output 12.7% to $9.10 on gpt-5.3-codex
- Cheaper Inference raised input 30.8% to $17.85 and output 30.8% to $143 on gpt-5.2-pro
- Cheaper Inference raised input 30.8% to $2.98 and output 30.8% to $23.80 on gpt-5.2-fast
- Cheaper Inference raised input 30.8% to $2.13 and output 30.8% to $17.00 on gpt-5.1-thinking-fast
- Cheaper Inference raised input 30.8% to $1.06 and output 30.8% to $8.50 on gpt-5.1-thinking
- Cheaper Inference raised input 30.8% to $0.212 and output 30.8% to $1.70 on gpt-5.1-codex-mini
- Cheaper Inference raised input 30.8% to $1.06 and output 30.8% to $8.50 on gpt-5.1-codex-max
- Cheaper Inference raised input 30.8% to $1.06 and output 30.8% to $8.50 on gpt-5.1-codex
- Cheaper Inference cut input 3% to $1.00 and output 3% to $8.00 on gpt-5.1
- Cheaper Inference cut input 8.9% to $0.033 and output 8.9% to $0.260 on gpt-5-nano
- Cheaper Inference raised input 30.8% to $0.383 and output 30.8% to $3.06 on gpt-5-mini-fast
- Cheaper Inference raised input 10.4% to $2.13 and output 10.4% to $1.70 on gpt-5-image-mini
- Cheaper Inference raised input 30.8% to $2.13 and output 30.8% to $17.00 on gpt-5-fast
- Cheaper Inference raised input 30.8% to $1.06 and output 30.8% to $8.50 on gpt-5-codex
- Cheaper Inference cut input 23.5% to $0.813 and output 23.5% to $6.50 on gpt-5
- Cheaper Inference cut input 2.3% to $1.63 and output 2.3% to $6.50 on gpt-4o
- Cheaper Inference raised input 6.8% to $0.338 and output 6.8% to $1.35 on gpt-4.1-mini
- Cheaper Inference cut input 18.5% to $1.30 and output 18.5% to $5.20 on gpt-4.1
- Cheaper Inference cut input 12.4% to $0.802 and output 12.4% to $2.67 on glm-5v-turbo
- Cheaper Inference cut input 22.9% to $0.240 and output 22.9% to $0.813 on glm-5.3-flashx
- Cheaper Inference raised input 30.8% to $1.78 and output 30.8% to $5.61 on glm-5.3-fast
- Cheaper Inference raised input 7.7% to $1.96 and output 7.7% to $6.16 on glm-5.2-fast
- Cheaper Inference raised input 30.8% to $0.051 and output 30.8% to $0.340 on glm-4.7-flashx
- Cheaper Inference cut input 9.6% to $0.045 and output 9.6% to $0.260 on glm-4.7-flash-heretic
- Cheaper Inference cut input 33.5% to $0.330 and output 33.5% to $1.21 on glm-4.6
- Cheaper Inference cut input 27.1% to $0.122 and output 27.1% to $0.671 on glm-4.5-air
- Cheaper Inference raised input 39.4% to $0.460 and output 39.4% to $1.69 on glm-4.5
- Cheaper Inference raised input 9% to $0.115 and output 9% to $0.354 on gemma-4-uncensored
- Cheaper Inference raised input 30.8% to $0.119 and output 30.8% to $0.340 on gemma-4-31b-it
- Cheaper Inference raised input 30.8% to $0.128 on gemini-embedding-001
- Cheaper Inference raised input 30.8% to $0.637 and output 30.8% to $3.83 on gemini-3.8-live-extended-thinking
- Cheaper Inference raised input 30.8% to $0.637 and output 30.8% to $3.83 on gemini-3.8-live
- Cheaper Inference raised input 30.8% to $0.425 and output 30.8% to $5.10 on gemini-3.8-flash-lite-tts
- Cheaper Inference cut input 17.5% to $0.526 and output 17.5% to $2.63 on gemini-3.7-flash
- Cheaper Inference raised input 30.8% to $128 on gemini-3.5-transcribe-live
- Cheaper Inference raised input 30.8% to $1.70 and output 30.8% to $10.20 on gemini-3.5-transcribe
- Cheaper Inference raised input 4.3% to $1.61 and output 4.3% to $9.63 on gemini-3.1-pro-preview
- Cheaper Inference cut input 18.7% to $0.813 and output 18.7% to $6.50 on gemini-2.5-pro-preview-06-05
- Cheaper Inference raised input 7.2% to $0.085 and output 7.2% to $0.340 on gemini-2.5-flash-lite
- Cheaper Inference cut input 23.5% to $3.25 and output 23.5% to $19.50 on fugu-ultra-v2
- Cheaper Inference raised input 30.8% to $4.25 and output 30.8% to $25.50 on fugu-ultra
- Cheaper Inference cut input 11% to $1.30 and output 11% to $3.90 on fugu-max
- Cheaper Inference raised input 30.8% to $85.00 on transcribe-1
- Cheaper Inference cut input 23.5% to $1.95 and output 23.5% to $9.75 on ember-1
- Cheaper Inference cut input 11% to $0.390 and output 11% to $1.95 on glimpse
- Cheaper Inference raised input 3.5% to $0.251 and output 3.5% to $0.752 on e2ee-qwen3.6-35b-a3b-uncensored-p
- Cheaper Inference cut input 5% to $0.117 and output 5% to $0.767 on e2ee-qwen3.6-35b-a3b
- Cheaper Inference cut input 11% to $1.14 and output 11% to $3.74 on e2ee-glm-5.2-p
- Cheaper Inference cut input 3.7% to $0.118 and output 3.7% to $0.242 on e2ee-deepseek-v4-flash
- Cheaper Inference raised input 30.8% to $0.510 and output 30.8% to $2.04 on deepseek-v4.1-flash-fast
- Cheaper Inference raised input 19.7% to $0.561 and output 19.7% to $1.68 on deepseek-v4-pro-0813
- Cheaper Inference raised input 18.5% to $0.508 and output 18.5% to $1.52 on deepseek-v4-pro
- Cheaper Inference cut input 2.6% to $0.228 and output 2.6% to $0.455 on deepseek-v4-flash-0731-fast
- Cheaper Inference raised input 30.8% to $0.238 and output 30.8% to $0.357 on deepseek-v3.2-thinking
- Cheaper Inference raised input 30.8% to $0.036 on d1-ultra
- Cheaper Inference cut input 23.5% to $0.195 and output 23.5% to $0.975 on command-a-plus
- Cheaper Inference raised input 30.8% to $2.13 and output 30.8% to $8.50 on command-a
- Cheaper Inference raised input 30.8% to $0.255 and output 30.8% to $0.765 on codestral
- Cheaper Inference cut input 11.3% to $0.325 and output 11.3% to $1.63 on seed-2.1-turbo
- Cheaper Inference cut input 23.5% to $0.325 and output 23.5% to $1.95 on seed-2.0-code
- Cheaper Inference cut input 23.5% to $0.163 and output 23.5% to $1.30 on seed-1.8
- Cheaper Inference cut input 5% to $0.119 and output 4.9% to $0.477 on beam
- Cheaper Inference raised input 19.6% to $0.040 on elephant-1
- Cheaper Inference raised input 30.8% to $0.425 and output 30.8% to $2.55 on apex
- Cheaper Inference cut input 19.2% to $1.32 and output 19.2% to $6.60 on claude-sonnet-5.5
- Cheaper Inference raised input 3.5% to $1.35 and output 3.5% to $6.73 on claude-sonnet-5
- Cheaper Inference cut input 1.3% to $1.95 and output 1.3% to $9.75 on claude-sonnet-4.6
- Cheaper Inference cut input 9.1% to $2.10 and output 9.1% to $10.50 on claude-sonnet-4.5
- Cheaper Inference raised input 30.8% to $6.80 and output 30.8% to $34.00 on claude-opus-5.5-fast
- Cheaper Inference raised input 5.7% to $3.40 and output 5.7% to $16.99 on claude-opus-5.5
- Cheaper Inference cut input 23.3% to $6.50 and output 23.3% to $32.50 on claude-opus-5-fast
- Cheaper Inference raised input 22.8% to $4.25 and output 22.8% to $21.25 on claude-opus-5
- Cheaper Inference raised input 30.3% to $8.47 and output 30.3% to $42.34 on claude-opus-4.8-fast
- Cheaper Inference raised input 8.4% to $3.52 and output 8.4% to $17.62 on claude-opus-4.6
- Cheaper Inference raised input 8.8% to $4.19 and output 8.8% to $20.93 on claude-opus-4.5
- Cheaper Inference raised input 4.8% to $0.085 and output 4.8% to $0.425 on claude-haiku-5.5
- Cheaper Inference raised input 30.8% to $0.850 and output 30.8% to $4.25 on claude-haiku-4.5
- Cheaper Inference cut input 2.9% to $6.50 and output 2.9% to $32.50 on claude-fable-5
- Cheaper Inference raised input 30.8% to $0.030 and output 30.8% to $0.119 on nova-micro
- Cheaper Inference raised input 30.8% to $0.255 and output 30.8% to $2.13 on nova-2-lite
- Cheaper Inference cut input 1.5% to $0.586 and output 1.5% to $1.17 on aion-3.5-mini
- Cheaper Inference cut input 1.5% to $2.51 and output 1.5% to $5.03 on aion-3.5
- Cheaper Inference cut input 33% to $0.385 and output 33% to $0.770 on aion-3.0-mini
- Cheaper Inference cut input 1.5% to $1.65 and output 1.5% to $3.30 on aion-3.0
- Cheaper Inference cut input 17.6% to $0.813 and output 17.6% to $1.63 on abliteration-abliterated-model-large-flash
- Morph cut input 40% to $0.042 and output 40% to $0.300 on Morph: GLM-5.3-Flash
- Morph cut input 51.1% to $0.086 and output 9.3% to $1.40 on Morph: GLM-5.3
- Morph cut input 50% to $0.022 and output 49.9% to $0.192 on Morph: DeepSeek V4.1 Flash 1017
- Morph cut input 50% to $0.022 and output 49.9% to $0.192 on Morph: DeepSeek V4.1 Flash
- LLM Gateway raised input 33.3% to $0.800 and output 11.5% to $3.40 on Kimi K2.6
- LLM Gateway raised input 212.5% to $0.100 and output 257.1% to $0.500 on GPT OSS 120B
- LLM Gateway cut input 25.9% to $0.100 and output 44.4% to $0.300 on DeepSeek V4.1 Flash
Context window changes (2)
Dropped (55)
- Cheaper Inference dropped qwen-image-2
- Cheaper Inference dropped longcat
- Cheaper Inference dropped laguna-s-2.1-free
- Cheaper Inference dropped kling-o3-4k
- Cheaper Inference dropped tts-qwen3-1-7b
- Cheaper Inference dropped tts-minimax-speech-02-hd
- Cheaper Inference dropped vidu-q3
- Cheaper Inference dropped nano-banana-2
- Cheaper Inference dropped venice-xai-stt-v1
- Cheaper Inference dropped nano-banana
- Cheaper Inference dropped venice-whisper-1
- Cheaper Inference dropped venice-wan-2.7-pro
- Cheaper Inference dropped venice-wai-illustrious
- Cheaper Inference dropped venice-uncensored
- Cheaper Inference dropped venice-tts-1
- Cheaper Inference dropped venice-seedream-v4
- Cheaper Inference dropped venice-sdxl
- Cheaper Inference dropped venice-runway-gen4-5-text
- Cheaper Inference dropped venice-qwen-image-3-pro
- Cheaper Inference dropped venice-qwen-image-3
- Cheaper Inference dropped venice-qwen-image-2.1-turbo
- Cheaper Inference dropped venice-qwen-image-2.1-pro
- Cheaper Inference dropped venice-qwen-image-2-pro
- Cheaper Inference dropped venice-pixverse-c1
- Cheaper Inference dropped venice-nano-banana-2.1
- Cheaper Inference dropped venice-lustify-sdxl
- Cheaper Inference dropped venice-luma-uni-1-max
- Cheaper Inference dropped venice-luma-uni-1
- Cheaper Inference dropped venice-krea-v2-medium
- Cheaper Inference dropped venice-krea-v2-large
- Cheaper Inference dropped venice-ideogram-v4.5
- Cheaper Inference dropped venice-ideogram-v4
- Cheaper Inference dropped venice-grok-imagine-pro
- Cheaper Inference dropped venice-grok-imagine
- Cheaper Inference dropped venice-flux-1.1-pro
- Cheaper Inference dropped venice-flux-1.1
- Cheaper Inference dropped tts-qwen3-0-6b
- Cheaper Inference dropped tts-inworld-1-5-max
- Cheaper Inference dropped tts-chatterbox-hd
- Cheaper Inference dropped qwen-edit-uncensored
- Cheaper Inference dropped pixverse-v5.6
- Cheaper Inference dropped pixverse-c1
- Cheaper Inference dropped ovi
- Cheaper Inference dropped nano-banana-pro
- Cheaper Inference dropped luma-uni-1-max
- Cheaper Inference dropped luma-uni-1
- Cheaper Inference dropped trinity-large-thinking
- Cheaper Inference dropped ltx-2-v2.3-fast
- Cheaper Inference dropped gemini-3.1-flash-image-preview
- Cheaper Inference dropped happyhorse-1.1
- Cheaper Inference dropped gpt-6-luna-pro
- Cheaper Inference dropped e2ee-qwen-2.5-7b-p
- Cheaper Inference dropped e2ee-gemma-4-26b-a4b-uncensored-p
- Cheaper Inference dropped claude-opus-4.7-fast
- Cheaper Inference dropped claude-opus-4.6-fast
No longer available anywhere (48)
- qwen-image-2 is no longer served by any gateway we track
- longcat is no longer served by any gateway we track
- laguna-s-2.1-free is no longer served by any gateway we track
- kling-o3-4k is no longer served by any gateway we track
- tts-qwen3-1-7b is no longer served by any gateway we track
- tts-minimax-speech-02-hd is no longer served by any gateway we track
- vidu-q3 is no longer served by any gateway we track
- venice-xai-stt-v1 is no longer served by any gateway we track
- venice-whisper-1 is no longer served by any gateway we track
- venice-wan-2.7-pro is no longer served by any gateway we track
- venice-wai-illustrious is no longer served by any gateway we track
- venice-tts-1 is no longer served by any gateway we track
- venice-seedream-v4 is no longer served by any gateway we track
- venice-sdxl is no longer served by any gateway we track
- venice-runway-gen4-5-text is no longer served by any gateway we track
- venice-qwen-image-3-pro is no longer served by any gateway we track
- venice-qwen-image-3 is no longer served by any gateway we track
- venice-qwen-image-2.1-turbo is no longer served by any gateway we track
- venice-qwen-image-2.1-pro is no longer served by any gateway we track
- venice-qwen-image-2-pro is no longer served by any gateway we track
- venice-pixverse-c1 is no longer served by any gateway we track
- venice-nano-banana-2.1 is no longer served by any gateway we track
- venice-lustify-sdxl is no longer served by any gateway we track
- venice-luma-uni-1-max is no longer served by any gateway we track
- venice-luma-uni-1 is no longer served by any gateway we track
- venice-krea-v2-medium is no longer served by any gateway we track
- venice-krea-v2-large is no longer served by any gateway we track
- venice-ideogram-v4.5 is no longer served by any gateway we track
- venice-ideogram-v4 is no longer served by any gateway we track
- venice-grok-imagine-pro is no longer served by any gateway we track
- venice-grok-imagine is no longer served by any gateway we track
- venice-flux-1.1-pro is no longer served by any gateway we track
- venice-flux-1.1 is no longer served by any gateway we track
- tts-qwen3-0-6b is no longer served by any gateway we track
- tts-inworld-1-5-max is no longer served by any gateway we track
- tts-chatterbox-hd is no longer served by any gateway we track
- qwen-edit-uncensored is no longer served by any gateway we track
- pixverse-v5.6 is no longer served by any gateway we track
- pixverse-c1 is no longer served by any gateway we track
- ovi is no longer served by any gateway we track
- luma-uni-1-max is no longer served by any gateway we track
- luma-uni-1 is no longer served by any gateway we track
- ltx-2-v2.3-fast is no longer served by any gateway we track
- happyhorse-1.1 is no longer served by any gateway we track
- gpt-6-luna-pro is no longer served by any gateway we track
- e2ee-qwen-2.5-7b-p is no longer served by any gateway we track
- e2ee-gemma-4-26b-a4b-uncensored-p is no longer served by any gateway we track
- laguna-s-2.1-free is no longer served by any gateway we track
Recorded by the catalog crawl on 31 October 2026. Each line is a difference between that crawl and the one before it, not an announcement from the gateway.