v6.0

12 new model(s), 6 removed model(s).

New Models

The following models have been added, grouped by provider:

• nano-gpt: THUDM/GLM-4-32B-0414, THUDM/GLM-4-9B-0414, THUDM/GLM-Z1-32B-0414, THUDM/GLM-Z1-9B-0414, THUDM/GLM-Z1-Rumination-32B-0414
• nebius: zai-org/GLM-5
• nvidia: stepfun-ai/step-3.5-flash
• opencode: nemotron-3-super-free
• openrouter: openrouter/healer-alpha, openrouter/hunter-alpha
• synthetic: hf:MiniMaxAI/MiniMax-M2.5, hf:zai-org/GLM-4.7-Flash

Removed Models

The following models have been removed, grouped by provider:

• nano-gpt: THUDM 2/GLM-4-32B-0414, THUDM 2/GLM-4-9B-0414, THUDM 2/GLM-Z1-32B-0414, THUDM 2/GLM-Z1-9B-0414, THUDM 2/GLM-Z1-Rumination-32B-0414
• nvidia: stepfun-ai/step-3-5-flash

v5.0

54 new model(s), 20 removed model(s).

New Models

The following models have been added, grouped by provider:

• abacus: gpt-5.4
• alibaba-coding-plan-cn: MiniMax-M2.5
• amazon-bedrock: mistral.devstral-2-123b
• chutes: zai-org/GLM-5-Turbo
• cloudferro-sherlock: MiniMaxAI/MiniMax-M2.5
• nano-gpt: TEE/deepseek-r1-0528, TEE/deepseek-v3.1, TEE/deepseek-v3.2, TEE/gemma-3-27b-it, TEE/glm-4.6, TEE/glm-4.7, TEE/glm-4.7-flash, TEE/glm-5, TEE/gpt-oss-120b, TEE/gpt-oss-20b, TEE/kimi-k2-thinking, TEE/kimi-k2.5, TEE/kimi-k2.5-thinking, TEE/llama3-3-70b, TEE/minimax-m2.1, TEE/qwen2.5-vl-72b-instruct, TEE/qwen3-30b-a3b-instruct-2507, TEE/qwen3-coder, TEE/qwen3.5-397b-a17b, chroma, hidream, qwen-image, qwen/qwen3.5-397b-a17b, z-image-turbo, zai-org/glm-5, zai-org/glm-5:thinking
• requesty: openai/gpt-5-chat, openai/gpt-5-codex, openai/gpt-5-image, openai/gpt-5-pro, openai/gpt-5.1, openai/gpt-5.1-chat, openai/gpt-5.1-codex, openai/gpt-5.1-codex-max, openai/gpt-5.1-codex-mini, openai/gpt-5.2, openai/gpt-5.2-chat, openai/gpt-5.2-codex, openai/gpt-5.2-pro, openai/gpt-5.3-codex, openai/gpt-5.4, openai/gpt-5.4-pro
• vercel: inception/mercury-2, openai/gpt-5.3-chat, openai/gpt-5.4, openai/gpt-5.4-pro, voyage/voyage-4, voyage/voyage-4-large, voyage/voyage-4-lite

Removed Models

The following models have been removed, grouped by provider:

• abacus: gemini-3-pro-preview
• cloudferro-sherlock: MiniMaxAI/MiniMax-M2.5
• nano-gpt: TEE 2/deepseek-r1-0528, TEE 2/deepseek-v3.1, TEE 2/deepseek-v3.2, TEE 2/gemma-3-27b-it, TEE 2/glm-4.6, TEE 2/glm-4.7, TEE 2/glm-4.7-flash, TEE 2/glm-5, TEE 2/gpt-oss-120b, TEE 2/gpt-oss-20b, TEE 2/kimi-k2-thinking, TEE 2/kimi-k2.5, TEE 2/kimi-k2.5-thinking, TEE 2/llama3-3-70b, TEE 2/minimax-m2.1, TEE 2/qwen2.5-vl-72b-instruct, TEE 2/qwen3-30b-a3b-instruct-2507, TEE 2/qwen3-coder

v4.0

1 new provider(s), 503 new model(s), 24 removed model(s).

New Providers

• clarifai

New Models

The following models have been added, grouped by provider:

• firmware: gpt-5-3-codex
• nano-gpt: Alibaba-NLP 2/Tongyi-DeepResearch-30B-A3B, Baichuan-M2, Baichuan4-Air, Baichuan4-Turbo, CrucibleLab 2/L3.3-70B-Loki-V2.0, Doctor-Shotgun 2/MS3.2-24B-Magnum-Diamond, EVA-UNIT-01 2/EVA-LLaMA-3.33-70B-v0.0, EVA-UNIT-01 2/EVA-LLaMA-3.33-70B-v0.1, EVA-UNIT-01 2/EVA-Qwen2.5-32B-v0.2, EVA-UNIT-01 2/EVA-Qwen2.5-72B-v0.2, Envoid 2/Llama-3.05-NT-Storybreaker-Ministral-70B, Envoid 2/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B, GLM-4.5-Air-Derestricted, GLM-4.5-Air-Derestricted-Iceblink, GLM-4.5-Air-Derestricted-Iceblink-ReExtract, GLM-4.5-Air-Derestricted-Iceblink-v2, GLM-4.5-Air-Derestricted-Iceblink-v2-ReExtract, GLM-4.5-Air-Derestricted-Steam, GLM-4.5-Air-Derestricted-Steam-ReExtract, GLM-4.6-Derestricted-v5, GalrionSoftworks 2/MN-LooseCannon-12B-v1, Gemma-3-27B-ArliAI-RPMax-v3, Gemma-3-27B-Big-Tiger-v3, Gemma-3-27B-CardProjector-v4, Gemma-3-27B-Glitter, Gemma-3-27B-Nidum-Uncensored, Gemma-3-27B-it, Gemma-3-27B-it-Abliterated, Gryphe 2/MythoMax-L2-13b, Infermatic 2/MN-12B-Inferor-v0.0, KAT-Coder-Air-V1, KAT-Coder-Exp-72B-1010, KAT-Coder-Pro-V1, LLM360 2/K2-Think, LatitudeGames 2/Wayfarer-Large-70B-Llama-3.3, Llama-3.3+(3.1v3.3)-70B-Hanami-x1, Llama-3.3+(3.1v3.3)-70B-New-Dawn-v1.1, Llama-3.3+(3v3.3)-70B-TenyxChat-DaybreakStorywriter, Llama-3.3-70B-Anthrobomination, Llama-3.3-70B-Argunaut-1-SFT, Llama-3.3-70B-ArliAI-RPMax-v1.4, Llama-3.3-70B-ArliAI-RPMax-v2, Llama-3.3-70B-ArliAI-RPMax-v3, Llama-3.3-70B-Aurora-Borealis, Llama-3.3-70B-Bigger-Body, Llama-3.3-70B-Cirrus-x1, Llama-3.3-70B-Cu-Mai-R1, Llama-3.3-70B-Damascus-R1, Llama-3.3-70B-Dark-Ages-v0.1, Llama-3.3-70B-Electra-R1, Llama-3.3-70B-Electranova-v1.0, Llama-3.3-70B-Fallen-R1-v1, Llama-3.3-70B-Fallen-v1, Llama-3.3-70B-Forgotten-Abomination-v5.0, Llama-3.3-70B-Forgotten-Safeword-3.6, Llama-3.3-70B-GeneticLemonade-Opus, Llama-3.3-70B-GeneticLemonade-Unleashed-v3, Llama-3.3-70B-Ignition-v0.1, Llama-3.3-70B-Incandescent-Malevolence, Llama-3.3-70B-Legion-V2.1, Llama-3.3-70B-MS-Nevoria, Llama-3.3-70B-Magnum-v4-SE, Llama-3.3-70B-Magnum-v4-SE-Cirrus-x1-SLERP, Llama-3.3-70B-Mhnnn-x1, Llama-3.3-70B-MiraiFanfare, Llama-3.3-70B-Mokume-Gane-R1, Llama-3.3-70B-Nova, Llama-3.3-70B-Predatorial-Extasy, Llama-3.3-70B-Progenitor-V3.3, Llama-3.3-70B-RAWMAW, Llama-3.3-70B-Sapphira-0.1, Llama-3.3-70B-Sapphira-0.2, Llama-3.3-70B-Shakudo, Llama-3.3-70B-StrawberryLemonade-v1.0, Llama-3.3-70B-Strawberrylemonade-v1.2, Llama-3.3-70B-The-Omega-Directive-Unslop-v2.0, Llama-3.3-70B-The-Omega-Directive-Unslop-v2.1, Llama-3.3-70B-Vulpecula-R1, Magistral-Small-2506, MarinaraSpaghetti 2/NemoMix-Unleashed-12B, Meta-Llama-3-1-8B-Instruct-FP8, MiniMax-M1, MiniMax-M2, MiniMaxAI 2/MiniMax-M1-80k, Mistral-Nemo-12B-Instruct-2407, NeverSleep 2/Llama-3-Lumimaid-70B-v0.1, NeverSleep 2/Lumimaid-v0.2-70B, NousResearch 2/DeepHermes-3-Mistral-24B-Preview, NousResearch 2/Hermes-4-70B:thinking, NousResearch 2/hermes-3-llama-3.1-70b, NousResearch 2/hermes-4-405b, NousResearch 2/hermes-4-405b:thinking, NousResearch 2/hermes-4-70b, QwQ-32B-ArliAI-RpR-v1, Qwen2.5-32B-EVA-v0.2, ReadyArt 2/MS3.2-The-Omega-Directive-24B-Unslop-v2.0, ReadyArt 2/The-Omega-Abomination-L-70B-v1.0, Salesforce 2/Llama-xLAM-2-70b-fc-r, Sao10K 2/L3-8B-Stheno-v3.2, Sao10K 2/L3.1-70B-Euryale-v2.2, Sao10K 2/L3.1-70B-Hanami-x1, Sao10K 2/L3.3-70B-Euryale-v2.3, Steelskull 2/L3.3-Cu-Mai-R1-70b, Steelskull 2/L3.3-Electra-R1-70b, Steelskull 2/L3.3-MS-Evalebis-70b, Steelskull 2/L3.3-MS-Evayale-70B, Steelskull 2/L3.3-MS-Nevoria-70b, Steelskull 2/L3.3-Nevoria-R1-70b, TEE 2/deepseek-r1-0528, TEE 2/deepseek-v3.1, TEE 2/deepseek-v3.2, TEE 2/gemma-3-27b-it, TEE 2/glm-4.6, TEE 2/glm-4.7, TEE 2/glm-4.7-flash, TEE 2/glm-5, TEE 2/gpt-oss-120b, TEE 2/gpt-oss-20b, TEE 2/kimi-k2-thinking, TEE 2/kimi-k2.5, TEE 2/kimi-k2.5-thinking, TEE 2/llama3-3-70b, TEE 2/minimax-m2.1, TEE 2/qwen2.5-vl-72b-instruct, TEE 2/qwen3-30b-a3b-instruct-2507, TEE 2/qwen3-coder, THUDM 2/GLM-4-32B-0414, THUDM 2/GLM-4-9B-0414, THUDM 2/GLM-Z1-32B-0414, THUDM 2/GLM-Z1-9B-0414, THUDM 2/GLM-Z1-Rumination-32B-0414, TheDrummer 2/Anubis-70B-v1, TheDrummer 2/Anubis-70B-v1.1, TheDrummer 2/Cydonia-24B-v2, TheDrummer 2/Cydonia-24B-v4, TheDrummer 2/Cydonia-24B-v4.1, TheDrummer 2/Cydonia-24B-v4.3, TheDrummer 2/Magidonia-24B-v4.3, TheDrummer 2/Rocinante-12B-v1.1, TheDrummer 2/UnslopNemo-12B-v4.1, TheDrummer 2/skyfall-36b-v2, Tongyi-Zhiwen 2/QwenLong-L1-32B, VongolaChouko 2/Starcannon-Unleashed-12B-v1.0, abacusai/Dracarys-72B-Instruct, aion-labs/aion-1.0, aion-labs/aion-1.0-mini, aion-labs/aion-rp-llama-3.1-8b, allenai/molmo-2-8b, allenai/olmo-3-32b-think, allenai/olmo-3.1-32b-instruct, allenai/olmo-3.1-32b-think, amazon/nova-2-lite-v1, amazon/nova-lite-v1, amazon/nova-micro-v1, amazon/nova-pro-v1, anthracite-org/magnum-v2-72b, anthracite-org/magnum-v4-72b, anthropic/claude-opus-4.6, anthropic/claude-opus-4.6:thinking, anthropic/claude-opus-4.6:thinking:low, anthropic/claude-opus-4.6:thinking:max, anthropic/claude-opus-4.6:thinking:medium, anthropic/claude-sonnet-4.6, anthropic/claude-sonnet-4.6:thinking, arcee-ai/trinity-large, arcee-ai/trinity-mini, asi1-mini, auto-model, auto-model-basic, auto-model-premium, auto-model-standard, azure-gpt-4-turbo, azure-gpt-4o, azure-gpt-4o-mini, azure-o1, azure-o3-mini, baidu/ernie-4.5-300b-a47b, baidu/ernie-4.5-vl-28b-a3b, baseten/Kimi-K2-Instruct-FP4, brave, brave-pro, brave-research, chutesai/Mistral-Small-3.2-24B-Instruct-2506, claude-3-5-haiku-20241022, claude-3-5-sonnet-20240620, claude-3-5-sonnet-20241022, claude-3-7-sonnet-20250219, claude-3-7-sonnet-reasoner, claude-3-7-sonnet-thinking, claude-3-7-sonnet-thinking:1024, claude-3-7-sonnet-thinking:128000, claude-3-7-sonnet-thinking:32768, claude-3-7-sonnet-thinking:8192, claude-haiku-4-5-20251001, claude-opus-4-1-20250805, claude-opus-4-1-thinking, claude-opus-4-1-thinking:1024, claude-opus-4-1-thinking:32000, claude-opus-4-1-thinking:32768, claude-opus-4-1-thinking:8192, claude-opus-4-20250514, claude-opus-4-5-20251101, claude-opus-4-5-20251101:thinking, claude-opus-4-thinking, claude-opus-4-thinking:1024, claude-opus-4-thinking:32000, claude-opus-4-thinking:32768, claude-opus-4-thinking:8192, claude-sonnet-4-20250514, claude-sonnet-4-5-20250929, claude-sonnet-4-5-20250929-thinking, claude-sonnet-4-thinking, claude-sonnet-4-thinking:1024, claude-sonnet-4-thinking:32768, claude-sonnet-4-thinking:64000, claude-sonnet-4-thinking:8192, cognitivecomputations/dolphin-2.9.2-qwen2-72b, cohere/command-r, cohere/command-r-plus-08-2024, command-a-reasoning-08-2025, deepclaude, deepcogito/cogito-v1-preview-qwen-32B, deepcogito/cogito-v2.1-671b, deepseek-ai/DeepSeek-R1-0528, deepseek-ai/DeepSeek-V3.1, deepseek-ai/DeepSeek-V3.1-Terminus, deepseek-ai/DeepSeek-V3.1-Terminus:thinking, deepseek-ai/DeepSeek-V3.1:thinking, deepseek-ai/deepseek-v3.2-exp, deepseek-ai/deepseek-v3.2-exp-thinking, deepseek-chat, deepseek-chat-cheaper, deepseek-math-v2, deepseek-r1, deepseek-r1-sambanova, deepseek-reasoner, deepseek-reasoner-cheaper, deepseek-v3-0324, deepseek/deepseek-prover-v2-671b, deepseek/deepseek-v3.2, deepseek/deepseek-v3.2-speciale, dmind/dmind-1, dmind/dmind-1-mini, doubao-1-5-thinking-pro-250415, doubao-1-5-thinking-pro-vision-250415, doubao-1-5-thinking-vision-pro-250428, doubao-1.5-pro-256k, doubao-1.5-pro-32k, doubao-1.5-vision-pro-32k, doubao-seed-1-6-250615, doubao-seed-1-6-flash-250615, doubao-seed-1-6-thinking-250615, doubao-seed-1-8-251215, doubao-seed-2-0-code-preview-260215, doubao-seed-2-0-lite-260215, doubao-seed-2-0-mini-260215, doubao-seed-2-0-pro-260215, doubao-seed-code-preview-latest, ernie-4.5-8k-preview, ernie-4.5-turbo-128k, ernie-4.5-turbo-vl-32k, ernie-5.0-thinking-latest, ernie-5.0-thinking-preview, ernie-x1-32k, ernie-x1-32k-preview, ernie-x1-turbo-32k, ernie-x1.1-preview, essentialai/rnj-1-instruct, exa-answer, exa-research, exa-research-pro, failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5, fastgpt, featherless-ai/Qwerky-72B, gemini-2.0-flash-001, gemini-2.0-flash-exp-image-generation, gemini-2.0-flash-lite, gemini-2.0-flash-thinking-exp-01-21, gemini-2.0-flash-thinking-exp-1219, gemini-2.0-pro-exp-02-05, gemini-2.0-pro-reasoner, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.5-flash-lite-preview-06-17, gemini-2.5-flash-lite-preview-09-2025, gemini-2.5-flash-lite-preview-09-2025-thinking, gemini-2.5-flash-nothinking, gemini-2.5-flash-preview-04-17, gemini-2.5-flash-preview-04-17:thinking, gemini-2.5-flash-preview-05-20, gemini-2.5-flash-preview-05-20:thinking, gemini-2.5-flash-preview-09-2025, gemini-2.5-flash-preview-09-2025-thinking, gemini-2.5-pro, gemini-2.5-pro-exp-03-25, gemini-2.5-pro-preview-03-25, gemini-2.5-pro-preview-05-06, gemini-2.5-pro-preview-06-05, gemini-3-pro-image-preview, gemini-3-pro-preview, gemini-3-pro-preview-thinking, gemini-exp-1206, glm-4, glm-4-air, glm-4-air-0111, glm-4-airx, glm-4-flash, glm-4-long, glm-4-plus, glm-4-plus-0111, glm-4.1v-thinking-flash, glm-4.1v-thinking-flashx, glm-z1-air, glm-z1-airx, glm-zero-preview, google/gemini-3-flash-preview, google/gemini-3-flash-preview-thinking, google/gemini-flash-1.5, grok-3-beta, grok-3-fast-beta, grok-3-mini-beta, grok-3-mini-fast-beta, `huihui-ai/DeepSeek-R1-Distill-Lla...

v3.0

47 new model(s), 33 removed model(s).

New Models

The following models have been added, grouped by provider:

• azure: gpt-5.3-chat, gpt-5.4, gpt-5.4-pro
• azure-cognitive-services: gpt-5.4, gpt-5.4-pro
• nebius: MiniMaxAI/MiniMax-M2.1, NousResearch/Hermes-4-405B, NousResearch/Hermes-4-70B, PrimeIntellect/INTELLECT-3, Qwen/Qwen2.5-Coder-7B-fast, Qwen/Qwen2.5-VL-72B-Instruct, Qwen/Qwen3-235B-A22B-Instruct-2507, Qwen/Qwen3-235B-A22B-Thinking-2507, Qwen/Qwen3-30B-A3B-Instruct-2507, Qwen/Qwen3-30B-A3B-Thinking-2507, Qwen/Qwen3-32B, Qwen/Qwen3-32B-fast, Qwen/Qwen3-Coder-30B-A3B-Instruct, Qwen/Qwen3-Coder-480B-A35B-Instruct, Qwen/Qwen3-Embedding-8B, Qwen/Qwen3-Next-80B-A3B-Thinking, deepseek-ai/DeepSeek-R1-0528, deepseek-ai/DeepSeek-R1-0528-fast, deepseek-ai/DeepSeek-V3-0324, deepseek-ai/DeepSeek-V3-0324-fast, deepseek-ai/DeepSeek-V3.2, meta-llama/Llama-3.3-70B-Instruct-fast, meta-llama/Llama-Guard-3-8B, meta-llama/Meta-Llama-3.1-8B-Instruct, meta-llama/Meta-Llama-3.1-8B-Instruct-fast, moonshotai/Kimi-K2-Instruct, moonshotai/Kimi-K2-Thinking, nvidia/Llama-3_1-Nemotron-Ultra-253B-v1, nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B, nvidia/Nemotron-Nano-V2-12b, zai-org/GLM-4.5, zai-org/GLM-4.5-Air, zai-org/GLM-4.7-FP8
• siliconflow-cn: Qwen/Qwen3.5-122B-A10B, Qwen/Qwen3.5-27B, Qwen/Qwen3.5-35B-A3B, Qwen/Qwen3.5-397B-A17B, Qwen/Qwen3.5-4B, Qwen/Qwen3.5-9B
• xai: grok-4.20-experimental-beta-0304-non-reasoning, grok-4.20-experimental-beta-0304-reasoning, grok-4.20-multi-agent-experimental-beta-0304

Removed Models

The following models have been removed, grouped by provider:

• nebius: MiniMaxAI/minimax-m2.1, NousResearch/hermes-4-405b, NousResearch/hermes-4-70b, PrimeIntellect/intellect-3, deepseek-ai/deepseek-r1-0528, deepseek-ai/deepseek-r1-0528-fast, deepseek-ai/deepseek-v3-0324, deepseek-ai/deepseek-v3-0324-fast, deepseek-ai/deepseek-v3.2, meta-llama/llama-3.3-70b-instruct-fast, meta-llama/llama-guard-3-8b, meta-llama/meta-llama-3.1-8b-instruct, meta-llama/meta-llama-3.1-8b-instruct-fast, moonshotai/kimi-k2-instruct, moonshotai/kimi-k2-thinking, nvidia/llama-3_1-nemotron-ultra-253b-v1, nvidia/nemotron-nano-v2-12b, nvidia/nvidia-nemotron-3-nano-30b-a3b, qwen/qwen2.5-coder-7b-fast, qwen/qwen2.5-vl-72b-instruct, qwen/qwen3-235b-a22b-instruct-2507, qwen/qwen3-235b-a22b-thinking-2507, qwen/qwen3-30b-a3b-instruct-2507, qwen/qwen3-30b-a3b-thinking-2507, qwen/qwen3-32b, qwen/qwen3-32b-fast, qwen/qwen3-coder-30b-a3b-instruct, qwen/qwen3-coder-480b-a35b-instruct, qwen/qwen3-embedding-8b, qwen/qwen3-next-80b-a3b-thinking, zai-org/glm-4.5, zai-org/glm-4.5-air, zai-org/glm-4.7-fp8

v2.0

3 new provider(s), 87 new model(s), 11 removed model(s).

New Providers

• alibaba-coding-plan
• alibaba-coding-plan-cn
• drun

New Models

The following models have been added, grouped by provider:

• abacus: claude-opus-4-6, claude-sonnet-4-6, gemini-3.1-flash-lite-preview, gemini-3.1-pro-preview, gpt-5-codex, gpt-5.1-codex, gpt-5.1-codex-max, gpt-5.2-codex, gpt-5.3-chat-latest, gpt-5.3-codex, gpt-5.3-codex-xhigh, kimi-k2.5, zai-org/glm-5
• aihubmix: coding-glm-5-free, glm-5, minimax-m2.5, qwen3-coder-next, qwen3.5-plus
• alibaba-cn: MiniMax/MiniMax-M2.5, glm-5, kimi/kimi-k2.5, minimax-m2.5, qwen3.5-flash, siliconflow/deepseek-r1-0528, siliconflow/deepseek-v3-0324, siliconflow/deepseek-v3.1-terminus, siliconflow/deepseek-v3.2
• cloudferro-sherlock: MiniMaxAI/MiniMax-M2.5
• cloudflare-workers-ai: @cf/zai-org/glm-4.7-flash
• cortecs: glm-4.5, glm-4.5-air, glm-4.7, glm-4.7-flash, kimi-k2.5, minimax-m2.1
• deepinfra: MiniMaxAI/MiniMax-M2.5, moonshotai/Kimi-K2-Instruct-0905, zai-org/GLM-4.6, zai-org/GLM-4.6V, zai-org/GLM-5
• firmware: deepseek-v3-2, gemini-3-1-pro-preview, glm-5, gpt-5-4, gpt-5.3-codex, grok-4-1-fast-non-reasoning, grok-4-1-fast-reasoning, grok-code-fast-1, kimi-k2.5, minimax-m2-5
• google: gemini-3.1-flash-image-preview, gemini-3.1-flash-lite-preview
• inception: mercury-2, mercury-edit
• kilo: inception/mercury-2, inception/mercury-edit
• nvidia: minimaxai/minimax-m2.5
• openrouter: inception/mercury, inception/mercury-2, inception/mercury-coder, openrouter/free
• poe: google/gemini-3.1-flash-lite, google/gemini-3.1-pro, openai/gpt-5.3-codex
• qiniu-ai: doubao-seed-2.0-code, doubao-seed-2.0-lite, doubao-seed-2.0-mini, doubao-seed-2.0-pro, meituan/longcat-flash-lite, minimax/minimax-m2.5, minimax/minimax-m2.5-highspeed, moonshotai/kimi-k2.5, qwen3-30b-a3b-instruct-2507, qwen3-30b-a3b-thinking-2507, qwen3-vl-30b-a3b-thinking, qwen3.5-397b-a17b, stepfun/step-3.5-flash, xiaomi/mimo-v2-flash, z-ai/glm-5
• sap-ai-core: sonar-deep-research
• venice: openai-gpt-4o-2024-11-20, openai-gpt-4o-mini-2024-07-18, openai-gpt-54, qwen3-5-35b-a3b
• vercel: google/gemini-3.1-flash-image-preview
• zenmux: google/gemini-3.1-pro-preview, openai/gpt-5.2-pro

Removed Models

The following models have been removed, grouped by provider:

• abacus: gemini-2.0-flash-001, gemini-2.0-pro-exp-02-05, meta-llama/Meta-Llama-3.1-70B-Instruct
• cortecs: glm-4p5, glm-4p5-air, glm-4p7, minimax-m2p1
• firmware: gpt-5, gpt-5.2
• nvidia: minimaxai/minimax-m2
• ollama-cloud: gemini-3-pro-preview

v1.4

Model metadata updated (no providers or models added/removed).

v1.3

11 new model(s).

New Models

The following models have been added, grouped by provider:

• cloudflare-ai-gateway: openai/gpt-5.4
• github-copilot: gpt-5.3-codex, gpt-5.4
• openai: gpt-5.4, gpt-5.4-pro
• opencode: gpt-5.3-codex-spark, gpt-5.4, gpt-5.4-pro
• openrouter: openai/gpt-5.3-codex, openai/gpt-5.4, openai/gpt-5.4-pro

v1.2

1 new provider(s).

New Providers

• perplexity-agent

v1.1

Model metadata updated (no providers or models added/removed).

v1.0

3 new provider(s), 55 new model(s), 2 removed model(s).

New Providers

• evroc
• meganova
• opencode-go

New Models

The following models have been added, grouped by provider:

• aihubmix: claude-opus-4-6, claude-opus-4-6-think, claude-sonnet-4-6, claude-sonnet-4-6-think, gemini-3-pro-preview-search, gpt-5.2-codex
• azure: gpt-5.3-codex
• azure-cognitive-services: gpt-5.2, gpt-5.3-codex
• baseten: MiniMaxAI/MiniMax-M2.5, zai-org/GLM-5
• cloudflare-ai-gateway: openai/gpt-5.2-codex, openai/gpt-5.3-codex
• friendli: MiniMaxAI/MiniMax-M2.5
• github-copilot: gemini-3.1-pro-preview
• gitlab: duo-chat-sonnet-4-6
• google: gemini-3.1-pro-preview, gemini-3.1-pro-preview-customtools
• google-vertex: gemini-3.1-pro-preview, gemini-3.1-pro-preview-customtools
• opencode: gemini-3.1-pro, gpt-5.3-codex
• openrouter: anthropic/claude-sonnet-4.6, google/gemini-3.1-pro-preview, google/gemini-3.1-pro-preview-customtools
• sap-ai-core: anthropic--claude-4.6-opus, anthropic--claude-4.6-sonnet, gemini-2.5-flash-lite, gpt-4.1, gpt-4.1-mini, sonar, sonar-pro
• siliconflow-cn: PaddlePaddle/PaddleOCR-VL, PaddlePaddle/PaddleOCR-VL-1.5, Pro/MiniMaxAI/MiniMax-M2.5, deepseek-ai/DeepSeek-OCR
• togetherai: Qwen/Qwen3.5-397B-A17B
• venice: gemini-3-1-pro-preview, nvidia-nemotron-3-nano-30b-a3b, openai-gpt-53-codex, qwen3-coder-480b-a35b-instruct-turbo
• vercel: alibaba/qwen3-coder-next, alibaba/qwen3.5-flash, alibaba/qwen3.5-plus, anthropic/claude-sonnet-4.6, google/gemini-3.1-pro-preview, minimax/minimax-m2.5, openai/gpt-5.3-codex, xai/grok-imagine-image, xai/grok-imagine-image-pro, zai/glm-5
• zenmux: anthropic/claude-sonnet-4.6, volcengine/doubao-seed-2.0-lite, volcengine/doubao-seed-2.0-mini, volcengine/doubao-seed-2.0-pro

Removed Models

The following models have been removed, grouped by provider:

• friendli: LGAI-EXAONE/EXAONE-4.0.1-32B, LGAI-EXAONE/K-EXAONE-236B-A23B