v105.0

9 new model(s), 5 removed model(s).

New Models

The following models have been added, grouped by provider:

• ambient: deepseek/deepseek-v4-flash, xiaomi/mimo-v2.5
• cloudflare-ai-gateway: moonshotai/kimi-k3
• empiriolabs: kimi-k3
• openrouter: thinkingmachines/inkling
• togetherai: thinkingmachines/Inkling
• venice: inkling, kimi-k3
• zenmux: moonshotai/kimi-k3

Removed Models

The following models have been removed, grouped by provider:

• kimi-for-coding: k2p5, k2p6, kimi-k2-thinking
• openrouter: meta-llama/llama-3.2-11b-vision-instruct, nvidia/llama-3.3-nemotron-super-49b-v1.5

v104.1

1 new provider(s), 26 new model(s).

New Providers

• thinkingmachines

New Models

The following models have been added, grouped by provider:

• aihubmix: claude-fable-5, claude-sonnet-5, gemini-3.5-flash, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, grok-4.5, grok-build-0.1, hy3-preview, kimi-k2.7-code, kimi-k2.7-code-highspeed
• baseten: thinkingmachines/inkling
• evroc: zai-org/GLM-5.2
• kimi-for-coding: k3
• llmgateway: kimi-k3
• moonshotai: kimi-k3
• moonshotai-cn: kimi-k3
• opencode-go: grok-4.5, kimi-k3
• openrouter: meta/muse-spark-1.1, moonshotai/kimi-k3
• vercel: anthropic/claude-opus-4.7-fast, anthropic/claude-opus-4.8-fast, moonshotai/kimi-k3, openai/gpt-realtime-whisper, thinkingmachines/inkling

v104.0

3 new model(s), 36 removed model(s).

New Models

The following models have been added, grouped by provider:

• kimi-for-coding: kimi-for-coding-highspeed
• privatemode-ai: kimi-k2.6, voxtral-mini-3b

Removed Models

The following models have been removed, grouped by provider:

• llmgateway: deepseek-v3.1, devstral-small-2507, llama-3-8b-instruct, pixtral-large-latest, qwen3-4b-fp8, qwen3-vl-30b-a3b-thinking, qwen3-vl-8b-instruct
• ollama-cloud: cogito-2.1:671b, deepseek-v3.1:671b, deepseek-v3.2, devstral-2:123b, devstral-small-2:24b, gemini-3-flash-preview, gemma3:12b, gemma3:27b, gemma3:4b, glm-4.6, glm-4.7, glm-5, kimi-k2-thinking, kimi-k2:1t, minimax-m2, minimax-m2.1, ministral-3:14b, ministral-3:3b, ministral-3:8b, qwen3-coder-next, qwen3-coder:480b, qwen3-next:80b, qwen3-vl:235b, qwen3-vl:235b-instruct, rnj-1:8b
• openrouter: arcee-ai/coder-large
• privatemode-ai: gemma-3-27b, qwen3-coder-30b-a3b
• venice: aion-labs-aion-2-0

v103.0

19 new model(s), 13 removed model(s).

New Models

The following models have been added, grouped by provider:

• ambient: stepfun/step-3.7-flash
• crossmodel: x-ai/grok-4.3, x-ai/grok-4.5, x-ai/grok-build-0.1
• openrouter: kwaipilot/kat-coder-air-v2.5, kwaipilot/kat-coder-pro-v2.5
• sap-ai-core: amazon--nova-lite, amazon--nova-micro, amazon--nova-pro, amazon--titan-embed-text, cohere--command-a-reasoning, gpt-4.1-nano, gpt-5.2, mistralai--mistral-medium-instruct, mistralai--mistral-small, nvidia--llama-3.2-nv-embedqa-1b, sap-abap-1, text-embedding-3-large, text-embedding-3-small

Removed Models

The following models have been removed, grouped by provider:

• openrouter: liquid/lfm-2.5-1.2b-instruct:free, liquid/lfm-2.5-1.2b-thinking:free, openai/gpt-oss-120b:free, sao10k/l3.1-70b-hanami-x1
• vercel: anthropic/claude-3.5-haiku, arcee-ai/trinity-large-preview, meituan/longcat-flash-chat, meituan/longcat-flash-thinking-2601, mistral/devstral-small, mistral/pixtral-large, openai/gpt-3.5-turbo-instruct, xiaomi/mimo-v2-flash, xiaomi/mimo-v2-pro

v102.0

28 new model(s), 4 removed model(s).

New Models

The following models have been added, grouped by provider:

• amazon-bedrock: openai.gpt-5.6-luna, openai.gpt-5.6-sol, openai.gpt-5.6-terra
• ambient: ambient/large, z-ai/glm-5.2
• azure: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-chat-latest
• azure-cognitive-services: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, gpt-chat-latest
• cloudflare-ai-gateway: openai/gpt-5.6-luna, openai/gpt-5.6-sol, openai/gpt-5.6-terra, workers-ai/@cf/zai-org/glm-5.2
• databricks: databricks-gpt-5-6-luna, databricks-gpt-5-6-sol, databricks-gpt-5-6-terra
• empiriolabs: mistral-medium-3, mistral-small-4
• gitlab: duo-chat-gpt-5-6-luna, duo-chat-gpt-5-6-sol, duo-chat-gpt-5-6-terra
• snowflake-cortex: openai-gpt-5.6-luna, openai-gpt-5.6-sol, openai-gpt-5.6-terra

Removed Models

The following models have been removed, grouped by provider:

• llmgateway: qwen-turbo, qwen-vl-max, qwen-vl-plus, qwq-plus

v101.0

7 new provider(s), 20 new model(s), 1 removed model(s).

New Providers

• ai-router
• blueclaw
• daoxe
• ebcloud
• lynkr
• stepfun-ai-step-plan
• stepfun-step-plan

New Models

The following models have been added, grouped by provider:

• crossmodel: openai/gpt-5.6-luna, openai/gpt-5.6-sol, openai/gpt-5.6-terra
• google-vertex: gemini-2.5-flash-image, gemini-3-pro-image, gemini-3.1-flash-image
• hpc-ai: anthropic/claude-opus-4.7, deepseek/deepseek-v4-flash, deepseek/deepseek-v4-pro, moonshotai/kimi-k2.7-code, openai/gpt-5.5, zai-org/glm-5.2
• vercel: bytedance/seedream-5.0-pro
• vivgrid: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra
• zenmux: openai/gpt-5.6-luna, openai/gpt-5.6-sol, openai/gpt-5.6-terra, x-ai/grok-4.5

Removed Models

The following models have been removed, grouped by provider:

• wafer.ai: Qwen3.5-397B-A17B

v100.0

1 new provider(s), 3 new model(s), 7 removed model(s).

New Providers

• inferx

New Models

The following models have been added, grouped by provider:

• ambient: zai-org/GLM-5.2-FP8
• wafer.ai: MiniMax-M3, glm5.2-fast

Removed Models

The following models have been removed, grouped by provider:

• llmgateway: mimo-v2-omni, mimo-v2-pro
• openrouter: meta-llama/llama-3-8b-instruct
• wafer.ai: Qwen3.6-35B-A3B, deepseek-v4-flash, deepseek-v4-pro, qwen3.7-max

v99.0

4 new provider(s), 51 new model(s), 6 removed model(s).

New Providers

• empiriolabs
• model-oracle-ai
• pioneer
• unorouter

New Models

The following models have been added, grouped by provider:

• abacus: MiniMaxAI/MiniMax-M2.7, MiniMaxAI/MiniMax-M3, Qwen/Qwen3-Coder-480B-A35B-Instruct, Qwen/Qwen3.6-27B, claude-fable-5, claude-opus-4-7, claude-opus-4-8, claude-sonnet-5, deepseek-ai/DeepSeek-V4-Flash, deepseek-ai/DeepSeek-V4-Pro, gemini-2.5-flash-image, gemini-3-pro-image-preview, gemini-3.1-flash-image-preview, gemini-3.1-flash-lite, gemini-3.5-flash, google/gemma-4-31b-it, gpt-4o, gpt-5.4-mini, gpt-5.4-nano, gpt-5.5, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, grok-4.3, grok-4.5, meta-llama/Meta-Llama-3.3-70B-Instruct, mimo-v2-pro, moonshotai/Kimi-K2.6, muse-spark-1.1, zai-org/GLM-4.5, zai-org/GLM-4.6, zai-org/GLM-4.7, zai-org/GLM-5, zai-org/GLM-5.1, zai-org/GLM-5.2
• databricks: databricks-glm-5-2, databricks-kimi-k2-7-code
• github-copilot: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra
• llmgateway: muse-spark-1.1
• openai: gpt-realtime-2.1
• opencode: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra
• routing-run: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra
• vercel: kwaipilot/kat-coder-air-v2.5, kwaipilot/kat-coder-pro-v2.5, openai/gpt-realtime-2.1

Removed Models

The following models have been removed, grouped by provider:

• abacus: Qwen/qwen3-coder-480b-a35b-instruct, zai-org/glm-4.5, zai-org/glm-4.6, zai-org/glm-4.7, zai-org/glm-5
• openrouter: arcee-ai/trinity-mini

v98.0

2 new provider(s), 40 new model(s), 30 removed model(s).

New Providers

• crossmodel
• meta

New Models

The following models have been added, grouped by provider:

• llmgateway: gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra, qwen3.6-flash
• openai: gpt-5.6, gpt-5.6-luna, gpt-5.6-sol, gpt-5.6-terra
• openrouter: cognitivecomputations/dolphin-mistral-24b-venice-edition, openai/gpt-5.6-luna, openai/gpt-5.6-luna-pro, openai/gpt-5.6-sol, openai/gpt-5.6-sol-pro, openai/gpt-5.6-terra, openai/gpt-5.6-terra-pro
• poolside: poolside/laguna-xs-2.1
• routing-run: claude-opus-4-8, claude-sonnet-4-6, deepseek-v4-flash, deepseek-v4-pro, glm-5.2, glm-5.2-nitro, kimi-k2.6, kimi-k2.6-nitro, kimi-k2.7-code, kimi-k2.7-code-nitro, nemotron-3-ultra, qwen3.5-9b
• sap-ai-core: gemini-3.1-flash-lite, gemini-3.5-flash
• venice: openai-gpt-56-luna, openai-gpt-56-luna-pro, openai-gpt-56-sol, openai-gpt-56-sol-pro, openai-gpt-56-terra, openai-gpt-56-terra-pro
• vercel: meta/muse-spark-1.1, openai/gpt-5.6-luna, openai/gpt-5.6-sol, openai/gpt-5.6-terra

Removed Models

The following models have been removed, grouped by provider:

• openrouter: google/gemini-2.5-flash-lite-preview-09-2025, liquid/lfm-2-24b-a2b, poolside/laguna-xs.2, poolside/laguna-xs.2:free
• routing-run: route/deepseek-v3.2, route/deepseek-v4-flash, route/deepseek-v4-flash-6bit, route/deepseek-v4-pro, route/deepseek-v4-pro-6bit, route/gemma-4-31b-it, route/glm-5.1, route/glm-5.1-6bit, route/kimi-k2.5, route/kimi-k2.6, route/kimi-k2.6-6bit, route/mimo-v2.5, route/mimo-v2.5-pro, route/mimo-v2.5-pro-6bit, route/minimax-m2.5, route/minimax-m2.5-highspeed, route/minimax-m2.7, route/minimax-m2.7-highspeed, route/mistral-large-3, route/mistral-medium-2505, route/mistral-small-2503, route/qwen3.6-27b, route/qwen3.6-27b-202k, route/step-3.5-flash, route/step-3.5-flash-2603, route/stepfun-3.5-flash

v97.0

1 new provider(s), 37 new model(s), 6 removed model(s).

New Providers

• zenifra

New Models

The following models have been added, grouped by provider:

• google: gemini-omni-flash-preview
• llmgateway: grok-4-5
• neon: claude-opus-4-8, gemini-3-5-flash, gemma-3-12b, gpt-5-1-codex-max, gpt-5-1-codex-mini, gpt-5-2-codex, gpt-5-3-codex, llama-4-maverick, meta-llama-3-1-8b-instruct, meta-llama-3-3-70b-instruct, qwen3-next-80b-a3b-instruct, qwen35-122b-a10b
• opencode: grok-4.5
• openrouter: x-ai/grok-4.5, ~x-ai/grok-latest
• sap-ai-core: anthropic--claude-4.8-opus
• venice: aion-labs-aion-3-0, aion-labs-aion-3-0-mini, grok-4-5
• vercel: google/gemini-omni-flash-preview, xai/grok-4.5
• wandb: JetBrains/Mellum2-12B-A2.5B-Instruct, Qwen/Qwen3.5-27B, Qwen/Qwen3.5-35B-A3B, Qwen/Qwen3.6-27B, Qwen/Qwen3.6-35B-A3B, deepseek-ai/DeepSeek-V4-Flash, deepseek-ai/DeepSeek-V4-Pro, google/gemma-4-31B-it, ibm-granite/granite-4.1-8b, moonshotai/Kimi-K2.6, moonshotai/Kimi-K2.7-Code, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, zai-org/GLM-5.2
• xai: grok-4.5

Removed Models

The following models have been removed, grouped by provider:

• llmgateway: gemini-2.5-flash-lite-preview-09-2025, qwen3-max-2026-01-23
• neon: gpt-5-5
• openrouter: switchpoint/router
• wandb: meta-llama/Llama-4-Scout-17B-16E-Instruct, zai-org/GLM-5-FP8