Skip to content

v2026.5.8

Choose a tag to compare

View all tags
@github-actions github-actions released this 08 May 03:14
· 152 commits to main since this release
v2026.5.8
87b379d

What changed

New models (27)

  • OpenRouter — Qwen3 Coder Plus (qwen/qwen3-coder-plus)
  • OpenRouter — Qwen: Qwen-Plus (qwen/qwen-plus)
  • Xiaomi Token Plan (China) — MiMo-V2-Flash (mimo-v2-flash)
  • Kilo Gateway — Mistral: Mistral Medium 3.5 (mistralai/mistral-medium-3-5)
  • Kilo Gateway — Microsoft: Phi 4 Mini Instruct (microsoft/phi-4-mini-instruct)
  • Kilo Gateway — OpenAI: GPT Chat Latest (openai/gpt-chat-latest)
  • Kilo Gateway — Baidu: CoBuddy (free) (baidu/cobuddy:free)
  • Xiaomi Token Plan (Singapore) — MiMo-V2-Flash (mimo-v2-flash)
  • Nebius Token Factory — Qwen3.5-397B-A17B (Qwen/Qwen3.5-397B-A17B)
  • Nebius Token Factory — Qwen3-235B-A22B-Thinking-2507-fast (Qwen/Qwen3-235B-A22B-Thinking-2507-fast)
  • Nebius Token Factory — Qwen3.5-397B-A17B-fast (Qwen/Qwen3.5-397B-A17B-fast)
  • Nebius Token Factory — Qwen3-Next-80B-A3B-Thinking-fast (Qwen/Qwen3-Next-80B-A3B-Thinking-fast)
  • Nebius Token Factory — Nemotron-3-Nano-Omni (nvidia/Nemotron-3-Nano-Omni)
  • Nebius Token Factory — DeepSeek-V3.2-fast (deepseek-ai/DeepSeek-V3.2-fast)
  • Nebius Token Factory — gpt-oss-120b-fast (openai/gpt-oss-120b-fast)
  • Nebius Token Factory — MiniMax-M2.5 (MiniMaxAI/MiniMax-M2.5)
  • Nebius Token Factory — MiniMax-M2.5-fast (MiniMaxAI/MiniMax-M2.5-fast)
  • Wafer — MiniMax-M2.7 (MiniMax-M2.7)
  • DigitalOcean — Llama 3.1 Instruct (8B) (llama3-8b-instruct)
  • DigitalOcean — Claude 3 Opus (anthropic-claude-3-opus)
  • DigitalOcean — Claude Haiku 4.5 (anthropic-claude-4.5-haiku)
  • DigitalOcean — Claude 3.5 Haiku (anthropic-claude-3.5-haiku)
  • DigitalOcean — Mistral Nemo Instruct (mistral-nemo-instruct-2407)
  • DigitalOcean — Claude 3.7 Sonnet (anthropic-claude-3.7-sonnet)
  • DigitalOcean — Claude 3.5 Sonnet (anthropic-claude-3.5-sonnet)
  • Google — Gemini 3.1 Flash Lite (gemini-3.1-flash-lite)
  • Xiaomi Token Plan (Europe) — MiMo-V2-Flash (mimo-v2-flash)

Removed models (30)

  • Kilo Gateway — AllenAI: Olmo 3.1 32B Instruct (allenai/olmo-3.1-32b-instruct)
  • Kilo Gateway — NVIDIA: Nemotron Nano 12B 2 VL (nvidia/nemotron-nano-12b-v2-vl)
  • Nebius Token Factory — FLUX.1-schnell (black-forest-labs/flux-schnell)
  • Nebius Token Factory — FLUX.1-dev (black-forest-labs/flux-dev)
  • Nebius Token Factory — Qwen3-30B-A3B-Thinking-2507 (Qwen/Qwen3-30B-A3B-Thinking-2507)
  • Nebius Token Factory — Qwen3-32B (Fast) (Qwen/Qwen3-32B-fast)
  • Nebius Token Factory — Qwen3-Coder-30B-A3B-Instruct (Qwen/Qwen3-Coder-30B-A3B-Instruct)
  • Nebius Token Factory — Qwen3 235B A22B Thinking 2507 (Qwen/Qwen3-235B-A22B-Thinking-2507)
  • Nebius Token Factory — Qwen3 Coder 480B A35B Instruct (Qwen/Qwen3-Coder-480B-A35B-Instruct)
  • Nebius Token Factory — Qwen2.5-Coder-7B (Fast) (Qwen/Qwen2.5-Coder-7B-fast)
  • Nebius Token Factory — GLM-4.5 (zai-org/GLM-4.5)
  • Nebius Token Factory — GLM-4.5-Air (zai-org/GLM-4.5-Air)
  • Nebius Token Factory — GLM-4.7 (FP8) (zai-org/GLM-4.7-FP8)
  • Nebius Token Factory — BGE-ICL (BAAI/bge-en-icl)
  • Nebius Token Factory — bge-multilingual-gemma2 (BAAI/bge-multilingual-gemma2)
  • Nebius Token Factory — Meta-Llama-3.1-8B-Instruct (Fast) (meta-llama/Meta-Llama-3.1-8B-Instruct-fast)
  • Nebius Token Factory — Llama-3.3-70B-Instruct (Fast) (meta-llama/Llama-3.3-70B-Instruct-fast)
  • Nebius Token Factory — Llama-Guard-3-8B (meta-llama/Llama-Guard-3-8B)
  • Nebius Token Factory — Nemotron-Nano-V2-12b (nvidia/Nemotron-Nano-V2-12b)
  • Nebius Token Factory — DeepSeek-V3-0324 (deepseek-ai/DeepSeek-V3-0324)
  • Nebius Token Factory — DeepSeek-V3-0324 (Fast) (deepseek-ai/DeepSeek-V3-0324-fast)
  • Nebius Token Factory — DeepSeek R1 0528 Fast (deepseek-ai/DeepSeek-R1-0528-fast)
  • Nebius Token Factory — DeepSeek-R1-0528 (deepseek-ai/DeepSeek-R1-0528)
  • Nebius Token Factory — gpt-oss-20b (openai/gpt-oss-20b)
  • Nebius Token Factory — Gemma-2-9b-it (Fast) (google/gemma-2-9b-it-fast)
  • Nebius Token Factory — Gemma-3-27b-it (Fast) (google/gemma-3-27b-it-fast)
  • Nebius Token Factory — Kimi-K2-Thinking (moonshotai/Kimi-K2-Thinking)
  • Nebius Token Factory — Kimi-K2-Instruct (moonshotai/Kimi-K2-Instruct)
  • Nebius Token Factory — MiniMax-M2.1 (MiniMaxAI/MiniMax-M2.1)
  • Nebius Token Factory — e5-mistral-7b-instruct (intfloat/e5-mistral-7b-instruct)

Price changes (2)

  • Venice AI — Grok 4.20 Multi-Agent: input $2.27 → $1.42, output $6.8 → $2.83
  • Venice AI — Grok 4.20: input $2.27 → $1.42, output $6.8 → $2.83
Assets 2
Loading