Mistral Cloud now serves DeepSeek V4.1 Flash and GLM 5.3 Flash, launches OpenAI-compatible Responses API
MistralAI · x · 2026-10-28
Mistral AI announced two fast, low-cost models on its cloud inference platform (served in EU & US):
- DeepSeek V4.1 Flash (public preview): geared for long-context coding and agentic tasks
- GLM 5.3 Flash (generally available): geared for subagents, tool calls, and coding tasks
Mistral also launched a Responses API (public preview) in OpenAI Responses format, easing migration of existing integrations. It's stateless and supports text/image/file inputs, JSON Schema structured outputs, streaming, function calling, and reasoning effort controls.
Related event: Mistral Platform Adds DeepSeek V4.1 Flash and GLM 5.3 Flash(2 posts)→
More from Infra
- 7.25M Gitee Repos Scanned, 26,400 Live Secrets Found Using Modal, TruffleHog and Kingfisher — charles_irl · 2026-10-28
- DeepSeek rerun through Fireworks reproduces results; original dip was likely a fluke — teortaxesTex · 2026-10-28
- NIST Releases Official Post-Quantum Cryptography Migration Guidance as Harvest-Now-Decrypt-Later Risk Grows — entrup · 2026-10-28
- Decision Models cut inference to ~100ms, making the retriever RAG's new latency bottleneck — CShorten30 · 2026-10-28
- Infinity: an open-source Rust agent runtime that treats concurrency as a scheduling problem — ShadajL · 2026-10-28
- vLLM PR Adds Native Nemotron-3.5-Transcribe Support: Transcription+Chat, FP8/NVFP4 — vllm_project · 2026-10-28