# \#mistral-large **URL:** https://forums.developer.nvidia.com/tag/mistral-large/994.md [Latest](https://forums.developer.nvidia.com/latest.md) · [Categories](https://forums.developer.nvidia.com/categories.md) · [Tags](https://forums.developer.nvidia.com/tags.md) --- ## [Hey New Mistral model incoming](https://forums.developer.nvidia.com/t/hey-new-mistral-model-incoming/385255)
**Author:** [@WilliamD](https://forums.developer.nvidia.com/u/WilliamD)\ **Replies:** 0\ **Last updated:** [October 7, 2026, 12:41am UTC](https://forums.developer.nvidia.com/t/hey-new-mistral-model-incoming/385255 "2026-10-07T00:41:51Z")
Hey, When Mistral announced deploying and serving GLM-5.3, even though it is an excellent model, it felt like the end… Well guess what, a new model dropped and pretend to be a direct contender to deepseek-v4.1. The weig… --- ## [Request to enable "Public API Endpoints" permission for my personal organization – 403 Authorization failed](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-permission-for-my-personal-organization-403-authorization-failed/383393)
**Author:** [@ryanraposo](https://forums.developer.nvidia.com/u/ryanraposo)\ **Replies:** 0\ **Last updated:** [September 16, 2026, 5:26am UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-permission-for-my-personal-organization-403-authorization-failed/383393 "2026-09-16T05:26:54Z")
Hi NVIDIA team, I’m getting a consistent 403 “Authorization failed” on all inference calls. What works: GET https://integrate.api.nvidia.com/v1/models → HTTP 200 (key is valid) What fails: POST https://integrate.a… --- ## [Request to enable Public API Endpoints for my account — 404 on several catalog models](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-for-my-account-404-on-several-catalog-models/382908)
**Author:** [@appts.extra](https://forums.developer.nvidia.com/u/appts.extra)\ **Replies:** 0\ **Last updated:** [September 10, 2026, 4:54pm UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-for-my-account-404-on-several-catalog-models/382908 "2026-09-10T16:54:10Z")
Hello NVIDIA team, I’m building a personal coding project using the NIM API and running into 404 errors on several models that appear correctly in my available models list, but fail when I actually try to call them: z… --- ## [Request to enable public api endpoints for my personal organization](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-for-my-personal-organization/379991)
**Author:** [@r0ck50lid](https://forums.developer.nvidia.com/u/r0ck50lid)\ **Replies:** 0\ **Last updated:** [August 13, 2026, 7:42am UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-for-my-personal-organization/379991 "2026-08-13T07:42:29Z")
Every POST /v1/chat/completions call to certain models (e.g. mistralai/mistral-large-2-instruct) returns 404 - Function ‘’: Not found for account ‘’, while the same key works fine for GET /v1/models and for most other ho… --- ## [Request to enable "Public API Endpoints" — models listed in /v1/models return 404 "Not found for account](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-models-listed-in-v1-models-return-404-not-found-for-account/379594)
**Author:** [@ugurucar777](https://forums.developer.nvidia.com/u/ugurucar777)\ **Replies:** 0\ **Last updated:** [August 8, 2026, 9:50am UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-models-listed-in-v1-models-return-404-not-found-for-account/379594 "2026-08-08T09:50:00Z")
Hello NVIDIA team, I am requesting activation of the “Public API Endpoints” permission for my account. Problem Models are listed correctly by GET https://integrate.api.nvidia.com/v1/models (100 models returned, HTTP … --- ## [Request to enable "Public API Endpoints" — models listed in /v1/models return 404 "Not found for account"](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-models-listed-in-v1-models-return-404-not-found-for-account/379205)
**Author:** [@erick23](https://forums.developer.nvidia.com/u/erick23)\ **Replies:** 0\ **Last updated:** [August 5, 2026, 4:55am UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-models-listed-in-v1-models-return-404-not-found-for-account/379205 "2026-08-05T04:55:13Z")
Hello NVIDIA team, I’m requesting the “Public API Endpoints” permission for my personal organization. Several models are returned by GET /v1/models but fail with HTTP 404 “Not found for account” when called via POST /v… --- ## [Request to enable "Public API Endpoints" permission for my account - 404 on 4 specialized models](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-permission-for-my-account-404-on-4-specialized-models/378872)
**Author:** [@abstractkevin92](https://forums.developer.nvidia.com/u/abstractkevin92)\ **Replies:** 0\ **Last updated:** [August 1, 2026, 11:47am UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-permission-for-my-account-404-on-4-specialized-models/378872 "2026-08-01T11:47:32Z")
Hi NVIDIA team, I’m unable to access several models via the NIM API on build.nvidia.com. They appear in GET /v1/models, but POST to /chat/completions returns 404 for all of them: moonshotai/kimi-k2.6 mistralai/mistra… --- ## [Request to enable "Public API Endpoints" permission — personal org (Belgium)](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-permission-personal-org-belgium/377782)
**Author:** [@bubuch242](https://forums.developer.nvidia.com/u/bubuch242)\ **Replies:** 0\ **Last updated:** [July 22, 2026, 8:13pm UTC](https://forums.developer.nvidia.com/t/request-to-enable-public-api-endpoints-permission-personal-org-belgium/377782 "2026-07-22T20:13:38Z")
Hi NVIDIA team, I'm unable to call newer commercial NIM models via https://integrate.api.nvidia.com/v1/chat/completions from my personal org account. \*\*Symptom\*\* - Models like \`meta/llama-3.1-8b-instruct\` and \`meta/ll… --- ## [Request for NVIDIA NIM API Rate Limit Increase (40 → 120 RPM)](https://forums.developer.nvidia.com/t/request-for-nvidia-nim-api-rate-limit-increase-40-120-rpm/377649)
**Author:** [@lealjosegabrielia](https://forums.developer.nvidia.com/u/lealjosegabrielia)\ **Replies:** 1\ **Last updated:** [July 21, 2026, 4:55pm UTC](https://forums.developer.nvidia.com/t/request-for-nvidia-nim-api-rate-limit-increase-40-120-rpm/377649 "2026-07-21T16:55:02Z")
Account Email: lealjosegabrielia@gmail.com API Key ID (last 4 chars): gpYR Current Limit: 40 RPM Requested Limit: 120 RPM Model(s) used: nvidia/nemotron-3-ultra-550b, nvidia/nemotron-3-super-120b, mistralai/mistral-l… --- ## [帖子标题 (Title) Request to enable Public API Endpoints for personal organization](https://forums.developer.nvidia.com/t/title-request-to-enable-public-api-endpoints-for-personal-organization/375432)
**Author:** [@winger35](https://forums.developer.nvidia.com/u/winger35)\ **Replies:** 0\ **Last updated:** [July 3, 2026, 9:28am UTC](https://forums.developer.nvidia.com/t/title-request-to-enable-public-api-endpoints-for-personal-organization/375432 "2026-07-03T09:28:42Z")
Hello NVIDIA Team, I’m a developer trying to use the NVIDIA NIM API for testing. Many models return “404 Not found for account” error when I call them via https://integrate.api.nvidia.com/v1/chat/completions. Account I… --- ## [Pushing GB10 to the Limit: Qwen3 235B MoE + Concurrent Best-of-4 + Persistent Agent Layer. Architecture check & Optimization tips?](https://forums.developer.nvidia.com/t/pushing-gb10-to-the-limit-qwen3-235b-moe-concurrent-best-of-4-persistent-agent-layer-architecture-check-optimization-tips/373118)
**Author:** [@ludbzh](https://forums.developer.nvidia.com/u/ludbzh)\ **Replies:** 0\ **Last updated:** [June 12, 2026, 7:21am UTC](https://forums.developer.nvidia.com/t/pushing-gb10-to-the-limit-qwen3-235b-moe-concurrent-best-of-4-persistent-agent-layer-architecture-check-optimization-tips/373118 "2026-06-12T07:21:15Z")
Hey everyone, I’m architecting a high-performance local AI node around a single ASUS Ascent GX10 (NVIDIA GB10 Grace Blackwell, SM121, 128GB unified LPDDR5x). The goal is to maximize reasoning depth and throughput on a s… --- ## [NVIDIA NIM API Rate Limit Increase Request (40 → 200 RPM) - Hermes Agent Workflows](https://forums.developer.nvidia.com/t/nvidia-nim-api-rate-limit-increase-request-40-200-rpm-hermes-agent-workflows/372545)
**Author:** [@akmalaka1122](https://forums.developer.nvidia.com/u/akmalaka1122)\ **Replies:** 0\ **Last updated:** [June 7, 2026, 9:49pm UTC](https://forums.developer.nvidia.com/t/nvidia-nim-api-rate-limit-increase-request-40-200-rpm-hermes-agent-workflows/372545 "2026-06-07T21:49:46Z")
Hi NVIDIA NIM Team, I’m writing to formally request a rate limit increase for my NVIDIA NIM API account. Current Limit: 40 RPM Requested Limit: 200 RPM Account Email: akmalaka1122@gmail.com API Key (last 4 character… --- ## [Subject: Rate Limit Increase Request: 40 → 200 RPM for AI Agent Workflow](https://forums.developer.nvidia.com/t/subject-rate-limit-increase-request-40-200-rpm-for-ai-agent-workflow/371349)
**Author:** [@2365360230](https://forums.developer.nvidia.com/u/2365360230)\ **Replies:** 0\ **Last updated:** [May 26, 2026, 12:44pm UTC](https://forums.developer.nvidia.com/t/subject-rate-limit-increase-request-40-200-rpm-for-ai-agent-workflow/371349 "2026-05-26T12:44:52Z")
Subject: Rate Limit Increase Request: 40 → 200 RPM for AI Agent Workflow Hello NVIDIA Team, Requesting a rate limit bump for my NIM API account. • Email: 2365360230@qq.com • API Key (last 4): pxHn • Current: 40 RPM … --- ## [NVFP4 quantization of a 123B Mistral-Large finetune on a 3-node heterogeneous cluster (2× Spark + 1× RTX 3090, distributed via Ray)](https://forums.developer.nvidia.com/t/nvfp4-quantization-of-a-123b-mistral-large-finetune-on-a-3-node-heterogeneous-cluster-2x-spark-1x-rtx-3090-distributed-via-ray/370266)
**Author:** [@kai.koehler](https://forums.developer.nvidia.com/u/kai.koehler)\ **Replies:** 0\ **Last updated:** [May 15, 2026, 2:39pm UTC](https://forums.developer.nvidia.com/t/nvfp4-quantization-of-a-123b-mistral-large-finetune-on-a-3-node-heterogeneous-cluster-2x-spark-1x-rtx-3090-distributed-via-ray/370266 "2026-05-15T14:39:56Z")
Hi all — follow-up to my Anubis-Pro-105B NVFP4 thread from earlier this week. Different model, different architecture family, and the cluster topology grew a third node. Just published an NVFP4 quantization of TheDrum… --- ## [Access](https://forums.developer.nvidia.com/t/access/367677)
**Author:** [@179072672](https://forums.developer.nvidia.com/u/179072672)\ **Replies:** 1\ **Last updated:** [April 27, 2026, 3:26pm UTC](https://forums.developer.nvidia.com/t/access/367677 "2026-04-27T15:26:34Z")
Hello NVIDIA team, I’m getting a 403 “Authorization failed” when calling models via https://integrate.api.nvidia.com/v1 (e.g., mistralai/mistral-large-3-675b-instruct-2512). Account details: Account email: 179072672… --- ## [Request for NVIDIA NIM API Rate Limit Increase (40 → 200 RPM) – AI Coding in VS Code + OpenCode](https://forums.developer.nvidia.com/t/request-for-nvidia-nim-api-rate-limit-increase-40-200-rpm-ai-coding-in-vs-code-opencode/366330)
**Author:** [@jocker1515](https://forums.developer.nvidia.com/u/jocker1515)\ **Replies:** 2\ **Last updated:** [April 16, 2026, 3:30pm UTC](https://forums.developer.nvidia.com/t/request-for-nvidia-nim-api-rate-limit-increase-40-200-rpm-ai-coding-in-vs-code-opencode/366330 "2026-04-16T15:30:33Z")
Hello NVIDIA Support Team, I am writing to request a rate limit increase for my NVIDIA NIM API account. Current Limit: 40 RPM Requested Limit: 200 RPM (or the next available higher tier for individual developer use) A… --- ## [Hosted Integrate /v1/responses returns 404 across multiple models while /v1/models and /v1/chat/completions work](https://forums.developer.nvidia.com/t/hosted-integrate-v1-responses-returns-404-across-multiple-models-while-v1-models-and-v1-chat-completions-work/364768)
**Author:** [@codyshanemitchell](https://forums.developer.nvidia.com/u/codyshanemitchell)\ **Replies:** 0\ **Last updated:** [March 25, 2026, 8:10pm UTC](https://forums.developer.nvidia.com/t/hosted-integrate-v1-responses-returns-404-across-multiple-models-while-v1-models-and-v1-chat-completions-work/364768 "2026-03-25T20:10:23Z")
I did a hosted compatibility repro against https://integrate.api.nvidia.com/v1 and put the artifacts here: GitHub - SproutSeeds/codex-nim-poc: Proof-of-concept for Codex custom-provider compatibility against NVIDIA NIM… --- ## [Mistral-large-3-675b-instruct-2512 Internal server error](https://forums.developer.nvidia.com/t/mistral-large-3-675b-instruct-2512-internal-server-error/356054)
**Author:** [@vutran\_kpt](https://forums.developer.nvidia.com/u/vutran_kpt)\ **Replies:** 4\ **Last updated:** [January 23, 2026, 10:57pm UTC](https://forums.developer.nvidia.com/t/mistral-large-3-675b-instruct-2512-internal-server-error/356054 "2026-01-23T22:57:31Z")
Can we look into this issue? Thank you. --- ## [Help: Running NVFP4 model on 2x DGX Spark with vLLM + Ray (multi-node)](https://forums.developer.nvidia.com/t/help-running-nvfp4-model-on-2x-dgx-spark-with-vllm-ray-multi-node/353723)
**Author:** [@letsrock85](https://forums.developer.nvidia.com/u/letsrock85)\ **Replies:** 18\ **Last updated:** [December 25, 2025, 7:17pm UTC](https://forums.developer.nvidia.com/t/help-running-nvfp4-model-on-2x-dgx-spark-with-vllm-ray-multi-node/353723 "2025-12-25T19:17:55Z")
Help: Running NVFP4 model on 2x DGX Spark with vLLM + Ray (multi-node) Hardware 2x DGX Spark (GB10 GPU each, sm\_121a / compute capability 12.1) Connected via 200GbE ConnectX-7/Ethernet Driver: 580.95.05, Host CUD… --- ## [Inferencing models from api taking very long](https://forums.developer.nvidia.com/t/inferencing-models-from-api-taking-very-long/355033)
**Author:** [@duytannguyen479](https://forums.developer.nvidia.com/u/duytannguyen479)\ **Replies:** 1\ **Last updated:** [December 19, 2025, 9:48pm UTC](https://forums.developer.nvidia.com/t/inferencing-models-from-api-taking-very-long/355033 "2025-12-19T21:48:55Z")
i have trying to inference from the NIM but it take very very long time \[2025-12-18 03:30:49,971\]\[httpx\]\[INFO\] - HTTP Request: POST https://integrate.api.nvidia.com/v1/chat/completions "HTTP/1.1 200 OK" \[2025-12-18 03:3… --- ## [New NIM Available: Mistral Large 2 Instruct LLM](https://forums.developer.nvidia.com/t/new-nim-available-mistral-large-2-instruct-llm/303298)
**Author:** [@jwitsoe](https://forums.developer.nvidia.com/u/jwitsoe)\ **Replies:** 0\ **Last updated:** [August 13, 2024, 8:37pm UTC](https://forums.developer.nvidia.com/t/new-nim-available-mistral-large-2-instruct-llm/303298 "2024-08-13T20:37:25Z")
Originally published at: https://developer.nvidia.com/blog/new-nim-available-mistral-large-2-instruct-llm/ The new model by Mistral excels at a variety of complex tasks including text summarization, multilingual tran…