From f3e60a92d1ee5b1fd0f91e158127ae2e12235840 Mon Sep 17 00:00:00 2001 From: Zain Hasan Date: Sun, 12 Jul 2026 15:10:41 +0000 Subject: [PATCH] together-chat-completions: drop serverless-deprecated models Sync with togethercomputer/mintlify-docs#1096 and #1068. Qwen/Qwen3.5-397B-A17B was removed from the serverless catalog and the serverless reasoning table, and the documented vision recommendation is now Kimi K2.6. essentialai/rnj-1-instruct was removed from the serverless catalog. - Update the Vision recommendation to moonshotai/Kimi-K2.6 and add it to the Vision Models table. - Remove Qwen/Qwen3.5-397B-A17B from the chat catalog, vision table, reasoning table, on-by-default list, structured-outputs support list, and function-calling supported models; retarget two code/example references to still-current models. - Remove the essentialai/rnj-1-instruct catalog row. Left GLM-5, gemma-3n-E4B-it, and Meta-Llama-3-8B-Instruct-Lite in place: all three are still present in the current serverless catalog/reasoning docs. Batch and fine-tuning references are out of this PR's sync-map scope and still list Qwen3.5-397B-A17B for their own product surfaces. --- .../references/function-calling-patterns.md | 2 +- skills/together-chat-completions/references/models.md | 6 ++---- .../references/reasoning-models.md | 4 +--- .../references/structured-outputs.md | 3 +-- 4 files changed, 5 insertions(+), 10 deletions(-) diff --git a/skills/together-chat-completions/references/function-calling-patterns.md b/skills/together-chat-completions/references/function-calling-patterns.md index 114c93e..fa16ebe 100644 --- a/skills/together-chat-completions/references/function-calling-patterns.md +++ b/skills/together-chat-completions/references/function-calling-patterns.md @@ -824,7 +824,7 @@ workflow. ## Supported Models openai/gpt-oss-120b, openai/gpt-oss-20b, moonshotai/Kimi-K2.6, -zai-org/GLM-5.1, zai-org/GLM-5, MiniMaxAI/MiniMax-M2.7, Qwen/Qwen3.5-397B-A17B, +zai-org/GLM-5.1, zai-org/GLM-5, MiniMaxAI/MiniMax-M2.7, Qwen/Qwen3.5-9B, Qwen/Qwen3.6-Plus, Qwen/Qwen3-235B-A22B-Instruct-2507-tput, deepseek-ai/DeepSeek-V4-Pro, meta-llama/Llama-3.3-70B-Instruct-Turbo, Qwen/Qwen2.5-7B-Instruct-Turbo, google/gemma-4-31B-it diff --git a/skills/together-chat-completions/references/models.md b/skills/together-chat-completions/references/models.md index 39ea96f..b99039e 100644 --- a/skills/together-chat-completions/references/models.md +++ b/skills/together-chat-completions/references/models.md @@ -10,7 +10,7 @@ | Small & Fast | GPT-OSS 20B | `openai/gpt-oss-20b` | `Qwen/Qwen2.5-7B-Instruct-Turbo`, `google/gemma-3n-E4B-it` | | Medium General | GPT-OSS 120B | `openai/gpt-oss-120b` | `zai-org/GLM-5` | | Function Calling | GLM-5.1 | `zai-org/GLM-5.1` | `moonshotai/Kimi-K2.6`, `MiniMaxAI/MiniMax-M2.7` | -| Vision | Qwen3.5 397B | `Qwen/Qwen3.5-397B-A17B` | `Qwen/Qwen3.5-9B`, `google/gemma-4-31B-it` | +| Vision | Kimi K2.6 | `moonshotai/Kimi-K2.6` | `google/gemma-4-31B-it`, `Qwen/Qwen3.5-9B` | ## Full Chat Model Catalog @@ -18,7 +18,6 @@ |-------------|-------|-----------|---------|-------| | MiniMax | MiniMax M2.7 | `MiniMaxAI/MiniMax-M2.7` | 202,752 | FP4 | | Qwen | Qwen3.7 Max | `Qwen/Qwen3.7-Max` | - | - | -| Qwen | Qwen3.5 397B A17B | `Qwen/Qwen3.5-397B-A17B` | 262,144 | BF16 | | Qwen | Qwen3.6 Plus | `Qwen/Qwen3.6-Plus` | 1,000,000 | - | | Qwen | Qwen3.5 9B | `Qwen/Qwen3.5-9B` | 262,144 | FP8 | | Qwen | Qwen3 235B Instruct | `Qwen/Qwen3-235B-A22B-Instruct-2507-tput` | 262,144 | FP8 | @@ -36,13 +35,12 @@ | Google | Gemma 3N E4B | `google/gemma-3n-E4B-it` | 32,768 | FP8 | | Liquid AI | LFM2.5-8B-A1B | `LiquidAI/LFM2.5-8B-A1B` | 32,768 | - | | Qwen | Qwen 2.5 7B Turbo | `Qwen/Qwen2.5-7B-Instruct-Turbo` | 32,768 | FP8 | -| Essential AI | Rnj-1 Instruct | `essentialai/rnj-1-instruct` | 32,768 | BF16 | ## Vision Models | Organization | Model | API String | Context | |-------------|-------|-----------|---------| -| Qwen | Qwen3.5 397B A17B | `Qwen/Qwen3.5-397B-A17B` | 262,144 | +| Moonshot | Kimi K2.6 | `moonshotai/Kimi-K2.6` | 262,144 | | Qwen | Qwen3.5 9B | `Qwen/Qwen3.5-9B` | 262,144 | | Google | Gemma 4 31B IT | `google/gemma-4-31B-it` | 262,144 | diff --git a/skills/together-chat-completions/references/reasoning-models.md b/skills/together-chat-completions/references/reasoning-models.md index 662723f..bed60c2 100644 --- a/skills/together-chat-completions/references/reasoning-models.md +++ b/skills/together-chat-completions/references/reasoning-models.md @@ -23,7 +23,6 @@ | Kimi K2.6 | `moonshotai/Kimi-K2.6` | Hybrid (on by default) | 262K | Yes | | MiniMax M2.7 | `MiniMaxAI/MiniMax-M2.7` | Reasoning only | 202K | Yes | | Nemotron 3 Ultra 550B A55B | `nvidia/nemotron-3-ultra-550b-a55b` | Hybrid (on by default) | 512K | Yes | -| Qwen3.5 397B | `Qwen/Qwen3.5-397B-A17B` | Hybrid (on by default) | 262K | Yes | | Qwen3.5 9B | `Qwen/Qwen3.5-9B` | Hybrid (on by default) | 262K | Yes | | Qwen3.6 Plus | `Qwen/Qwen3.6-Plus` | Hybrid (on by default) | 1M | Yes | @@ -104,7 +103,6 @@ Hybrid models support `reasoning={"enabled": True/False}` to toggle reasoning on **Models supporting this parameter:** - `deepseek-ai/DeepSeek-V4-Pro` (on by default) -- `Qwen/Qwen3.5-397B-A17B` (on by default) - `Qwen/Qwen3.5-9B` (on by default) - `Qwen/Qwen3.6-Plus` (on by default) - `moonshotai/Kimi-K2.6` (on by default) @@ -196,7 +194,7 @@ print(response.choices[0].message.content) ```python response = client.chat.completions.create( - model="Qwen/Qwen3.5-397B-A17B", + model="Qwen/Qwen3.5-9B", messages=[{"role": "user", "content": "Prove that sqrt(2) is irrational."}], chat_template_kwargs={"thinking": True}, stream=True, diff --git a/skills/together-chat-completions/references/structured-outputs.md b/skills/together-chat-completions/references/structured-outputs.md index cf0ff32..6c103bb 100644 --- a/skills/together-chat-completions/references/structured-outputs.md +++ b/skills/together-chat-completions/references/structured-outputs.md @@ -512,7 +512,6 @@ console.log(`Title: ${result.title}`); - `zai-org/GLM-5.1` - `zai-org/GLM-5` - `MiniMaxAI/MiniMax-M2.7` -- `Qwen/Qwen3.5-397B-A17B` - `Qwen/Qwen3.6-Plus` - `deepseek-ai/DeepSeek-V4-Pro` @@ -538,5 +537,5 @@ console.log(`Title: ${result.title}`); 3. Use `json_schema` mode when you need guaranteed structure 4. Use `json_object` for simpler cases where prompt guidance is sufficient 5. Use `regex` mode for simple constrained outputs (classification, IDs, phone numbers) -6. Works with vision models (e.g., `Qwen/Qwen3.5-397B-A17B`) +6. Works with vision models (e.g., `moonshotai/Kimi-K2.6`) 7. Works with reasoning models (e.g., `deepseek-ai/DeepSeek-V4-Pro`)