Documentation Index
Fetch the complete documentation index at: https://togetherai-migration.mintlify.app/llms.txt
Use this file to discover all available pages before exploring further.
Overview
This document outlines our deprecation policy and provides information on migrating from deprecated models to newer or alternate versions.Deprecation Policy
| Model Type | Deprecation Notice | Notes |
|---|---|---|
| Preview Model | <24 hrs of notice, after 30 days | Clearly marked in docs and playground with “Preview” tag |
| Serverless Endpoint | 2 or 3 weeks* | |
| On Demand Dedicated Endpoint | 2 or 3 weeks* |
- Users of models scheduled for deprecation will be notified by email.
- All changes will be reflected on this page.
- Each deprecated model will have a specified removal date.
- After the removal date, the model will no longer be queryable via its serverless endpoint but options to migrate will be available as described below.
Migration Options
When a model is deprecated on our serverless platform, users have three options:-
On-demand Dedicated Endpoint (if supported):
- Reserved solely for the user, users choose underlying hardware.
- Charged on a price per minute basis.
- Endpoints can be dynamically spun up and down.
-
Monthly Reserved Dedicated Endpoint:
- Reserved solely for the user.
- Charged on a month-by-month basis.
- Can be requested via this form.
-
Migrate to a newer serverless model:
- Switch to an updated model on the serverless platform.
Migration Steps
- Review the deprecation table below to find your current model.
- Check if on-demand dedicated endpoints are supported for your model.
- Decide on your preferred migration option.
- If choosing a new serverless model, test your application thoroughly with the new model before fully migrating.
- Update your API calls to use the new model or dedicated endpoint.
Planned Deprecations
| Planned Deprecation Date | Model | Recommended Model Replacement |
|---|---|---|
| 2025-04-17 | google-gemma-2-9b-it | Qwen/Qwen2.5-7B-Instruct-Turbo |
| 2025-04-17 | google-gemma-2b-it | Qwen/Qwen2.5-7B-Instruct-Turbo |
| 2025-04-17 | gryphe-mythomax-l2-13b-lite | gryphe-mythomax-l2-13b |
| 2025-04-17 | meta-llama-llama-3-2-3b-instruct-turbo-lora | meta-llama/Meta-Llama-3.1-8B-Instruct-lora |
| 2025-04-30 | gryphe-mythomax-l2-13b | meta-llama/Llama-3.3-70B-Instruct-Turbo |
| 2025-04-30 | mistralai-mixtral-8x22b-instruct-v0-1 | meta-llama/Llama-3.3-70B-Instruct-Turbo |
| 2025-04-30 | mistralai-mixtral-8x7b-v0-1 | meta-llama/Llama-3.3-70B-Instruct-Turbo |
| 2025-04-30 | togethercomputer-m2-bert-80m-2k-retrieval | togethercomputer/m2-bert-80M-32k-retrieval |
| 2025-04-30 | togethercomputer-m2-bert-80m-8k-retrieval | togethercomputer/m2-bert-80M-32k-retrieval |
| 2025-04-30 | whereisai-uae-large-v1 | togethercomputer/m2-bert-80M-32k-retrieval |
Deprecation History
All deprecations are listed below, with the most recent deprecations at the top.| Removal Date | Model | Supported by on-demand dedicated endpoints |
|---|---|---|
| 2025-04-17 | meta-llama-meta-llama-3-8b-instruct-turbo | No (coming soon!) |
| 2025-04-24 | meta-llama/Llama-2-13b-chat-hf | No (coming soon!) |
| 2025-04-24 | xmeta-llama-meta-llama-3-70b-instruct-turbo | No (coming soon!) |
| 2025-04-24 | meta-llama-meta-llama-3-1-8b-instruct-turbo-lora | No (coming soon!) |
| 2025-04-24 | meta-llama-meta-llama-3-1-70b-instruct-turbo-lora | No (coming soon!) |
| 2025-04-24 | meta-llama-llama-3-2-1b-instruct-lora | No (coming soon!) |
| 2025-04-24 | microsoft-wizardlm-2-8x22b | No (coming soon!) |
| 2025-04-24 | upstage-solar-10-7b-instruct-v1 | No (coming soon!) |
| 2025-04-14 | stabilityai/stable-diffusion-xl-base-1.0 | No (coming soon!) |
| 2025-04-04 | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo-lora | No (coming soon!) |
| 2025-03-27 | mistralai/Mistral-7B-v0.1 | No |
| 2025-03-25 | Qwen/QwQ-32B-Preview | No |
| 2025-03-13 | databricks-dbrx-instruct | No |
| 2025-03-11 | meta-llama/Meta-Llama-3-70B-Instruct-Lite | No |
| 2025-03-08 | Meta-Llama/Llama-Guard-7b | No |
| 2025-02-06 | sentence-transformers/msmarco-bert-base-dot-v5 | No |
| 2025-02-06 | bert-base-uncased | No |
| 2024-10-29 | Qwen/Qwen1.5-72B-Chat | No |
| 2024-10-29 | Qwen/Qwen1.5-110B-Chat | No |
| 2024-10-07 | NousResearch/Nous-Hermes-2-Yi-34B | No |
| 2024-10-07 | NousResearch/Hermes-3-Llama-3.1-405B-Turbo | No |
| 2024-08-22 | NousResearch/Nous-Hermes-2-Mistral-7B-DPO | Yes |
| 2024-08-22 | SG161222/Realistic_Vision_V3.0_VAE | No |
| 2024-08-22 | meta-llama/Llama-2-70b-chat-hf | No |
| 2024-08-22 | mistralai/Mixtral-8x22B | No |
| 2024-08-22 | Phind/Phind-CodeLlama-34B-v2 | No |
| 2024-08-22 | meta-llama/Meta-Llama-3-70B | Yes |
| 2024-08-22 | teknium/OpenHermes-2p5-Mistral-7B | Yes |
| 2024-08-22 | openchat/openchat-3.5-1210 | Yes |
| 2024-08-22 | WizardLM/WizardCoder-Python-34B-V1.0 | No |
| 2024-08-22 | NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT | Yes |
| 2024-08-22 | NousResearch/Nous-Hermes-Llama2-13b | Yes |
| 2024-08-22 | zero-one-ai/Yi-34B-Chat | No |
| 2024-08-22 | codellama/CodeLlama-34b-Instruct-hf | No |
| 2024-08-22 | codellama/CodeLlama-34b-Python-hf | No |
| 2024-08-22 | teknium/OpenHermes-2-Mistral-7B | Yes |
| 2024-08-22 | Qwen/Qwen1.5-14B-Chat | Yes |
| 2024-08-22 | stabilityai/stable-diffusion-2-1 | No |
| 2024-08-22 | meta-llama/Llama-3-8b-hf | Yes |
| 2024-08-22 | prompthero/openjourney | No |
| 2024-08-22 | runwayml/stable-diffusion-v1-5 | No |
| 2024-08-22 | wavymulder/Analog-Diffusion | No |
| 2024-08-22 | Snowflake/snowflake-arctic-instruct | No |
| 2024-08-22 | deepseek-ai/deepseek-coder-33b-instruct | No |
| 2024-08-22 | Qwen/Qwen1.5-7B-Chat | Yes |
| 2024-08-22 | Qwen/Qwen1.5-32B-Chat | No |
| 2024-08-22 | cognitivecomputations/dolphin-2.5-mixtral-8x7b | No |
| 2024-08-22 | garage-bAInd/Platypus2-70B-instruct | No |
| 2024-08-22 | google/gemma-7b-it | Yes |
| 2024-08-22 | meta-llama/Llama-2-7b-chat-hf | Yes |
| 2024-08-22 | Qwen/Qwen1.5-32B | No |
| 2024-08-22 | Open-Orca/Mistral-7B-OpenOrca | Yes |
| 2024-08-22 | codellama/CodeLlama-13b-Instruct-hf | Yes |
| 2024-08-22 | NousResearch/Nous-Capybara-7B-V1p9 | Yes |
| 2024-08-22 | lmsys/vicuna-13b-v1.5 | Yes |
| 2024-08-22 | Undi95/ReMM-SLERP-L2-13B | Yes |
| 2024-08-22 | Undi95/Toppy-M-7B | Yes |
| 2024-08-22 | meta-llama/Llama-2-13b-hf | No |
| 2024-08-22 | codellama/CodeLlama-70b-Instruct-hf | No |
| 2024-08-22 | snorkelai/Snorkel-Mistral-PairRM-DPO | Yes |
| 2024-08-22 | togethercomputer/LLaMA-2-7B-32K-Instruct | Yes |
| 2024-08-22 | Austism/chronos-hermes-13b | Yes |
| 2024-08-22 | Qwen/Qwen1.5-72B | No |
| 2024-08-22 | zero-one-ai/Yi-34B | No |
| 2024-08-22 | codellama/CodeLlama-7b-Instruct-hf | Yes |
| 2024-08-22 | togethercomputer/evo-1-131k-base | No |
| 2024-08-22 | codellama/CodeLlama-70b-hf | No |
| 2024-08-22 | WizardLM/WizardLM-13B-V1.2 | Yes |
| 2024-08-22 | meta-llama/Llama-2-7b-hf | No |
| 2024-08-22 | google/gemma-7b | Yes |
| 2024-08-22 | Qwen/Qwen1.5-1.8B-Chat | Yes |
| 2024-08-22 | Qwen/Qwen1.5-4B-Chat | Yes |
| 2024-08-22 | lmsys/vicuna-7b-v1.5 | Yes |
| 2024-08-22 | zero-one-ai/Yi-6B | Yes |
| 2024-08-22 | Nexusflow/NexusRaven-V2-13B | Yes |
| 2024-08-22 | google/gemma-2b | Yes |
| 2024-08-22 | Qwen/Qwen1.5-7B | Yes |
| 2024-08-22 | NousResearch/Nous-Hermes-llama-2-7b | Yes |
| 2024-08-22 | togethercomputer/alpaca-7b | Yes |
| 2024-08-22 | Qwen/Qwen1.5-14B | Yes |
| 2024-08-22 | codellama/CodeLlama-70b-Python-hf | No |
| 2024-08-22 | Qwen/Qwen1.5-4B | Yes |
| 2024-08-22 | togethercomputer/StripedHyena-Hessian-7B | No |
| 2024-08-22 | allenai/OLMo-7B-Instruct | No |
| 2024-08-22 | togethercomputer/RedPajama-INCITE-7B-Instruct | No |
| 2024-08-22 | togethercomputer/LLaMA-2-7B-32K | Yes |
| 2024-08-22 | togethercomputer/RedPajama-INCITE-7B-Base | No |
| 2024-08-22 | Qwen/Qwen1.5-0.5B-Chat | Yes |
| 2024-08-22 | microsoft/phi-2 | Yes |
| 2024-08-22 | Qwen/Qwen1.5-0.5B | Yes |
| 2024-08-22 | togethercomputer/RedPajama-INCITE-7B-Chat | No |
| 2024-08-22 | togethercomputer/RedPajama-INCITE-Chat-3B-v1 | No |
| 2024-08-22 | togethercomputer/GPT-JT-Moderation-6B | No |
| 2024-08-22 | Qwen/Qwen1.5-1.8B | Yes |
| 2024-08-22 | togethercomputer/RedPajama-INCITE-Instruct-3B-v1 | No |
| 2024-08-22 | togethercomputer/RedPajama-INCITE-Base-3B-v1 | No |
| 2024-08-22 | WhereIsAI/UAE-Large-V1 | No |
| 2024-08-22 | allenai/OLMo-7B | No |
| 2024-08-22 | togethercomputer/evo-1-8k-base | No |
| 2024-08-22 | WizardLM/WizardCoder-15B-V1.0 | No |
| 2024-08-22 | codellama/CodeLlama-13b-Python-hf | Yes |
| 2024-08-22 | allenai-olmo-7b-twin-2t | No |
| 2024-08-22 | sentence-transformers/msmarco-bert-base-dot-v5 | No |
| 2024-08-22 | codellama/CodeLlama-7b-Python-hf | Yes |
| 2024-08-22 | hazyresearch/M2-BERT-2k-Retrieval-Encoder-V1 | No |
| 2024-08-22 | bert-base-uncased | No |
| 2024-08-22 | mistralai/Mistral-7B-Instruct-v0.1-json | No |
| 2024-08-22 | mistralai/Mistral-7B-Instruct-v0.1-tools | No |
| 2024-08-22 | togethercomputer-codellama-34b-instruct-json | No |
| 2024-08-22 | togethercomputer-codellama-34b-instruct-tools | No |
Notes on model support:
- Models marked “Yes” in the on-demand dedicated endpoint support column can be spun up as dedicated endpoints with customizable hardware.
- Models marked “No” are not available as on-demand endpoints and will require migration to a different model or a monthly reserved dedicated endpoint.
Recommended Actions
- Regularly check this page for updates on model deprecations.
- Plan your migration well in advance of the removal date to ensure a smooth transition.
- If you have any questions or need assistance with migration, please contact our support team.