Together AI
The publisher documents serverless text generation through Together AI.
- Verified facts
- 7
- Offers
- —
- Sources
- 4
- Pricing
- Metered usage
Overview
Inference and client scope
Together AI’s publisher documentation describes serverless text generation and examples using its Python v2 SDK. The documentation also describes separate training and other API workflows. Check whether the exact model, input type and endpoint you need are currently available.
The selected skills repository is an agent-skills project, not the inference service itself. Its MIT licence does not establish rights to hosted inference, model weights, trademarks or third-party dependencies.
Read the full editorial overview
Costs and operating checks
Together’s pricing page, captured 9 November 2026, lists serverless chat models with separate input and output prices per 1 million tokens, and its rate-limits documentation says serverless performance is best-effort and requests may be limited under high demand, with committed throughput offered separately as provisioned throughput. Its privacy documentation says prompts and responses are stored by default and may be used for product improvements, and that organization admins can turn storage off to enable zero data retention. The captured pages do not establish numeric rate limits or a price for your workload. Check the relevant billing units, current price, rate limits, region and agreement before sending requests.
The documentation examples are not a live test or guarantee of output quality, speed or availability. No account, key, SDK execution, model request or paid provider call was used.
Sources
Together AI: together-docs · Evidence: documentation · Not checked
Documented facts
Each fact comes from official documentation and shows when it was verified.
Who it is for
The publisher documents serverless text generation through Together AI.
Coverage limits
The publisher describes Python SDK v2 examples for Together AI.
API interfaces
OpenAI-compatible serverless text generation
Publisher skills README (togethercomputer/skills) captured 3 November 2026; supplier description of the chat-completions skill, not an API call or compatibility test. Which OpenAI endpoints and parameters are supported is not established.
Model catalogue
Kimi K3, GLM-5.3, GLM-5.3-Flash
Together AI pricing page captured 9 November 2026 (amounts shown with a $ sign; the page states no ISO currency); supplier statement, not a hands-on test. Three of the serverless chat models listed in the pricing table; the table lists more and changes often, so it is not the complete catalogue.
Billing basis
Models are priced per 1 million tokens, with separate input and output prices for each model.
Together AI pricing page captured 9 November 2026 (amounts shown with a $ sign; the page states no ISO currency); supplier statement, not a hands-on test. Serverless Inference pricing table (Chat tab): rates vary by model, some models list a cached-input price, and the table header also lists a Batch API price. Image, video, audio and other modalities use other units. Dedicated endpoints, provisioned throughput and GPU clusters are priced separately and not captured.
Data controls
By default prompts and responses are stored and may be used for product improvements; organization admins can turn storage off to enable zero data retention.
Together AI Privacy and security documentation captured 9 November 2026; supplier statement, not an audit or test. The page also says training on customer data is opt-in and off by default, and that some passthrough models forward prompts to third-party providers who apply their own data policies.
Availability
Serverless performance is best-effort and requests may be limited under high demand; committed throughput with reliability guarantees is offered separately as provisioned throughput.
Together AI serverless rate-limits documentation captured 9 November 2026; supplier statement, not a load test. Numeric limits are not stated on the page; the page says custom limits or access restrictions can apply to models in high demand.
Applies to the facts above: Publisher documentation captured 3 November 2026; describes selected documentation or client behavior, not a live service test. Current model availability, prices and service terms require confirmation.
Not confirmed in our sources
We have not confirmed these terms for Together AI in the linked documentation. That does not mean Together AI lacks them; confirm them before you rely on them.
- Pricing
Sources & methodology
Facts come from the linked documentation. Documentation checks are not hands-on tests, and readable sources can have incomplete coverage.
Discovered an undocumented discrepancy or pricing shift? Submit a correction request.
Submit correctionTogether AI alternatives
Other AI providers tools to weigh. Different billing units do not establish a cost winner, so compare plans side by side.
OpenAI API
AI providers
Hosted models for text and image inputs, with Responses API access and client SDKs. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Anthropic Claude API
AI providers
Programmatic access to Claude models through a REST API. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Google Gemini API
AI providers
A developer API catalogue with text, multimodal, audio and image model families. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Together AI comparisons
Compare two products in the same category using their documented terms and sources.
- Together AI vs Anthropic Claude API
- Together AI vs DeepInfra
- Together AI vs Google Gemini API
- Together AI vs Mistral AI API
- Together AI vs Nebius Token Factory
- Together AI vs OpenAI API
- Together AI vs Perplexity API Platform
- Together AI vs Replicate
- Together AI vs xAI API
- Together AI vs Baseten
- Together AI vs Cerebras Inference
- Together AI vs Cohere API
- Together AI vs Fireworks AI API
- Together AI vs Groq API
- Together AI vs Hugging Face Inference Providers
- Together AI vs IBM watsonx.ai
- Together AI vs NVIDIA NIM
- Together AI vs OpenRouter API
- Together AI vs SambaCloud