Provider
Together AI
Open-source model inference platform. Hosts hundreds of third-party community model families (DeepSeek, Llama, Qwen, MiniMax, FLUX, etc.) — Together is a hosting platform, not a model creator.
Together AI
VerifiedSan Francisco, USA
Last checked: 2026-05-21 · brand mark: nominative
Official sources
Primary links
Vendor-published documentation roots. Linked content has not been individually verified as primary-source citations unless this provider's verification status is 'verified'.
- Websitetogether.ai
- Documentationdocs.together.ai
- API referencedocs.together.ai/reference
- Pricingtogether.ai/pricing
- Model cataloguedocs.together.ai/docs/serverless-models
- Status (vendor)Data not yet verified.
- DeprecationsData not yet verified.
Catalogue
Tracked models
0 models in the catalogue, 0 verified end-to-end.
No Together AI models in the catalogue yet.
Hosted platform
Together AI hosts third-party models
Together AI is a hosting/inference platform — it bills for models created by other organisations. The rows below are pricing references sourced from Together AI's own pricing page, not live quotes. Pricing is volatile and may change after retrieval. Treat prices as source-backed references, not live quotes.
| Model | Model creator | Hosted model ID | Input / 1M | Output / 1M | Freshness | Source |
|---|---|---|---|---|---|---|
| DeepSeek V4 Pro | DeepSeek | deepseek-ai/DeepSeek-V4-Pro | $2.10 | $4.40 | Fresh | Together AI |
Hosted pricing is set by Together AI — not by the model's creator. Rows are source-backed references, not live quotes; WebmasterID Models does not rank hosting platforms by price. See methodology for the full distinction.
What we cover
Data coverage
Which areas have verified data for this provider on the WebmasterID Models graph.
| Area | Coverage |
|---|---|
| Pricing | No verified pricing yet |
| Models | 0 tracked, 0 verified |
| Benchmarks | No verified third-party benchmark scores yet |
| Infrastructure | No verified region/latency/uptime data yet |
| Status | No independent monitor wired yet |
Data gaps
Fields not yet verified
These fields are intentionally null until verified against a primary source. They are not estimated.
Deprecations URL
Provider does not publish a stable deprecations page in their docs, or it has not yet been recorded.
Public status page
Provider has no public status page recorded.
Status observer
No vendor-status or independent-probe observer wired for this provider yet.
Regional availability
Per-provider regions array is null across the catalogue. Wiring Bedrock / Vertex availability matrices is a planned data expansion.
Per-account rate-limit numbers
Rate-limit tiers live in account consoles and are not surfaced as verified fields on this site.
How a value moves from this list to a verified row — see source verification methodology.
Entity graph
Related coverage
- Filtered models view: /models?provider=together-ai
- Pricing rows: /pricing?provider=together-ai
- Sources: /sources?provider=together-ai
- Comparisons: /compare?provider=together-ai
- Status observer: /api/status/together-ai
Continue
Related providers
Providers that appear alongside this one in comparisons, plus the rest of the catalogue.
Audit log
Verification attempts
Every primary-source URL targeted for this provider and what came back. Blocked attempts are recorded honestly rather than substituted with second-hand data.
Together AI serverless-models reference
docs.together.ai/docs/serverless-modelsTogether AI serverless-models page retrieved. Lists hosted third-party model families across chat, image, video, audio, and embedding categories. Used only to verify the provider/platform itself — these models are NOT Together-created, so no per-model entries are added under provider=together-ai.
2026-05-21
verified
Together AI serverless inference pricing
www.together.ai/pricingTogether AI pricing page retrieved as raw HTML. The serverless inference table anchors 'DeepSeek V4 Pro' at $2.10/1M input, $4.40/1M output, with $0.20/1M cache-hit input — recorded as a hosted-provider row (creator=deepseek, billing=together-ai). Llama 4 Scout and Llama 4 Maverick appear ONLY in Together's separate Fine-Tuning table (LoRA + Full Fine-Tuning columns) and ONLY in the dedicated-GPU section, not in serverless inference — those prices are intentionally NOT recorded as inference pricing.
2026-05-23
verified
Together AI serverless-models docs (Llama 4 lookup)
docs.together.ai/docs/serverless-modelsRe-retrieved Together's docs/serverless-models page on 2026-05-23. The page contained zero references to 'Llama 4 Scout', 'Llama 4 Maverick', 'Maverick', 'Scout', 'Llama-4', or 'llama-4'. Together does not appear to expose Llama 4 on serverless inference at this time; the catalogue records no Together hosted pricing for the Llama 4 family.
2026-05-23
insufficient data
Together AI pricing page (Llama 4 Scout/Maverick rows)
www.together.ai/pricingLlama 4 Scout and Llama 4 Maverick appear on Together's pricing page only inside the Fine-Tuning table (LoRA / Full Fine-Tuning columns) and the dedicated-GPU section. The numbers cannot be safely mapped to per-1M-tokens serverless inference rates without misattribution — recorded as ambiguous-model-mapping rather than published.
2026-05-23
ambiguous model mapping