Together AI
Official sourceAnnouncement
Today marks the launch of our Rerank API, featuring Salesforce's LlamaRank as our inaugural model. ... Client( base_url="https://api.together.xyz/ ...
$10 off the fastest DeepSeek V4.1 Flash, Kimi K3 and GLM 5.3 from Synthetic
Provider details
Together AI
Learn more about this provider, then browse the models currently listed under it.
togetheraitogetherai
Latest news about Together AI
Together AI
Official sourceAnnouncement
Together AI's official blog index (together.ai/blog) surfaces several first-party announcements relevant to the platform. The company announced an $800M Series C to accelerate the shift to open-source AI, citing the economics of closed models as motivation. Together also partnered with Y Combinator to launch a dedicate The blog also publishes multiple DeepSWE benchmark studies authored by Together, each based on 904 rollouts: GLM-5.3 vs GLM-5.3 Flash and GLM-5.3 vs GPT-5.6 Sol on DeepSWE (Sol leads pass@1 by 3.7 points, GLM-5.3 wins pass@4 at half the cost, GLM-first cascade hits 85.9%); DeepSeek V4 Pro 0813 vs GPT-5.6 Sol (Sol leads
Together AI
Coverage
Together AI announced an $800 million Series C funding round led by Aramco Ventures, more than doubling its valuation to $8.3 billion. Participating investors included Vista Equity Partners, General Catalyst, Emergence Capital, Nvidia, Salesforce Ventures, March Capital, Pegatron, and SentinelOne's S Ventures. The roun The company stated it will use the proceeds to widen its offerings as it expands into a provider of inference for open models such as DeepSeek, Moonshot's Kimi, and others at lower cost than closed systems. Annual bookings crossed $1.15 billion last quarter, with customers including Cursor, Cognition, and Decagon, and
Together AI
Official sourceRelease Notes
Together AI's September 2026 changelog documents several platform-level changes relevant to developers using its hosted inference and GPU cluster products. On September 15, the company deprecated serverless availability of openai/gpt-oss-20b, google/gemma-4-31B-it, and thinkingmachines/Inkling-Small, recommending zai-o The Together CLI v2.34.0 ships the rollouts feature in the Python SDK at client.beta.endpoints.rollouts and adds HIPAA placement controls (--placement.hipaa) so deployments can be restricted to HIPAA-attested clusters, plus stricter Parquet file-size validation in `tg files check`. On September 11, Together added deeps
About Together AI
What they do
Together AI provides a full-stack AI cloud with hosted inference, fine-tuning, dedicated deployments, and GPU clusters for model workloads.
How they were founded
Founded in 2022 by Vipul Ved Prakash, Ce Zhang, Chris Re, Tri Dao, and Percy Liang to bring research-grade AI infrastructure to production developers.
Quick Info
- Organization
- Together AI
- Headquarters
- San Francisco, California, United States
- SDK package
- @ai-sdk/togetherai
- Synced at
- Jul 11, 2026
Models served
29 models available through Together AI
These model results are sorted newest first so you can quickly see the latest options from this provider.
Together AIdeepseek-flash
DeepSeek V4.1 Flash
deepseek-ai/DeepSeek-V4.1-FlashTogether AIReleased Sep 10, 20261,048,576 token context windowIn $0.30 · Out $1.20
Input
Output
Together AIglm-flash
GLM-5.3-Flash
zai-org/GLM-5.3-FlashTogether AIReleased Aug 26, 20261,048,575 token context windowIn $0.15 · Out $0.50
Input
Output
Together AIglm
Input
Output
Together AIdeepseek-thinking
DeepSeek V4 Pro 0813
deepseek-ai/DeepSeek-V4-Pro-0813Together AIReleased Aug 12, 20261,048,576 token context windowIn $1.32 · Out $3.96
Input
Output
Together AIdeepseek-flash
DeepSeek V4 Flash 0731
deepseek-ai/DeepSeek-V4-Flash-0731Together AIReleased Jul 31, 20261,048,576 token context windowIn $0.14 · Out $0.28
Input
Output
Together AIkimi-k3
Kimi K3
moonshotai/Kimi-K3Together AIReleased Jul 16, 20261,048,576 token context windowIn $3.00 · Out $15.00
Input
Output
Together AIling
Inkling
thinkingmachines/InklingTogether AIReleased Jul 15, 2026524,288 token context windowIn $1.00 · Out $4.05
Input
Output
Together AIglm
Input
Output
Together AIminimax
MiniMax-M3
MiniMaxAI/MiniMax-M3Together AIReleased Jun 12, 2026524,288 token context windowIn $0.30 · Out $1.20
Input
Output
Together AInemotron
Nemotron 3 Ultra 550B A55B
nvidia/nemotron-3-ultra-550b-a55bTogether AIReleased Jun 4, 2026512,300 token context windowIn $0.60 · Out $3.60
Input
Output
Together AIqwen
Input
Output
Together AIqwen
Input
Output
Together AIglmdeprecated
Input
Output
Together AIminimax
MiniMax-M2.7
MiniMaxAI/MiniMax-M2.7Together AIReleased Mar 18, 2026196,608 token context windowIn $0.30 · Out $1.20
Input
Output
Together AIqwen
Input
Output
Together AIliquid
LFM2-24B-A2B
LiquidAI/LFM2-24B-A2BTogether AIReleased Feb 25, 202632,768 token context windowIn $0.03 · Out $0.12
Input
Output
Together AIqwendeprecated
Qwen3.5 397B A17B
Qwen/Qwen3.5-397B-A17BTogether AIReleased Feb 16, 2026262,144 token context windowIn $0.60 · Out $3.60
Input
Output
Together AIminimaxdeprecated
MiniMax-M2.5
MiniMaxAI/MiniMax-M2.5Together AIReleased Feb 12, 2026204,800 token context windowIn $0.30 · Out $1.20
Input
Output