Together
Explore Together models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Togethertogether
These privacy labels describe Together, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.
| Provider | Together |
|---|---|
| API operator country | US Legal home of the API operator, not an inference-location guarantee. |
| Headquarters | Not verified |
| Routing status | Active |
| Provider website | https://www.together.ai/ |
| Models | 13 public models |
| Credits routes | 13 |
| Zero data retention | yes All routes |
| Verified confidential inference | Not verified |
| Policy note | Tracked as provider ZDR. Together documents that inference inputs and outputs are not stored by default; temporary prompt caching may be used for performance, and sharing content for training is opt-in. Policy source |
Inference locations
Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.
Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.
- Declared countries or regions
- Not verified
No inference-location declaration has been verified for this provider. - Can locations change?
- Not verified. Do not assume that the serving location is fixed.
- Provider region pinning
- Not verified.
- Pinning through TrustedRouter
- No verified provider-specific location pin documented here.
- Infrastructure declaration
- Inference location not verified; no country-specific residency commitment.
- Evidence
- Not yet reviewed.
Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.
Measured performance
499 samplesContinuously sampled across Together's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 964 ms |
|---|---|
| Effective throughput | 164 tok/s n=1 |
| Uptime | 99.80% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4.1-flash | 964 ms | — | 99.79% | — | 485 |
| openai/gpt-oss-120b | 357 ms | — | 100.00% | — | 1 |
| meta-models/muse-glimmer-30b | 1223 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 1353 ms | — | 100.00% | — | 3 |
| qwen/qwen3.8-2.4t-a95b | 1657 ms | — | 100.00% | — | 1 |
| prism-ml/ternary-bonsai-27b | 1806 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | — | — | 100.00% | — | 6 |
| minimax/minimax-m3 | — | 164 tok/s n=1 | — | — | 0 |
Together performance history · Full provider & model leaderboard.
Models served by Together.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Input | Cached input | Output |
|---|---|---|---|---|---|
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | $0.1477/1M | $0.03165/1M | $0.2954/1M |
deepseek/deepseek-v4.1-flashDeepSeek: DeepSeek V4.1 Flash |
IQ 126#21 | 1,048,576 | $0.3165/1M | $0.01/1M | $1.266/1M |
meta-llama/llama-3.3-70b-instructMeta: Llama 3.3 70B Instruct |
— | 131,072 | $1.0972/1M | Not published | $1.0972/1M |
meta-models/muse-glimmer-30bmeta-models/Muse-Glimmer-30B |
— | 131,072 | $0.36925/1M | $0.0422/1M | $1.5825/1M |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 115#54 | 524,288 | $0.3165/1M | $0.0633/1M | $1.266/1M |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 127#20 | 1,048,576 | $3.165/1M | $0.3165/1M | $15.825/1M |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 98#126 | 131,072 | $0.15825/1M | Not published | $0.633/1M |
prism-ml/ternary-bonsai-27bTernary Bonsai 27B |
— | 262,144 | $0.01/1M | Not published | $0.01/1M |
qwen/qwen3.5-9bQwen: Qwen3.5-9B |
IQ 98#131 | 262,144 | $0.17935/1M | Not published | $0.26375/1M |
qwen/qwen3.8-2.4t-a95bQwen: Qwen3.8 2.4T A95B |
IQ 124#31 | 1,000,000 | $2.11/1M | $0.26375/1M | $6.33/1M |
thinkingmachines/inklingThinking Machines: Inkling |
IQ 108#81 | 524,288 | $1.055/1M | $0.17935/1M | $4.27275/1M |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 119#45 | 1,048,576 | $1.477/1M | $0.2743/1M | $4.642/1M |
z-ai/glm-5.3-flashZ.ai: GLM 5.3 Flash |
IQ 120#42 | 1,048,576 | $0.15825/1M | $0.03165/1M | $0.5275/1M |
Questions
Does Together have zero data retention?
TrustedRouter records Together as supporting provider-level zero data retention based on the policy source linked on this page. This is a provider policy claim, separate from TrustedRouter's content-stateless real-time gateway and from end-to-end confidential compute.
Is Together end-to-end encrypted?
TrustedRouter does not currently mark Together as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Together models are available through TrustedRouter?
This page currently lists 13 public Together models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.