# Portkey vs Together AI

**Leader by Vioscale score:** Portkey

| Attribute | Portkey | Together AI |
|---|---|---|
| **Vioscale score** | 78.9 (76% (high)) | 72.8 (60% (medium)) |
| deployment.options | `{"cloud":true,"hybrid":true,"self_hosted":true}` | `{"cloud":true}` |
| description.long | A unified platform combining an AI gateway, observability dashboards, prompt versioning, governance controls, and guardrails. Enables teams to route requests across LLM providers, monitor costs and performance, securely manage API keys, and deploy production-ready prompts with version control. | Together AI provides cloud infrastructure for hosting and serving open-source language, image, audio, and video models through serverless inference, reserved capacity, and dedicated GPU instances. The platform includes fine-tuning capabilities, batch processing, managed storage, and GPU cluster support for custom model development and training—eliminating the need for users to manage underlying infrastructure. |
| features.capabilities | `{"role":"gateway","caching":"semantic","evaluation":true,"open_source":true,"soc2_type_ii":true,"managed_cloud":true,"model_serving":true,"pricing_model":"pay_per_10k_traces","rate_limiting":true,"self_hostable":true,"multi_provider":true,"vpc_deployment":true,"deployment_model":"managed-SaaS","no_train_on_data":"unknown","routing_strategy":"load-based","llm_observability":true,"prompt_management":true,"architecture_model":"managed_cloud_saas","automatic_failover":true,"framework_agnostic":true,"experiment_tracking":true,"budget_spend_controls":true,"guardrails_moderation":"via-integration","openai_compatible_api":true,"virtual_key_management":true,"request_cost_observability":true,"mit_or_apache_permissive_oss_license":true,"production_ab_testing_of_system_prompts":true,"token_cost_and_latency_waterfall_charts":true,"pii_redaction_and_prompt_content_masking":true,"prompt_playground_and_in_dashboard_replay":true,"multi_step_agentic_workflow_distributed_tracing":true,"user_feedback_score_api_for_thumbs_up_down_tags":true,"native_integration_with_langchain_and_llamaindex":true}` | `{"role":"platform","evaluation":false,"soc2_type_ii":false,"compute_model":"multi_tenant_hybrid","managed_cloud":true,"model_serving":true,"pricing_model":"per_million_tokens","self_hostable":false,"multi_provider":true,"vpc_deployment":true,"otel_compatible":false,"no_train_on_data":"yes","llm_observability":false,"prompt_management":false,"framework_agnostic":true,"experiment_tracking":false,"openai_compatible_rest_api_schema":false,"bring_your_own_weights_byow_hosting":true,"dynamic_batching_and_kv_cache_management":false,"massive_context_window_support_100k_plus":false,"hipaa_baa_compliance_for_medical_inference":false,"multimodal_vision_and_audio_in_out_support":true,"native_function_calling_and_strict_json_mode":false,"streaming_server_sent_events_sse_token_yield":false,"lpu_or_custom_silicon_for_extreme_low_latency":false,"zero_data_retention_training_opt_out_enterprise":true}` |
| integrations.count | 1,600 | - |
| integrations.list | `[{"name":"OpenAI"},{"name":"Google Cloud (Vertex AI, Gemini)"},{"name":"Azure"},{"name":"AWS"},{"name":"GCP"},{"name":"Langgraph"},{"name":"CrewAI"},{"name":"Strands Agents"},{"name":"Google ADK"},{"name":"Anthropic"},{"name":"Claude"},{"name":"Mistral"},{"name":"Google"},{"name":"MongoDB"},{"name":"Vertex AI"}]` | - |
| market.availability | `{"primaryMarkets":[],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` | `{"primaryMarkets":["US"],"availabilityScope":"global","availableCountries":[],"notAvailableCountries":[]}` |
| platform.support | `{"web":true}` | `{"cli":true,"web":true}` |
| pricing | `{"type":"hybrid","plans":[{"free":true,"name":"Developer","summary":"Free forever, 10k logs/month","features":["Universal API & Key Management","Routing, Fallbacks, Load Balancing, Retries","3 Prompt Templates with Playground, Versioning, Variables","Logs, Traces, Feedback, Custom Metadata, Filters","Simple Caching","Deterministic Guardrails","Community Support","3 days log retention, 30 days metrics retention"],"components":[{"kind":"fixed","amount":0,"period":"month","currency":"USD"}],"description":"Free tier for prototyping and testing; not suitable for production workloads","contactSales":false,"includedLimits":{"recorded_logs":"10k/month"}},{"free":false,"name":"Production","summary":"$49/month + $9 per 100k request overage","features":["Universal API, Fallbacks, Load Balancing, Retries","Unlimited Prompt Templates with Playground, API Deployment, Versioning, Variables","Logs, Traces, Feedback, Metadata, Filters, Alerts","LLM & Partner Guardrails","Role-Based Access Control, Service Account API Keys","Simple & Semantic Caching","Production Support","30 days log retention, 90 days metrics retention"],"commitment":"monthly","components":[{"kind":"fixed","amount":49,"period":"month","currency":"USD"},{"per":{"qty":100000,"unit":"requests"},"kind":"metered","amount":9,"currency":"USD"}],"description":"For teams deploying LLM apps to production","contactSales":false,"includedLimits":{"recorded_logs":"100k/month"}},{"free":false,"name":"Enterprise","summary":"Custom pricing","features":["Custom retention periods for logs and metrics","Advanced Evaluation Templates with custom guardrail hooks","Role-Based Access Control, SSO (Okta), Granular Budget & Rate Limits","Private Cloud Deployment, VPC Hosting, Data Export to Data Lakes","SOC2 Type 2, GDPR, HIPAA compliance certifications","Custom Business Associate Agreements","Data Isolation, Configurable exports to data lakes","Dedicated Onboarding & Priority Support"],"description":"For organizations with complex compliance and high-volume production requirements","contactSales":true,"includedLimits":{"recorded_logs":"10M+/month"}}],"summary":"Free tier with 10k logs/month. Production at $49/month with usage overages. Enterprise custom pricing for compliance-focused organizations.","currency":"USD","freeTier":true,"sourceUrl":"https://portkey.ai/pricing","retrievedAt":"2026-08-21T13:46:13.229Z","startingPrice":{"amount":49,"period":"month","currency":"USD"},"billingPeriods":["month"]}` | `{"type":"usage","plans":[{"free":false,"name":"Serverless Inference","summary":"From $0.00014–$15/1M tokens depending on model. Pay only for usage.","features":["50+ open-source models","Variable pricing by model and token type","Batch API support","Private endpoints"],"components":[{"per":{"qty":1000000,"unit":"tokens"},"kind":"metered","amount":0.00014,"currency":"USD"}],"contactSales":false},{"free":false,"name":"Provisioned Throughput","summary":"Reserved throughput capacity with 99% SLA. PTU-based pricing structure.","features":["Reserved token capacity","99% uptime SLA","Token-based pricing model","Production-grade reliability"],"commitment":"monthly","contactSales":false},{"free":false,"name":"Dedicated Inference","summary":"$3.69–$8.99 per GPU per hour (on-demand); reserved discounts available.","features":["Single-tenant GPU instances","Guaranteed performance (no resource sharing)","Custom model support","Autoscaling for traffic spikes"],"commitment":"monthly","components":[{"kind":"fixed","amount":3.69,"period":"hour","currency":"USD"}],"contactSales":false}],"addOns":[{"name":"Fine-Tuning","components":[{"per":{"qty":1000000,"unit":"tokens"},"kind":"metered","amount":0.48,"currency":"USD"}]},{"name":"Managed Storage"},{"name":"GPU Clusters"}],"summary":"Usage-based pricing starting from $0.00014/1M tokens for serverless inference. Reserved capacity and dedicated GPU instances available; on-demand GPU pricing from $3.69/hour.","currency":"USD","freeTier":false,"sourceUrl":"https://www.together.ai/pricing","retrievedAt":"2026-08-21T12:44:34.463Z","startingPrice":{"unit":"tokens","amount":0.00014,"currency":"USD"},"billingPeriods":["month"]}` |
| pricing.free_tier | yes | no |
| pricing.model | freemium | commercial |
| pricing.price_level | mid | low |
| pricing.starting_price | `{"amount":49,"currency":"USD"}` | `{"amount":0.00014,"currency":"USD"}` |
| pricing.transparent | yes | yes |
| reliability.sla_pct | - | 99 |
| reliability.status_page | yes | yes |
| security.disclosure_policy | - | yes |
| security.gdpr | yes | yes |
| security.hipaa | yes | - |
| security.iso27001 | yes | yes |
| security.soc2 | yes | yes |

## Capabilities (MLOps & LLMOps Tools)

| Capability | Portkey | Together AI |
|---|:--:|:--:|
| **Core** |  |  |
| Tool role | Model gateway / router | End-to-end ML platform |
| **Deployment** |  |  |
| Self-hostable / OSS core | ✓ | ✗ |
| Managed cloud available | ✓ | ✓ |
| On-prem / VPC deployment | ✓ | ✓ |
| **Observability** |  |  |
| LLM tracing / observability | ✓ | ✗ |
| Evaluation (offline / LLM-judge / human) | ✓ | ✗ |
| **Dev** |  |  |
| Prompt management + versioning | ✓ | ✗ |
| **Tracking** |  |  |
| Experiment tracking / model registry | ✓ | ✗ |
| **Serving** |  |  |
| Model serving / inference endpoint | ✓ | ✓ |
| **Interop** |  |  |
| OpenTelemetry / OpenLLMetry compatible | - | ✗ |
| Framework-agnostic | ✓ | ✓ |
| **Gateway** |  |  |
| Multi-provider model support | ✓ | ✓ |
| **Data** |  |  |
| No-train-on-customer-data guarantee | Unknown | Yes |

*Source: Vioscale. Generated 2026-09-01T15:13:58.784Z. "-" = undocumented, not absent.*