LiteLLM vs Together AI
LiteLLM vs Together AI: side-by-side comparison of two inference platforms & gateways systems — architecture, taxonomy, license, pricing, MCP/A2A support, and direct edges.
How they relate
- LiteLLM integrates with Together AI — LiteLLM docs have a Together AI provider page.
- Together AI integrates with LiteLLM — Together AI docs third-party/agent integrations: LiteLLM (incl. Claude Code on Together via LiteLLM proxy).
Cost & capability
| LiteLLM | Together AI | |
|---|---|---|
| Cost tier | searched not found | mid |
| $/Mtok input | searched not found | — |
| $/Mtok output | searched not found | — |
Where they differ (11)
Rows where both sides have data and the values disagree — the shortlist of dimensions that actually distinguish these two systems.
| LiteLLM | Together AI | |
|---|---|---|
| Cost tier | searched not found | mid |
| Type | Universal LLM API + Proxy | Inference + fine-tuning cloud |
| Created | 2023 | 2022 |
| Latest release | v1.106.4 (2026-10-25) | v3.0.0 (2026-10-22) — together (Python SDK) |
| License | MIT (except enterprise/ directory, commercial license) | proprietary; Python SDK Apache-2.0 |
| GitHub | BerriAI/litellm — ~62.1k stars, last commit 2026-10 | searched not found |
| Pricing | OSS free; Enterprise custom pricing (30-day self-hosted trial key) | Serverless pay-per-token (e.g. $0.15–$3.00 per 1M input tokens); dedicated endpoints per GPU-hour (H100 $5.49/hr); fine-tuning per 1M training tokens; GPU clusters from $3.19–$3.99 per H100-hour |
| Funding | BerriAI raised $1.6M seed 2023 (Y Combinator W23); commercial steward of LiteLLM OSS. | $800M Series C 2026-07-01 (Aramco Ventures, NVIDIA, Vista Equity, General Catalyst, Salesforce Ventures and others); earlier rounds: $20M seed, $102.5M Series A, $305M Series B at $3.3B valuation |
| Deployment | Self-hosted only — SDK and proxy; Enterprise self-hosted or air-gapped | Managed-only — serverless and dedicated inference, fine-tuning, GPU clusters |
| API surface | Python SDK, OpenAI-compatible proxy REST API | searched not found |
| MCP | yes — MCP Gateway in LiteLLM Proxy (Streamable HTTP, SSE, stdio) with per-key/team access control | searched not found |
At a glance
| LiteLLM | Together AI | |
|---|---|---|
| Section | Inference platforms & gateways | Inference platforms & gateways |
| Tier | T1 | T1 |
| Type | Universal LLM API + Proxy | Inference + fine-tuning cloud |
| Created | 2023 | 2022 |
| Latest release | v1.106.4 (2026-10-25) | v3.0.0 (2026-10-22) — together (Python SDK) |
| License | MIT (except enterprise/ directory, commercial license) | proprietary; Python SDK Apache-2.0 |
| GitHub | BerriAI/litellm — ~62.1k stars, last commit 2026-10 | searched not found |
| Pricing | OSS free; Enterprise custom pricing (30-day self-hosted trial key) | Serverless pay-per-token (e.g. $0.15–$3.00 per 1M input tokens); dedicated endpoints per GPU-hour (H100 $5.49/hr); fine-tuning per 1M training tokens; GPU clusters from $3.19–$3.99 per H100-hour |
| Funding | BerriAI raised $1.6M seed 2023 (Y Combinator W23); commercial steward of LiteLLM OSS. | $800M Series C 2026-07-01 (Aramco Ventures, NVIDIA, Vista Equity, General Catalyst, Salesforce Ventures and others); earlier rounds: $20M seed, $102.5M Series A, $305M Series B at $3.3B valuation |
| Deployment | Self-hosted only — SDK and proxy; Enterprise self-hosted or air-gapped | Managed-only — serverless and dedicated inference, fine-tuning, GPU clusters |
| API surface | Python SDK, OpenAI-compatible proxy REST API | searched not found |
| Multi-tenancy | searched not found | searched not found |
| MCP | yes — MCP Gateway in LiteLLM Proxy (Streamable HTTP, SSE, stdio) with per-key/team access control | searched not found |
| A2A | searched not found | searched not found |
| OpenTelemetry | searched not found | searched not found |
| Optimised for | searched not found | searched not found |
| Anti-fit | searched not found | searched not found |
Pros & cons
LiteLLM
Pros: searched not found
Cons: searched not found
Together AI
Pros: searched not found
Cons: searched not found