Baseten vs Together AI
What the benchmark found. Baseten had the lower end-to-end p99 latency at 3.23 seconds. Together AI had the higher task success rate at 98.5%. Both figures come from 600 submitted requests per provider. Measured across 10 LLM inference providers serving GLM 5.3 Flash, 600 requests each, Sep 3, 2026.
Providers measured. Baseten, DeepInfra, Fireworks AI, Modal, Nebius, Novita AI, Parasail, Telnyx, Together AI, and Z.AI, each serving GLM 5.3 Flash behind an OpenAI-compatible chat-completions endpoint.
What this page compares. Baseten and Together AI are compared as delivery layers for the same GLM model. Completion latency, first visible answer, tokens per second, task success, and failures are calculated from their shared 600-question schedule.
How to read the result. Both providers received identical selected items in the same temporal rounds. Each axis below is computed independently; the faster complete response is not automatically the more accurate or reliable API.
Workload and configuration. Every provider received the same 600 deliberately easy structured tasks: 200 meeting-note lookups, 200 ticket-triage classifications, and 200 contract-term extractions. GLM 5.3 Flash ran with streaming enabled, reasoning low, temperature 0, top-p 1, a 256-token output ceiling, one attempt, a 20-second timeout, and per-provider concurrency one.
APIs used. The runner called each provider's OpenAI-compatible chat-completions surface with the model identifiers below; the links open the provider documentation used to verify each adapter.
- Baseten:
zai-org/GLM-5.3-Flash· API docs ↗ - Together AI:
zai-org/GLM-5.3-Flash· API docs ↗
Baseten vs Together AI: which is faster, and which is more accurate?
Lower wins for latency and failure rate; higher wins for tokens per second and task success. The gap is shown in the native unit of each metric.
| Metric | Baseten | Together AI | Measured leader | Absolute gap |
|---|---|---|---|---|
| End-to-end p99 | 3.23 s | 12.4 s | Baseten | 9221 ms |
| End-to-end p95 | 2.29 s | 3.66 s | Baseten | 1377 ms |
| Time to first token p95 | 1.16 s | 2.26 s | Baseten | 1099 ms |
| Tokens per second p50 | 240.5 tok/s | 151.6 tok/s | Baseten | 88.8 tok/s |
| Tokens per second p95 | 61.6 tok/s | 34.0 tok/s | Baseten | 27.6 tok/s |
| Task success | 95.8% | 98.5% | Together AI | 2.7 pp |
| Failure rate | 0.0% | 1.0% | Baseten | 1.0 pp |
Provider by provider, in the order above
- Baseten: 331 ms median, 3.23 seconds end-to-end p99, time to first token p95 1.16 seconds, 240.5 tokens per second, 95.8% task success, 0.0% failures.
- Together AI: 609 ms median, 12.45 seconds end-to-end p99, time to first token p95 2.26 seconds, 151.6 tokens per second, 98.5% task success, 1.0% failures.
Where should I compare Baseten with Together AI?
- Agent tool-result generation. Start with task success, then compare end-to-end p95 and p99 because downstream code waits for the complete structured result.
- Live ticket classification. Compare time to first token p95 for response start and tokens per second p95 for the slow throughput tail.
- Meeting-note answer lookup. Use end-to-end p99 with failure rate when this model call sits directly on a user-visible critical path.
How is LLM inference provider latency and accuracy measured here?
- Same model. Every endpoint serves GLM 5.3 Flash; the provider layer is the only variable.
- Same request. One-turn, non-tool chat completion in JSON-object mode, streaming on, temperature 0, top-p 1, reasoning low, 256-token ceiling, 20-second timeout, concurrency one.
- Client clock, pinned tokenizer. Time to first token, end-to-end latency and tokens per second come from the client; visible answer tokens are counted with a pinned
tiktoken o200k_basetokenizer, never provider-reported usage. - Exact task success. An answer counts only when it is schema-valid and exactly correct under the task rubric. Timeouts, HTTP errors and malformed responses stay in the denominator.
- Serverless endpoints only. Dedicated capacity is outside the comparison. Runner and per-request records: openbenchmarks-labs/inference ↗.
Baseten vs Together AI: direct questions
Baseten vs Together AI: which had the lower complete-answer tail?
Baseten had the lower end-to-end p99 latency at 3.23 seconds. Together AI had the higher task success rate at 98.5%. Both figures come from 600 submitted requests per provider.
Did Together AI or Baseten start visible answers sooner?
Baseten had the lower time to first token p95 at 1.16 seconds. The head-to-head table keeps end-to-end tail latency beside it because a fast visible start does not guarantee a fast complete answer.
What should an agent builder inspect beyond the Baseten and Together median?
Beyond median latency, inspect end-to-end p99 for rare long waits, task success for usable structured results, and failure rate for requests that never completed normally.
Same run, other questions
Read the complete LLM inference provider benchmark
Metric definitions, request scheduling, task rubrics, failure handling, and the complete provider scorecard live on the LLM Inference Provider Benchmark →