Baseten Model APIs

LLM 6.7/10

Open models (DeepSeek, Llama, Qwen) billed per million tokens with cached-input discounts; deploy behind dedicated endpoints in seconds

Baseten Model APIs scores 6.7/10 for free value in LLM. The main constraint: Paid — Pay-per-million-tokens. Open models (DeepSeek, Llama, Qwen) billed per million tokens with cached-input discounts; deploy behind dedicated endpoints in seconds.

Category LLM Kind Paid plan

Free value score

6.7 / 10

Show the math

Model Quality 8/10

value = 44 artificial_analysis_score

weighted score = 0.2 * 8/10

Access 10/10

value = 10/10

weighted score = 0.1 * 10/10

Price Efficiency 5.8/10

value = 2380952 tok/$

weighted score = 0.7 * 5.8/10

Key metrics

DeepSeek 44 Best model

$0.42/M Price

What you get

Paid — Pay-per-million-tokens. Open models (DeepSeek, Llama, Qwen) billed per million tokens with cached-input discounts; deploy behind dedicated endpoints in seconds

Per-token open-model rates competitive with DeepInfra/Together; cached input cheaper

Gotchas

No gotchas documented yet. Contribute one if you know a constraint we missed.

Sources

"Model APIs bill per million tokens. For current per-model rates, see the Model APIs pricing page. Cached input tokens are prompt tokens served from the KV cache"
https://docs.baseten.co/inference/model-apis/overview
"Baseten (FP8) is listed at $0.42 per 1M tokens for DeepSeek V3.1 (blended price)."
https://artificialanalysis.ai/models/deepseek-v3-1/providers
"In reasoning mode, DeepSeek V3.2 scores 66 on the Artificial Analysis Intelligence Index"
https://www.linkedin.com/pulse/deepseek-v32-2-most-intelligent-open-weights-model-qnwoc

paid value llm-providers

Open service ← All LLM

Alternatives

Same category · similar quota

ZenMux Pay-As-You-Go APIZenMux Pay-As-You-Go API · paid · Paid plan

6.6

Cheapest GLM 5.2 API verified (Jul 2026): $0.43/M input, $1.35/M output, $0.08/M cache read, 1M context; Kimi K2.7 Code $0.43/$1.79 (+HighSpeed tier); OpenAI- AND Anthropic-compatible gateway, no rate/concurrency limits, production allowed

1.5M/$51.1 AA1.5M/$

May be outdatedChecked 23d ago

Best valuePaid onlyMetered

Fireworks AI BatchFireworks AI Batch · paid · Paid plan

6.5

Batch inference billed at 50% of serverless on both input and output across the open catalog

2×44.3 AA2.0×

May be outdatedChecked 26d ago

Paid onlyEmbeddings

Together AI Batch APITogether AI Batch API · paid · Paid plan

6.5

Batch inference at half serverless price; DeepSeek V4 Pro listed at $0.20 batch vs $1.74 serverless

2×44.3 AA2.0×

May be outdatedChecked 26d ago

Paid onlyEmbeddings