Infercom vs Together AI: Token Pricing, Speed & Intelligence

Full comparison of Infercom and Together AI — live token pricing, latency, throughput, context window, strengths, weaknesses, and best use cases. Rates sourced from public APIs — verify before use.

Infercom

EU inference on SambaNova chips — Gemma 4, gpt-oss-120b, Whisper, embeddings

Infercom is an EU-based inference provider running on SambaNova RDU chips, offering Gemma 4 31B, gpt-oss-120b, Whisper Large v3, and E5-Mistral embeddings. Prices are in EUR per 1M tokens, excl. VAT, on a PAYG basis. Suited for European workloads requiring EU infrastructure without the overhead of a sovereign gateway.

EU inferenceEmbeddingsTranscriptionCost-sensitive workloads

Open-weight hostHosts open weights

Together AI

MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro, gpt-oss-120B — plus GB200/B200 GPU clusters

Together AI offers hosted inference for open-weight models, GPU clusters, provisioned throughput and fine-tuning. Compare listed rates and check the provider for current models, availability and terms.

Open-sourceFine-tuningCodingChatCost-efficiencyModel varietyGPU compute

Open-weight hostHosts open weights

Key metric comparison

Cheapest input ($/1M)

—

Cheapest output ($/1M)

—

Peak throughput

—

Best latency (TTFT)

—

Intelligence score

—

Context window

—

Live token pricing

Strengths and weaknesses

Infercom

EU-based infrastructure on SambaNova RDU chips

Competitive EUR pricing on Gemma 4 31B and gpt-oss-120b

Covers multiple modalities: chat, speech-to-text, embeddings

PAYG — no minimum spend

EUR pricing excluded from USD cross-provider comparisons

Small model catalog

Newer provider — limited ecosystem integrations

Together AI

Open-model catalog — MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro, gpt-oss-120B, Qwen3.x, Llama 4

GB200/B200/H200/H100 GPU clusters with preemptible and reserved pricing

Provisioned Throughput (PTUs) for SLA-backed capacity

Serverless Training API for fine-tuning without infrastructure

Fine-tuning for Llama 4, Qwen3.5, DeepSeek, GLM, and more

OpenAI-compatible API — easy migration

No proprietary frontier models

Throughput lower than Groq/Cerebras for speed-critical apps

Fine-tuning adds complexity vs. pure inference providers

Key differentiators

Infercom

EU inference on SambaNova chips covering chat, speech-to-text, and embeddings at competitive EUR rates.

Together AI

An open-weight model catalog — MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro, gpt-oss-120B — with GPU clusters (GB200/B200), Provisioned Throughput, and a Serverless Training API.

Frequently asked questions

Infercom FAQs

What is Infercom?

Infercom is an EU-based inference provider running on SambaNova RDU chips. It offers Gemma 4 31B, gpt-oss-120b, Whisper Large v3, and E5-Mistral embeddings at PAYG EUR rates. See infercom.ai/pricing for current rates.

Does Infercom offer embeddings?

Yes. Infercom offers E5-Mistral embeddings at EUR 0.13 per 1M input tokens.

Together AI FAQs

What new models did Together AI add in 2026?

Together AI expanded its catalog with MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro 0813, gpt-oss-120B, Muse Glimmer 30B, and the full Qwen3.x family. Check api.together.ai/models for current pricing.

How much does Together AI cost?

Together AI uses per-token pricing across its model catalog. Check api.together.ai/models for current rates on MiniMax M3, DeepSeek V4 Pro, GLM-5.3, Llama 3.3 70B, and other models.

Does Together AI offer GPU compute?

Yes. Together AI offers GPU clusters with H100, H200, B200, and GB200/GB300 NVL72 (contact sales). Check together.ai/pricing for current GPU compute rates.

Provider resources

Infercom

Provider page

Website

Pricing

Together AI

Provider page

Website

Pricing Docs

Infercom — EU inference on SambaNova chips — Gemma 4, gpt-oss-120b, Whisper, embeddings

EU inference on SambaNova chips covering chat, speech-to-text, and embeddings at competitive EUR rates.

Together AI — MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro, gpt-oss-120B — plus GB200/B200 GPU clusters

An open-weight model catalog — MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro, gpt-oss-120B — with GPU clusters (GB200/B200), Provisioned Throughput, and a Serverless Training API.

Key strengths compared

Infercom

EU-based infrastructure on SambaNova RDU chips
Competitive EUR pricing on Gemma 4 31B and gpt-oss-120b
Covers multiple modalities: chat, speech-to-text, embeddings

EUR pricing excluded from USD cross-provider comparisons
Small model catalog

Together AI

Open-model catalog — MiniMax M3, Kimi K3, GLM-5.3, DeepSeek V4 Pro, gpt-oss-120B, Qwen3.x, Llama 4
GB200/B200/H200/H100 GPU clusters with preemptible and reserved pricing
Provisioned Throughput (PTUs) for SLA-backed capacity

No proprietary frontier models
Throughput lower than Groq/Cerebras for speed-critical apps

Key weaknesses compared

Infercom

EUR pricing excluded from USD cross-provider comparisons
Small model catalog
Newer provider — limited ecosystem integrations

Together AI

No proprietary frontier models
Throughput lower than Groq/Cerebras for speed-critical apps
Fine-tuning adds complexity vs. pure inference providers

Provider category context

Infercom is a inference api, founded in 2024. Together AI is a inference api, founded in 2022. Both are inference api providers — the comparison is primarily about pricing, model selection, and feature differentiation within the same tier.

How to choose between them

Both Infercom and Together AI host open-weight models. The key differentiators are latency, throughput, and which specific model versions each provider offers. Check the speed metrics above — inference API providers often differ significantly on tokens-per-second for the same model. Pricing is typically competitive between them; availability of specific model versions (e.g., Llama 3.1 405B, DeepSeek V3) may be the deciding factor.