--- title: Inference Pricing | Telnyx canonical: https://telnyx.com/pricing/inference-api --- # Inference Pricing | Telnyx EDGE # Inference Pricing OpenAI-compatible LLMs on owned GPUs. Per token, per model. Open-source models catching up with frontier at a fraction of the cost, with zero egress to storage and inference. [SIGN UP FOR FREE](https://telnyx.com/sign-up)[GET VOLUME RATE](https://telnyx.com/contact-us) ADJUST SETTINGS Input tokens 01 T Cached tokens 0100% Output tokens 01 T LLM GLM 5.3 Flash on Telnyx GPUs ESTIMATED COST $71Per month Input tokens200M × $0.135 / 1M $27.00 Cached input tokens800M × $0.027 / 1M $21.60 Output tokens50M × $0.45 / 1M $22.50 [SIGN UP FOR FREE](https://telnyx.com/sign-up)[GET VOLUME-BASED RATE](https://telnyx.com/contact-us) Published rates, pay as you go, before volume tiers. Caching means large prompts cost far less than list rate; actual billing is per token at the rates in the table below, with no prompt-size multipliers and no minimums. Rates ## What's on the card. Each row is a line on your invoice. Nothing is bundled into another primitive's rate and nothing turns on unless you call it. ### Chat completions pricing (per 1M tokens) FlexDefaultPriority ### Chat completions pricing (per 1M tokens) | Model | Price | | ------------------------------------------------------ | ----------------------------------------------------------------------------------- | | DeepSeek V4.1 Flash — Low-latency multimodal inference | Input: $0.150 / 1M tokensCached Input: $0.003 / 1M tokensOutput: $0.600 / 1M tokens | ### Chat completions pricing (per 1M tokens) | Model | Price | | --------------------------------------------------------- | ------------------------------------------------------------------------------------ | | GLM-5.3 — Flagship frontier intelligence | Input: $1.250 / 1M tokensCached Input: $0.240 / 1M tokensOutput: $4.000 / 1M tokens | | GLM-5.3 Flash — Fast, efficient inference | Input: $0.135 / 1M tokensCached Input: $0.027 / 1M tokensOutput: $0.450 / 1M tokens | | DeepSeek V4.1 Flash — Low-latency multimodal inference | Input: $0.300 / 1M tokensCached Input: $0.006 / 1M tokensOutput: $1.200 / 1M tokens | | Kimi K3 — Multimodal intelligence, 1M context | Input: $2.700 / 1M tokensCached Input: $0.270 / 1M tokensOutput: $13.500 / 1M tokens | | Kimi K2.6 — Highest intelligence, voice AI | Input: $0.665 / 1M tokensCached Input: $0.080 / 1M tokensOutput: $4.000 / 1M tokens | | GLM-5.2 — Next-gen efficient reasoning | Input: $1.000 / 1M tokensCached Input: $0.200 / 1M tokensOutput: $4.000 / 1M tokens | | MiniMax-M3 — Cheapest while maintaining high intelligence | Input: $0.270 / 1M tokensCached Input: $0.080 / 1M tokensOutput: $1.100 / 1M tokens | | DeepSeek V4 Flash — Ultra-fast, cost-efficient inference | Input: $0.130 / 1M tokensCached Input: $0.030 / 1M tokensOutput: $0.260 / 1M tokens | | Qwen 3.8 27B — Lightweight open-weight reasoning | Input: $0.400 / 1M tokensCached Input: $0.050 / 1M tokensOutput: $3.000 / 1M tokens | | Gemma 4 26B A4B — Efficient open-weight MoE inference | Input: $0.130 / 1M tokensCached Input: $0.050 / 1M tokensOutput: $0.400 / 1M tokens | ### Chat completions pricing (per 1M tokens) | Model | Price | | ------------------------------------------ | ----------------------------------------------------------------------------------- | | GLM-5.3 Flash — Fast, efficient inference | Input: $1.350 / 1M tokensCached Input: $0.270 / 1M tokensOutput: $4.500 / 1M tokens | | Kimi K2.6 — Highest intelligence, voice AI | Input: $1.330 / 1M tokensCached Input: $0.160 / 1M tokensOutput: $8.000 / 1M tokens | | GLM-5.2 — Next-gen efficient reasoning | Input: $2.000 / 1M tokensCached Input: $0.400 / 1M tokensOutput: $8.000 / 1M tokens | | Gemma 4 31B — Dense open-weight inference | Input: $0.320 / 1M tokensCached Input: $0.160 / 1M tokensOutput: $1.200 / 1M tokens | ### Decision model pricing (per 1M tokens) | Model | Price | | --------------------- | ----------------------------------------- | | telnyx/decision-flash | Input: $0.035 / 1M tokensOutput: INCLUDED | | telnyx/decision-pro | Input: $0.200 / 1M tokensOutput: INCLUDED | ### Other services | Service | Price | | -------------------------------- | ------------------- | | Embeddings (gte-large) | $0.0001 / 1K tokens | | Speech to text | $0.003 / minute | | AI-enabled storage and retrieval | $0.02 / GB / day | Machine readable: GET /v2/public/pricing. Rates may vary by destination and volume tier. Machine readable: GET /v2/public/pricing?primitive=inference. VOLUME ## Commit more, pay less per unit. Nothing is gated. PAY AS YOU GO $0 Standard rates. Card on file. Automatic tier discounts as usage crosses thresholds, no contract needed. [START BUILDING](https://telnyx.com/sign-up) VOLUME RATE Custom Committed volume on this product, priced on your forecast. Share the numbers and get a rate, no plan required. [GET A VOLUME RATE](https://telnyx.com/contact-us) ENTERPRISE $5,000/ mo Monthly minimum spend. Dedicated infrastructure and IPs, private interconnect, in region GPUs, unlimited rate limits. [CONTACT SALES](https://telnyx.com/contact-us) Usually bought with ## What people add next. See the whole composition on private ai deployment ↗ * [Embeddingsgte large on owned GPUs, colocated with object storage for RAG with no egress..$0.0001 / 1K TOK · RATES ↗](https://telnyx.com/pricing/embeddings) * [Object StorageS3 compatible storage in the same buildings as the GPUs and the media plane.$0.006 / GB/MO · RATES ↗](https://telnyx.com/pricing/storage) * [CloudFSPOSIX mount over object storage, so recordings and model files are files.CUSTOM · RATES ↗](https://telnyx.com/pricing/cloudfs) * [SQLDBManaged SQL colocated with functions and actors.BETA · RATES ↗](https://telnyx.com/pricing/sqldb) ## Live in five minutes. No sales gate in front of the API. Card on file, provisioned by API. When you want a human, they run the network and pick up 24/7. [SIGN UP FOR FREE](https://telnyx.com/sign-up)[TALK TO SALES](https://telnyx.com/contact-us) [Start building](https://telnyx.com/sign-up) ### Ask AI * [![GPT](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/chatgpt_icon-ea55e09d.jpeg?width=92&format=webp)](https://chat.openai.com/?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Claude](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/claude_icon-c7c8eef3.webp?width=92&format=webp)](https://claude.ai/new?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Perplexity](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/perplexity_icon-cd5b74f1.webp?width=92&format=webp)](https://www.perplexity.ai/search?q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Gemini](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/gemini_icon-4ff1cbf4.webp?width=92&format=webp)](https://www.google.com/search?udm=50&aep=11&q=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.) * [![Grok](https://d2efw2akbx8gaf.cloudfront.net/https://dotcom-payload-assets-prod.s3.us-east-1.amazonaws.com/cms-media/grok_icon-e588e5bd.webp?width=92&format=webp)](https://x.com/i/grok?text=What makes Telnyx's global network different, breakdown call quality for normal phone calls and voice AI calls.)