Telnyx x402 Gateway

Pay per request for Telnyx Inference and Audio.

OpenAI-compatible chat completions via Telnyx Inference. One endpoint, 13 open-weight models, pay-per-request in USDC. Plus OpenAI-compatible audio: text-to-speech (4,000+ voices) and speech-to-text (Whisper), metered at Telnyx list rates. Agents can call the endpoint with a wallet only: no Telnyx account, no API key, and no subscription.

Quickstart View all 13 models Audio: TTS & STT
Endpoint POST /v1/chat/completions
Price $0.002–$0.150193 USDC per call
Models 13 open-weight models (select via body.model)
Payment x402 exact + upto on Base mainnet (eip155:8453)
Audio TTS $0.000006/char · STT $0.003/min (details)

Quickstart

Send an unsigned request to receive the PAYMENT-REQUIRED challenge, then retry with a signed PAYMENT-SIGNATURE header using an x402 client. Use GET /v1/models to discover model ids; price varies by selected model.

curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"MiniMaxAI/MiniMax-M2.7","messages":[{"role":"user","content":"Say hello in one short sentence."}],"max_tokens":64}'

# Discover available models (no payment):
curl https://x402.telnyx.com/v1/models

Payment schemes: exact, upto — upto supports EIP-2612 sponsored approval on USDC.

Available models (13)

Each tier offers two payment schemes: exact (flat per-call price with tight usage limits — predictable, for light to medium usage) and upto (per-token metered pricing at Telnyx list rates, up to the model's full context + output capabilities — for any usage size). For requests within exact's limits, upto never costs more than exact; for larger requests only available via upto, you pay per-token up to the spending cap. Pick a model, set body.model, and copy the curl snippet.

MiniMaxAI/MiniMax-M2.7 frontier
Exact price
$0.002856 per call
Upto ceiling
$0.024892 max (per-token)
Context (exact / upto)
8,000 / 66,666 tokens
Max output (exact / upto)
512 / 8,192 tokens
Per-message (exact / upto)
8,000 / 200,000 chars
sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"MiniMaxAI/MiniMax-M2.7","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
moonshotai/Kimi-K2.6 mid
Exact price
$0.01385 per call
Upto ceiling
$0.079376 max (per-token)
Context (exact / upto)
12,000 / 66,666 tokens
Max output (exact / upto)
1,024 / 8,192 tokens
Per-message (exact / upto)
12,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"moonshotai/Kimi-K2.6","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
zai-org/GLM-5.1-FP8 reasoning
Exact price
$0.023386 per call
Upto ceiling
$0.104493 max (per-token)
Context (exact / upto)
12,000 / 66,666 tokens
Max output (exact / upto)
2,048 / 8,192 tokens
Per-message (exact / upto)
12,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"zai-org/GLM-5.1-FP8","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
moonshotai/Kimi-K2.6-long long-context
Exact price
$0.0543 per call
Upto ceiling
$0.079376 max (per-token)
Context (exact / upto)
66,666 / 66,666 tokens
Max output (exact / upto)
2,048 / 8,192 tokens
Per-message (exact / upto)
200,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"moonshotai/Kimi-K2.6-long","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
google/gemma-2b-it small
Exact price
$0.002 per call
Context
2,000 tokens
Max output
256 tokens
Per-message
2,000 chars
exact
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"google/gemma-2b-it","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
meta-llama/Meta-Llama-3.1-8B-Instruct small
Exact price
$0.002237 per call
Upto ceiling
$0.015187 max (per-token)
Context (exact / upto)
8,000 / 66,666 tokens
Max output (exact / upto)
512 / 4,096 tokens
Per-message (exact / upto)
8,000 / 200,000 chars
sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"meta-llama/Meta-Llama-3.1-8B-Instruct","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
meta-llama/Llama-3.3-70B-Instruct large
Exact price
$0.007016 per call
Upto ceiling
$0.044559 max (per-token)
Context (exact / upto)
8,000 / 66,666 tokens
Max output (exact / upto)
1,024 / 4,096 tokens
Per-message (exact / upto)
8,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"meta-llama/Llama-3.3-70B-Instruct","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
meta-llama/Meta-Llama-3.1-70B-Instruct large
Exact price
$0.007016 per call
Upto ceiling
$0.044559 max (per-token)
Context (exact / upto)
8,000 / 66,666 tokens
Max output (exact / upto)
1,024 / 4,096 tokens
Per-message (exact / upto)
8,000 / 200,000 chars
sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"meta-llama/Meta-Llama-3.1-70B-Instruct","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
MiniMaxAI/MiniMax-M3-MXFP8 frontier
Exact price
$0.011974 per call
Upto ceiling
$0.028233 max (per-token)
Context (exact / upto)
33,333 / 66,666 tokens
Max output (exact / upto)
2,048 / 8,192 tokens
Per-message (exact / upto)
32,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"MiniMaxAI/MiniMax-M3-MXFP8","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
moonshotai/Kimi-K2.5 mid
Exact price
$0.016673 per call
Upto ceiling
$0.066677 max (per-token)
Context (exact / upto)
20,000 / 66,666 tokens
Max output (exact / upto)
1,024 / 8,192 tokens
Per-message (exact / upto)
20,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"moonshotai/Kimi-K2.5","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
Qwen/Qwen3-235B-A22B reasoning
Exact price
$0.010497 per call
Upto ceiling
$0.058485 max (per-token)
Context (exact / upto)
8,000 / 66,666 tokens
Max output (exact / upto)
2,048 / 8,192 tokens
Per-message (exact / upto)
8,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"Qwen/Qwen3-235B-A22B","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
zai-org/GLM-5.2 reasoning
Exact price
$0.037526 per call
Upto ceiling
$0.102602 max (per-token)
Context (exact / upto)
26,666 / 66,666 tokens
Max output (exact / upto)
2,048 / 8,192 tokens
Per-message (exact / upto)
32,000 / 200,000 chars
sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"zai-org/GLM-5.2","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'
moonshotai/Kimi-K3 frontier
Exact price
$0.150193 per call
Upto ceiling
$0.408886 max (per-token)
Context (exact / upto)
12,000 / 66,666 tokens
Max output (exact / upto)
8,192 / 16,384 tokens
Per-message (exact / upto)
12,000 / 200,000 chars
cached credit · sponsored approval · exact + upto
curl -i -X POST https://x402.telnyx.com/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"model":"moonshotai/Kimi-K3","messages":[{"role":"user","content":"hi"}],"max_tokens":64}'

Audio: text-to-speech & speech-to-text

OpenAI-compatible audio endpoints at Telnyx list rates, zero margin — the same x402 payment flow as inference: exact flat per-call, or upto metered (per character for TTS, per second for STT).

Unsigned, these curls return 402 with the payment offer in the base64 payment-required response header (x402 v2 — the body is just {}). Pay by retrying with a signed PAYMENT-SIGNATURE header via an x402 client; a paid TTS call then returns raw mp3 bytes (save them with curl -o).

POST /v1/audio/speech text-to-speech
Metered (upto)
$0.000006 per character ($0.002 minimum settle per call)
Exact price
$0.018 per call
Input cap
3,000 characters
Voices
4,000+ across 9 providers — free catalog at GET /v1/audio/voices (OpenAI voice names like alloy work too)
Output
mp3
curl -i -X POST https://x402.telnyx.com/v1/audio/speech \
  -H 'Content-Type: application/json' \
  -d '{"input":"Hello from Telnyx.","voice":"alloy"}'
POST /v1/audio/transcriptions speech-to-text
Metered (upto)
$0.003 per minute, metered per second ($0.002 minimum settle ≈ 40s)
Exact price
$0.015 per call
Model
Whisper large-v3-turbo (model=whisper-1 accepted), 100 languages
Upload cap
wav/mp3, up to 5 min / 12 MB (multipart)
Response
json or verbose_json (segment timestamps + duration)
curl -i -X POST https://x402.telnyx.com/v1/audio/transcriptions \
  -F [email protected] \
  -F model=whisper-1