Getting Started
Credits & Rate Limits
Transparent pricing for all CallMissed services. All LLM models are OpenAI-compatible — just change the model field.
Credits
Every new account receives 1000 free API credits on signup. Credits work across all APIs — STT, TTS, LLM, and bot conversations. Credits never expire. 1 credit = ₹1 ≈ US$0.0104 (US$1 = ₹96).
Sign up freePlans
Free
Free
- 1000 API credits on signup
- All APIs (STT, TTS, LLM, Image, Embeddings)
- 11 LLM models: Kimi K2.5/K2.6/K2.7 Code, Sarvam 105B / 105B Conversations, GLM 4.7/5.2, GPT-OSS 120B, Nemotron 3, Gemma 4, Mistral Small 3.1
- 4 STT models: Saaras v3, Saaras v4, Whisper, Nova-3
- 4 TTS models: Bulbul v3, Aura 2 EN/ES, MeloTTS
- 6 image models: Flux 2, Lucid Origin, Phoenix, SDXL, Dreamshaper
- 2 embedding models: Text Embedding 3 Small / Large
- 100 LLM / 50 STT / 50 TTS calls / mo
- 2 team members
- Community support
Starter
$10/month
+550 credits your first month, then +500 a month
- +550 credits your first month, then +500 a month
- All APIs · 500 req/min
- 5,000 LLM / 2,500 STT / 2,500 TTS calls / mo
- 500 image generations / mo
- 5 team members · 1 GB storage
- Email support
Pro
$52/month
+6,000 credits your first month, then +5,000 a month
- +6,000 credits your first month, then +5,000 a month
- All APIs · 3,000 req/min
- 50,000 LLM / 25,000 STT / 25,000 TTS calls / mo
- 5,000 image generations / mo
- 20 team members · 10 GB storage
- Priority email · Usage analytics · Custom webhooks
Enterprise
$208/month
+26,000 credits your first month, then +20,000 a month
- +26,000 credits your first month, then +20,000 a month
- No monthly call caps (pay-as-you-go from credits)
- Unlimited team members & storage
- Highest rate limit · 10,000 req/min
- Priority support
- Dedicated infrastructure
- Dedicated account manager
- Custom SLA · 99.99% uptime
Voice Agent Plans
One flat rate a minute for listening, the language model and the voice · 30-second minimum per call · phone carriage billed separately · how plans work
| Plan | voice_tier | Per minute |
|---|---|---|
| Standard | t1 | ₹4 |
| Expressive | t2 | ₹5 |
| Best latency | t3 | ₹6 |
Sarvam AI — Speech to Text
POST /v1/audio/transcriptions · 22 Indic languages + English
| Model | Price |
|---|---|
| saaras:v4Free | $0.3125/hr |
| saaras:v3Free | $0.3125/hr |
| whisper-large-v3-turboFree | $0.0625/hr |
| nova-3Free | $0.5208/hr |
| gnani-prisma-v2.5 | $0.2813/hr |
| deepgram-nova-3 | $0.3021/hr |
| deepgram-flux-general-en | $0.4063/hr |
| deepgram-nova-2 | $0.3646/hr |
| ink-whisper | $0.1875/hr |
| ink-2 | $0.5625/hr |
Sarvam AI — Text to Speech
POST /v1/audio/speech · 37 voices · default shubh
| Model | Price |
|---|---|
| sonic-3.6 | $0.5208/10K chars |
| bulbul:v3Free | $0.3125/10K chars |
| aura-2-enFree | $0.4167/10K chars |
| aura-2-esFree | $0.4167/10K chars |
| deepgram-aura-2 | $0.3125/10K chars |
| deepgram-aura-1 | $0.1563/10K chars |
| melottsFree | $0.05208/10K chars |
| gpt-4o-mini-tts | $0.2083/10K chars |
| gnani-timbre-v2.0 | $0.2813/10K chars |
Sarvam AI — Chat Completion
POST /v1/chat/completions · model: sarvam-105b
| Model | Input | Output |
|---|---|---|
| sarvam-105bFree | $0.3646 | $0.3646 |
| sarvam-105b-conversationsFree | $0.3646 | $0.3646 |
Prices per 1M tokens
LLM Models
POST /v1/chat/completions · Direct-routed, first-party, and frontier models. Use the model ID as the model field. Prices per 1M tokens.
| Model ID | Input / 1M | Output / 1M |
|---|---|---|
gpt-4o OpenAI | $2.604 | $10.42 |
gpt-4.1 OpenAI | $2.083 | $8.333 |
gpt-5-mini OpenAI | $0.2604 | $2.083 |
gpt-5.5 OpenAI | $5.208 | $31.25 |
gpt-5.6-sol OpenAI | $5.208 | $31.25 |
gpt-5.6-terra OpenAI | $2.083 | $12.5 |
gpt-5.6-luna OpenAI | $0.2083 | $1.25 |
gpt-6-sol OpenAI | $2.083 | $10.42 |
gpt-6-luna OpenAI | $0.1042 | $0.5208 |
gpt-6.1-sol OpenAI | $2.083 | $10.42 |
kimi-k2.5Free Moonshot | $0.8438 | $4.219 |
kimi-k2.5-fastmaintenance Moonshot | $0.8438 | $4.219 |
kimi-k2.6Free Moonshot | $1.333 | $5.625 |
kimi-k2.7-codeFree Moonshot | $1.333 | $5.625 |
DeepSeek-V4-Pro DeepSeek | $1.375 | $4.125 |
DeepSeek-V4-Flash DeepSeek | $0.4583 | $1.375 |
glm-4.7-flashFree Z.ai | $0.5208 | $2.083 |
glm-5.2Free Z.ai | $1.969 | $6.188 |
glm-5.3 Z.ai | $2.125 | $6.667 |
gpt-oss-120bFree OpenAI | $1.042 | $4.167 |
nemotron-3-superFree NVIDIA | $1.563 | $6.25 |
gemma-4-26b-a4b-itFree Google | $0.4167 | $1.667 |
gemma-4-31b Google | $0.6146 | $1.542 |
gemini-3.8-flash Google | $1.563 | $7.813 |
gemini-3.7-flash Google | $1.563 | $7.813 |
gemini-3.6-flash Google | $1.563 | $7.813 |
gemini-3.5-flash Google | $1.563 | $9.375 |
gemini-3.5-flash-lite Google | $0.3125 | $2.604 |
gemini-3.1-pro-preview Google | $2.083 | $12.5 |
gemini-3.1-flash-lite Google | $0.2604 | $1.563 |
mistral-small-3.1Free Mistral | $0.4896 | $0.7917 |
grok-4.3 xAI | $3.646 | $15.63 |
nova-sonic-2 Amazon | $4.167 | $15.63 |
nova-sonic Amazon | $4.688 | $17.71 |
gpt-realtime OpenAI | $4.167 | $16.67 |
gpt-realtime-mini OpenAI | $0.625 | $2.5 |
gpt-realtime-2 OpenAI | $4.167 | $25 |
gpt-realtime-1.5 OpenAI | $4.167 | $16.67 |
gpt-realtime-2.1 OpenAI | $4.167 | $25 |
gpt-realtime-2.1-mini OpenAI | $0.625 | $2.5 |
gpt-live-1 OpenAI | — | — |
Image Generation
OpenAI-compatible. Call POST /v1/images/generations with a model, prompt, and optional n / size. Flat price per 1024×1024 image.
| Model | Per image |
|---|---|
| flux-2-pro | $0.1042 |
| flux-2-devFree | $0.125 |
| gpt-image-2.5-sunburst | $0.2604 |
| gemini-3.1-flash-lite-image | $0.035 |
| gpt-image-2.5-flare | $0.2604 |
| gpt-image-2 | $0.2604 |
| gpt-image-1.5 | $0.2604 |
| flux-2-klein-9bFree | $0.1042 |
| flux-1.1-pro | $0.05208 |
| nano-banana-2 | $0.06979 |
| nano-banana-pro | $0.1396 |
| lucid-originFree | $0.08333 |
| phoenix-1.0Free | $0.1042 |
| sdxl-lightningFree | $0.04167 |
| dreamshaper-8-lcmFree | $0.04167 |
Send email from your own domain. ₹30 per 1,000 emails, charged from your credit balance.
| Model | Price |
|---|---|
| Email send | $0.3125/1K emails |
Monthly Limits by Plan
| Resource | Free | Starter | Pro | Enterprise |
|---|---|---|---|---|
| LLM calls / mo | 100 | 5,000 | 50,000 | No cap |
| STT calls / mo | 50 | 2,500 | 25,000 | No cap |
| TTS calls / mo | 50 | 2,500 | 25,000 | No cap |
| Image generations / mo | 50 | 500 | 5,000 | No cap |
| Conversations / mo | 50 | 1,000 | 10,000 | No cap |
| Storage | 100 MB | 1 GB | 10 GB | Unlimited |
| Team members | 2 | 5 | 20 | Unlimited |
Limits are per tenant; all API keys share the same monthly pool. Each plan also has a default per-key request rate: Free 60 · Starter 500 · Pro 3,000 · Enterprise 10,000 req/min (override per key).
“No cap” means Enterprise has no monthly call quota — usage is pay-as-you-go, metered from your credit balance at the same per-model rates as every other plan. Need more than Enterprise? Talk to sales for a custom volume deal.
Error Codes
| Code | Meaning | Action |
|---|---|---|
| 429 | Rate limit exceeded | Retry with exponential backoff |
| 402 | Credits exhausted | Add credits from dashboard |
| 503 | Service overloaded | Retry after 1–2 seconds |
| 401 | Invalid API key | Check your cm_ key |
Need a custom plan?
Volume discounts, dedicated infrastructure, custom SLAs, and white-glove onboarding.