Skip to main content

Getting Started > Models

MODEL ACCESS BY PLAN

See which models each plan tier can call. Free plan includes 15 models across LLM, STT, TTS, and Image.

Overview

Not all models are available on every plan. The free tier includes 17 models; paid plans (Starter, Pro, Enterprise) unlock all models.

Use the /api/v1/models/access endpoint to programmatically check which models your plan can call.

Endpoint

GET /api/v1/models/access — No authentication required.

curl https://api.callmissed.com/api/v1/models/access

Response shape:

json
{
  "plans": {
    "free": {
      "models": ["sarvam-30b", "sarvam-105b", "kimi-k2.5", "..."],
      "by_category": {
        "llm": ["auto", "sarvam-30b", "sarvam-105b", "kimi-k2.5", "kimi-k2.6", "glm-4.7-flash", "gpt-oss-120b", "nemotron-3-super", "gemma-4-26b-a4b-it", "mistral-small-3.1"],
        "stt": ["saaras:v3", "whisper-large-v3-turbo", "nova-3"],
        "tts": ["bulbul:v3", "aura-2-en", "aura-2-es", "melotts"],
        "image": ["flux-2-klein-9b", "flux-2-dev", "lucid-origin", "phoenix-1.0", "sdxl-lightning", "dreamshaper-8-lcm"]
      },
      "restriction": "Only the models listed here are callable on the free plan."
    },
    "starter": {
      "models": ["...all models..."],
      "by_category": { "llm": [...], "stt": [...], "tts": [...], "image": [...] },
      "restriction": "All models callable. Per-service monthly call limits apply."
    },
    "pro": { "..." : "..." },
    "enterprise": { "..." : "..." }
  }
}

Free Plan Models

The free plan includes 23 models. Source of truth: FREE_TIER_MODELS in backend/app/api/v1/services.py.

LLM (10):

Model IDDescription
autoFree auto-router — picks a free model per request
sarvam-30b30B MoE, 64K context — real-time chat, Indic languages
sarvam-105b105B MoE, 128K context — complex reasoning
kimi-k2.5Moonshot 1T MoE, 256K context — coding, math
kimi-k2.6Moonshot K2.6 — improved reasoning + coding, 256K context
glm-4.7-flashZ.ai bilingual, 128K context — fast, tool use
gpt-oss-120bOpenAI open-weight 120B MoE — reasoning-grade
nemotron-3-superNVIDIA 120B MoE — long-context enterprise
gemma-4-26b-a4b-itGoogle 26B MoE — efficient chat + code
mistral-small-3.1Mistral 24B Instruct, 128K context — fast, tool use

STT (3):

Model IDDescription
saaras:v323 langs (22 Indic + English), best for code-mixed
whisper-large-v3-turboWhisper — 99 langs with auto-detect, transcribe + translate
nova-3Nova 3 — 11 langs, diarize, smart-format, streaming

TTS (4):

Model IDDescription
bulbul:v339 voices, 11 Indian languages
aura-2-enAura 2 — 39 English voices, low-latency streaming
aura-2-esAura 2 — 10 Spanish voices, low-latency streaming
melottsMeloTTS — en + fr, cheapest TTS available

Image (6):

Model IDDescription
flux-2-klein-9bFlux 2 Klein 9B — high-quality text-to-image
flux-2-devFlux 2 Dev — higher fidelity, 50-step
lucid-originLucid Origin — cinematic compositions
phoenix-1.0Phoenix 1.0 — photorealistic portraits
sdxl-lightningSDXL Lightning — fastest, 4-step inference
dreamshaper-8-lcmDreamShaper 8 LCM — stylised illustrations

Starter, Pro, and Enterprise plans unlock all models. The only difference between paid tiers is per-service monthly call limits (see Credits & Rate Limits).

Paid-only models include: kimi-k2.5-fast (currently under maintenance), openai/gpt-5.4, openai/gpt-5.4-mini, openai/gpt-5.4-pro, openai/gpt-5.4-nano, anthropic/claude-opus-4.6, anthropic/claude-sonnet-4.6, google/gemini-3.1-pro-preview, google/gemini-3-flash-preview, google/gemini-3.1-flash-lite, google/gemini-3.1-flash-lite, x-ai/grok-4.20, qwen/qwen3.5-plus, qwen/qwen3.5-flash, and mistralai/mistral-small-2603. Note: the free-tier auto-router is exposed as auto (not openrouter/auto) and IS available on the free plan.

Error Handling

When a free-plan user calls a paid-only model, the API returns:

json
{
  "error": {
    "message": "Model 'openai/gpt-5.4' requires a paid plan. See GET /api/v1/models/access for the full list of free-plan models. Upgrade at https://app.callmissed.com/pricing",
    "type": "invalid_request_error",
    "code": "model_not_available"
  }
}

HTTP status: 403. Check the code field for model_not_available to handle this programmatically.

Was this page helpful?