Find the best LLM API deal today
Compare price, free tiers, quotas, reliability and implementation-ready configs from live DealsForge data.
Loaded
13
Hot
10
Free
5
No CC
5
Shortlist first, audit only when there is a real stack
Turn a deal shortlist into a safer agent routing decision.
Free tiers and cheap tokens help, but production cost usually comes from context replay, retries and fallback logic. Use the route map before moving traffic.
Start with the 4-line brief
No keys, no repo access. A rough paragraph is fine; we just need enough context to decide whether the 100 EUR audit has a practical route to test.
1. providers/models: 2. rough monthly spend or token volume: 3. workflow type: 4. one expensive session or failure loop:
13 of 13 deals(cached — live data loading)
Verified by default. Use All or Review for pending source checks.
DeepInfra — Mixtral 8x22B
Open source
Price
$1.09
Quota
60/min
Card
CC req
DeepInfra—Mixtral 8x22B
Open source
Google AI Studio — Gemini 2.5 Pro
Long ctx · Enterprise · OpenAI compat
Price
Free
Quota
50/min
Card
No CC
Google AI Studio—Gemini 2.5 Pro
Long ctx · Enterprise · OpenAI compat
Google AI Studio — Gemini 2.0 Flash
Fast
Price
$0.84
Quota
60/min
Card
CC req
Google AI Studio—Gemini 2.0 Flash
Fast
Kilo Gateway — Sonar Pro
Enterprise
Price
Free
Quota
1500/min
Card
No CC
Kilo Gateway—Sonar Pro
Enterprise
Kilo Gateway — DeepSeek V3
Multi-purpose
Price
$1.35
Quota
60/min
Card
CC req
Kilo Gateway—DeepSeek V3
Multi-purpose
Fireworks AI — Phi-4
Multi-purpose
Price
$0.24
Quota
60/min
Card
CC req
Fireworks AI—Phi-4
Multi-purpose
OpenRouter — Mixtral 8x22B
Open source · OpenAI compat
Price
$1.20
Quota
∞/min
Card
CC req
OpenRouter—Mixtral 8x22B
Open source · OpenAI compat
Modal — Mixtral 8x22B
Open source
Price
$2.07
Quota
60/min
Card
CC req
Modal—Mixtral 8x22B
Open source
NVIDIA NIM — Nemotron
OpenAI compat
Price
Free
Quota
40/min
Card
No CC
NVIDIA NIM—Nemotron
OpenAI compat
Groq — Mixtral 8x7B
Open source · OpenAI compat
Price
Free
Quota
30/min
Card
No CC
Groq—Mixtral 8x7B
Open source · OpenAI compat
Modal — Llama 3.3 70B
Open source
Price
Free
Quota
50/min
Card
No CC
Modal—Llama 3.3 70B
Open source
Together AI — Llama 3 70B
Open source · OpenAI compat
Price
$0.90
Quota
∞/min
Card
CC req
Together AI—Llama 3 70B
Open source · OpenAI compat
Fireworks AI — Llama 3.3 70B
Open source · OpenAI compat
Price
$0.40
Quota
∞/min
Card
CC req
Fireworks AI—Llama 3.3 70B
Open source · OpenAI compat