14
Models Available
$0.030
Cheapest Input / 1M
131K
Largest Context
What is Llamagate?
Llamagate is an AI model provider offering 14 large language models for developers. Their cheapest model starts at $0.030 per 1M input tokens, and their largest context window reaches 131K. Llamagate provides 14 AI models accessible via API.
Llamagate Strengths
All Llamagate Models
| Model | Input $/1M | Output $/1M | Context | Max Output | Released |
|---|---|---|---|---|---|
| Llama 3.1 8b | $0.030 | $0.050 | 131K | 8,192 | — |
| Gemma3 4b | $0.030 | $0.080 | 128K | 8,192 | — |
| Llama 3.2 3b | $0.040 | $0.080 | 131K | 8,192 | — |
| Qwen3 8b | $0.040 | $0.14 | 33K | 8,192 | — |
| Qwen2.5 Coder 7b | $0.060 | $0.12 | 33K | 8,192 | — |
| Deepseek Coder 6.7b | $0.060 | $0.12 | 16K | 4,096 | — |
| Codellama 7b | $0.060 | $0.12 | 16K | 4,096 | — |
| Dolphin3 8b | $0.080 | $0.15 | 128K | 8,192 | — |
| Deepseek R1 7b Qwen | $0.080 | $0.15 | 131K | 16,384 | — |
| Openthinker 7b | $0.080 | $0.15 | 33K | 8,192 | — |
| Mistral 7b V0.3 | $0.10 | $0.15 | 33K | 8,192 | — |
| Deepseek R1 8b | $0.10 | $0.20 | 66K | 16,384 | — |
| Llava 7b | $0.10 | $0.20 | 4K | 2,048 | — |
| Qwen3 Vl 8b | $0.15 | $0.55 | 33K | 8,192 | — |
Model Details
Llama 3.1 8b
Llama 3.1 8b is available via Llamagate with a 131K context window and up to 8,192 output tokens. Pricing: $0.0300/1M input tokens, $0.0500/1M output tokens.
Gemma3 4b
Gemma3 4b is available via Llamagate with a 128K context window and up to 8,192 output tokens. Pricing: $0.0300/1M input tokens, $0.0800/1M output tokens.
Llama 3.2 3b
Llama 3.2 3b is available via Llamagate with a 131K context window and up to 8,192 output tokens. Pricing: $0.0400/1M input tokens, $0.0800/1M output tokens.
Qwen3 8b
Qwen3 8b is available via Llamagate with a 33K context window and up to 8,192 output tokens. Pricing: $0.0400/1M input tokens, $0.1400/1M output tokens.
Qwen2.5 Coder 7b
Qwen2.5 Coder 7b is available via Llamagate with a 33K context window and up to 8,192 output tokens. Pricing: $0.0600/1M input tokens, $0.1200/1M output tokens.
Deepseek Coder 6.7b
Deepseek Coder 6.7b is available via Llamagate with a 16K context window and up to 4,096 output tokens. Pricing: $0.0600/1M input tokens, $0.1200/1M output tokens.
Codellama 7b
Codellama 7b is available via Llamagate with a 16K context window and up to 4,096 output tokens. Pricing: $0.0600/1M input tokens, $0.1200/1M output tokens.
Dolphin3 8b
Dolphin3 8b is available via Llamagate with a 128K context window and up to 8,192 output tokens. Pricing: $0.0800/1M input tokens, $0.1500/1M output tokens.
Deepseek R1 7b Qwen
Deepseek R1 7b Qwen is available via Llamagate with a 131K context window and up to 16,384 output tokens. Pricing: $0.0800/1M input tokens, $0.1500/1M output tokens.
Openthinker 7b
Openthinker 7b is available via Llamagate with a 33K context window and up to 8,192 output tokens. Pricing: $0.0800/1M input tokens, $0.1500/1M output tokens.
Mistral 7b V0.3
Mistral 7b V0.3 is available via Llamagate with a 33K context window and up to 8,192 output tokens. Pricing: $0.1000/1M input tokens, $0.1500/1M output tokens.
Deepseek R1 8b
Deepseek R1 8b is available via Llamagate with a 66K context window and up to 16,384 output tokens. Pricing: $0.1000/1M input tokens, $0.2000/1M output tokens.
Llava 7b
Llava 7b is available via Llamagate with a 4K context window and up to 2,048 output tokens. Pricing: $0.1000/1M input tokens, $0.2000/1M output tokens.
Qwen3 Vl 8b
Qwen3 Vl 8b is available via Llamagate with a 33K context window and up to 8,192 output tokens. Pricing: $0.1500/1M input tokens, $0.5500/1M output tokens.
Compare Llamagate model pricing
Use our pricing calculator to find the cheapest Llamagate model for your workload.