Serverless
Pay-per-token inference with zero infrastructure. Prices are set live by the sourcing engine — at or below the reference platform's list price, never below our cost.
| Model | Modality | Context | $/1M input | $/1M output | Reference | |
|---|---|---|---|---|---|---|
| GLM 5.2 allais/glm-5-2 | text | 202K | $0.72 | $2 | $0.9 · $2.5 | Try |
| Kimi K2 Instruct allais/kimi-k2-instruct | text | 131K | $0.48 | $2 | $0.6 · $2.5 | Try |
| DeepSeek V3.2 allais/deepseek-v3-2 | text | 164K | $0.448 | $1.344 | $0.56 · $1.68 | Try |
| Qwen3 235B-A22B allais/qwen3-235b-a22b | text | 131K | $0.176 | $0.704 | $0.22 · $0.88 | Try |
| Llama 4 Maverick allais/llama-4-maverick | vision | 1000K | $0.176 | $0.704 | $0.22 · $0.88 | Try |
| Llama 3.3 70B Instruct allais/llama-3-3-70b | text | 131K | $0.72 | $0.72 | $0.9 · $0.9 | Try |
| Qwen3 Coder 32B allais/qwen3-coder-32b | text | 131K | $0.5831 | $1.28 | $0.4 · $1.6 | Try |
| Llama 3.1 8B Instruct allais/llama-3-1-8b | text | 131K | $0.3077 | $0.3077 | $0.2 · $0.2 | Try |
| FLUX.1 [dev] allais/flux-1-dev | image-gen | — | usage-based | — | — | Try |
| Whisper V3 Large allais/whisper-v3-large | audio | — | usage-based | — | — | Try |
| All Embed Large v3 allais/embed-large-v3 | embedding | 33K | $0.1753 | — | $0.08 · $0 | Try |
Prices refresh every 10 minutes from live GPU-market quotes across six providers.