Loading models...
Model Catalog
Access state-of-the-art open-source AI models through a simple, unified API. From chat to embeddings, find the right model for your use case.
Categories
29 models
Chat Pico
chat
Smallest available chat model for on-device and extreme-latency scenarios.
Context: 4.1K
Input: $0.15/1M
Output: $0.55/1M
Assisters Chat Mini
chat
Ultra-low latency chat for simple tasks. Ideal for autocomplete, short summaries, and high-volume pipelines. 2-4B edge model.
Context: 8.2K
Input: $0.15/1M
Output: $0.55/1M
Chat v6
chat
Ultra-lightweight model for high-throughput, cost-sensitive text generation.
Context: 4.1K
Input: $0.15/1M
Output: $0.55/1M
Chat Mini 2
chat
Upgraded compact model with strong multilingual support.
Context: 128K
Input: $0.15/1M
Output: $0.55/1M
Chat Nano
chat
Ultra-fast compact chat. Optimised for low-latency tasks.
Context: 131.1K
Input: $0.15/1M
Output: $0.55/1M
Chat v15 (Compact)
chat
Compact open-weight chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.15/1M
Output: $0.55/1M
Chat Mini 3 (Lightweight)
chat
Lightweight instruct chat with automatic multi-tier failover.
Context: 32.8K
Input: $0.15/1M
Output: $0.55/1M
Chat v17 (Free Lite)
chat
Highest-throughput free chat tier for high-frequency lightweight tasks. Automatic multi-tier failover.
Context: 32.8K
Input: $0.15/1M
Output: $0.55/1M
Chat v12 (Balanced)
chat
Balanced MoE chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.40/1M
Output: $3.25/1M
Chat v14 (Efficient)
chat
Efficient general chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.40/1M
Output: $3.25/1M
Chat IN (Indic)
chat
Indic-languages-optimized chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.40/1M
Output: $3.25/1M
Chat JA (Japanese)
chat
Japanese-optimized chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.40/1M
Output: $3.25/1M
Chat v10 (Multilingual)
chat
Multilingual frontier chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.60/1M
Output: $3.25/1M
Chat v11 (Long Context)
chat
Long-context agentic chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.60/1M
Output: $3.25/1M
Chat v19 (Sparse MoE)
chat
Classic sparse-MoE chat with automatic multi-tier failover.
Context: 65.5K
Input: $0.80/1M
Output: $3.25/1M
Chat Medium
chat
Quality between turbo and pro tiers.
Context: 128K
Input: $0.85/1M
Output: $3.25/1M
Chat v13 (Flagship)
chat
Flagship MoE chat with automatic multi-tier failover.
Context: 65.5K
Input: $1.75/1M
Output: $13.00/1M
Chat v7 (Ultra)
chat
Frontier-grade 550B MoE general chat with automatic multi-tier failover.
Context: 65.5K
Input: $1.75/1M
Output: $13.00/1M
Chat v5
chat
Broad-capability open-weight chat. Free tier.
Context: 128K
Input: $2.00/1M
Output: $6.00/1M
Assisters Chat Turbo
chat
Mixture-of-Experts model optimized for instruction-following, function calling, and agentic tool use. Best speed-to-capability ratio.
Context: 32.8K
Input: $2.00/1M
Output: $6.00/1M
Chat v1
chat
Advanced conversational AI with frontier-class reasoning. 128K context window with 500+ tokens/second throughput.
Context: 128K
Input: $2.00/1M
Output: $6.00/1M
Assisters Chat v2
chat
Enhanced 70B model with stronger instruction-following, code comprehension, and multi-language support. Ideal for agentic workflows.
Context: 32.8K
Input: $2.00/1M
Output: $6.00/1M
Assisters Chat v4
chat
High-capacity 120B chat model. Strong reasoning and instruction following.
Context: 131.1K
Input: $2.00/1M
Output: $6.00/1M
Chat v18 (Free Pro)
chat
Highest-quality free chat tier. Best for complex reasoning and long-context tasks.
Context: 65.5K
Input: $2.00/1M
Output: $13.00/1M
Chat v16 (Free Flash)
chat
Fast, multimodal chat with 1M-token context. Free tier with automatic multi-tier failover.
Context: 65.5K
Input: $2.00/1M
Output: $6.00/1M
Assisters MoE
chat
Mixture-of-Experts smart routing. Automatically selects the best model from the pool based on task type, load, and quality requirements. Ideal for unpredictable workloads.
Context: 32.8K
Input: $2.00/1M
Output: $6.00/1M
Assisters Chat v3
chat
Frontier-grade 675B MoE model for the most demanding reasoning, analysis, and generation tasks. Ideal for enterprise workloads requiring maximum accuracy.
Context: 131.1K
Input: $4.00/1M
Output: $6.00/1M
Chat v8 (Flash)
chat
Fast, low-latency MoE chat with automatic multi-tier failover.
Context: 65.5K
Input: $4.00/1M
Output: $6.00/1M
Need a specific model?
We're constantly adding new models. Let us know what you need and we'll work on adding it.
Request a Model