Newer StepFun flash model for faster agents, coding, and multimodal prompts
Model catalog
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
17 providers
StepFun flash lane for quick multimodal reasoning and coding assistance
14 providers
Late GLM-4 workhorse for coding agents, reasoning, and structured tasks
18 providers
Mistral's coding-agent model for repository work, terminal tasks, and software fixes
13 providers
Fast Mistral production model for chat, extraction, and cost-sensitive agents
12 providers
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning
12 providers
Smaller Qwen coder for efficient local agents and repo-level fixes
13 providers
Classic open reasoning model for transparent math, coding, and deliberate problem solving
14 providers
Popular open Llama workhorse for multilingual chat, coding, and self-hosting
25 providers
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Step 3.7 Flashstepfun/step-3.7-flash | 35.6 | 256K | $0.185 | $1.11 | 2026-05-29 | |||
| Step 3.5 Flashstepfun/step-3.5-flash | 27.3 | 256K | $0.1 | $0.3 | 2026-01-29 | |||
| GLM-4.6zhipuai/glm-4.6 | 25.0 | 204.8K | $0.6 | $2.2 | 2025-09-30 | |||
| Devstral 2mistral/devstral-2512 | 18.9 | 262.144K | $0.4 | $2 | 2025-12-09 | |||
| Mistral Small 4mistral/mistral-small-2603 | 17.4 | 256K | $0.15 | $0.6 | 2026-03-16 | |||
| Mistral Large 3mistral/mistral-large-2512 | 15.9 | 262.144K | $0.5 | $1.5 | 2024-11-01 | |||
| Qwen3-Coder 30B-A3B Instructalibaba/qwen3-coder-30b-a3b-instruct | 15.2 | 262.144K | $0.45 | $2.25 | 2025-04 | |||
| DeepSeek-R1deepseek/deepseek-r1 | 6.1 | 128K | $0.7 | $2.5 | 2025-01-20 | |||
| Llama-3.3-70B-Instructmeta/llama-3.3-70b-instruct | 3.0 | 128K | $0.1 | $0.32 | 2024-12-06 |