PromptForge
Side-by-side comparison

Model Matrix

Every model compared at a glance — maker, modality, context, and indicative pricing. Click a column to sort, or a model name for full details.

Claude Fable 5AnthropicText + visionVery large context$10$50Closed
Claude Haiku 4.5AnthropicText + visionLarge context$1$5Closed
Claude Opus 4.8AnthropicText + visionVery large context$5$25Closed
Claude Sonnet 5AnthropicText + visionLarge context$3$15Closed
Codestral 25.06Mistral AICodeCode-optimized contextOpen
Cohere Command RCohereText (RAG)Tuned for RAGClosed
DeepSeek R1DeepSeekText (reasoning)Large contextOpen
DeepSeek V3.2DeepSeekTextLarge contextOpen
Gemini 3.1 Flash-LiteGoogle DeepMindText + visionLarge context$0.25$1.5Closed
Gemini 3.1 ProGoogle DeepMindText + vision + audio + video1M token context$2$12Closed
Gemini 3.6 FlashGoogle DeepMindText + vision + audio + videoUp to ~1M tokens$1.5$7.5Closed
GPT-5.5 ProOpenAIText + visionLarge context$30$180Closed
GPT-5.6 LunaOpenAITextLarge context$1$6Closed
GPT-5.6 SolOpenAIText + vision + audioLarge context$5$30Closed
GPT-5.6 TerraOpenAIText + visionLarge context$2.5$15Closed
Grok 4.5xAIText + visionLarge context$5$25Closed
Llama 4 BehemothMetaText + visionLong context (MoE)Open
Llama 4 MaverickMetaText + visionLong context (MoE)Open
Llama 4 ScoutMetaTextVery long contextOpen
Mistral Large 3Mistral AITextLarge contextOpen
Mistral Small 4Mistral AITextEfficient contextOpen
Perplexity (Sonar)Perplexity AIAnswer engineRetrieval-focusedClosed
Qwen 3 235BAlibaba CloudTextLarge context (MoE)Open
Qwen 3.7 MaxAlibaba CloudText + visionLarge contextOpen

Pricing is indicative, per 1M tokens (USD), reviewed July 2026. Open-weight models show “—” (self-host or provider-dependent). Always verify current pricing on the provider's site.