Quick Answer
Best Model APIs for Chat, Embeddings and Reranking 2026
The short answer
Pick the three layers separately unless you need one contract. As of November 15, 2026:
- One vendor for everything: Google (Gemini chat, Gemini Embedding 2, Vertex AI Ranking API).
- Best retrieval pair: Cohere Embed 5 + Rerank 5, or Voyage voyage-4 + rerank-3, next to any chat model.
- Cheapest workable stack: OpenAI GPT-6 Luna or Claude Haiku 5.5 for chat ($0.10/$0.50), OpenAI text-embedding-3-small ($0.02) and Cohere Rerank 5 Fast ($0.02).
- European vendor: Mistral (chat, embeddings and OCR in one account; no reranker).
What are the best model APIs for chat, embeddings and reranking for a SaaS product? A chat model from OpenAI, Anthropic or Google, plus embeddings and reranking from Cohere or Voyage AI — or Google alone if you want one bill.
Who sells what
| Vendor | Chat (per 1M tokens, in/out) | Embeddings (per 1M tokens) | Reranking | One bill for all three? |
|---|---|---|---|---|
| Gemini 4 Hydrogen $1.50/$7.50; Gemini 3.8 Flash $0.75/$3.75 (intro, to Dec 31, 2026) | Gemini Embedding 2: $0.20 text (multimodal) | Vertex AI Ranking API $1.00 per 1,000 queries | Yes | |
| OpenAI | GPT-6.1 Sol $2/$10; GPT-6.1 Terra $1/$5; GPT-6 Luna $0.10/$0.50 | text-embedding-3-small $0.02; -large $0.13 | No dedicated reranker | No |
| Anthropic | Claude Sonnet 5.5 $2/$10; Haiku 5.5 $0.10/$0.50 | None (docs point to Voyage) | None | No |
| Cohere | Command family (often paired with another chat vendor) | Embed 5 Pro $0.12; Fast $0.08 | Rerank 5 Pro $0.05; Fast $0.02 per 1M tokens | Partly |
| Voyage AI (MongoDB) | None | voyage-4-large $0.12; voyage-4 $0.06; voyage-4-lite $0.02 | rerank-3 $0.05; rerank-3-lite $0.02 per 1M tokens | No chat |
| Mistral | Mistral Large 4 $0.70/$2.10 | Mistral Embed $0.10; Codestral Embed for code | None | No reranker |
Chat prices are from vendor pricing pages and our current API prices table; embedding and reranking prices were read from the vendor pages and OpenRouter on November 15, 2026.
Picks by use case
| You are building | Chat | Embeddings | Reranker |
|---|---|---|---|
| B2B SaaS search / RAG over customer docs | Claude Sonnet 5.5 or GPT-6.1 Sol | Cohere Embed 5 Pro or voyage-4-large | Cohere Rerank 5 Pro |
| High-volume support bot on a budget | GPT-6 Luna or Claude Haiku 5.5 | text-embedding-3-small or voyage-4-lite | Rerank 5 Fast or rerank-3-lite |
| Already on Google Cloud, one contract | Gemini 4 Hydrogen | Gemini Embedding 2 | Vertex AI Ranking API |
| Images, PDFs and video in the index | Gemini 4 Hydrogen | Gemini Embedding 2 or Cohere Embed 5 (image input) | Rerank 5 Pro |
| EU data residency, one vendor | Mistral Large 4 | Mistral Embed | Add Cohere Rerank 5 (VPC/on-prem available) |
| Code search | Any | Codestral Embed or voyage-code-4 | rerank-3 |
Pricing models differ — watch the units
- Embeddings are billed once per token when you index, then per query token. Re-indexing a 50-million-token corpus costs $1 on text-embedding-3-small and $6 on Embed 5 Pro — trivial next to the engineering cost of migrating.
- Reranking is billed per token on Cohere Rerank 5 and Voyage, but per query on Google (up to a fixed number of records per query). Voyage counts
query tokens × documents + document tokens, so reranking 100 candidates of 500 tokens is about 50,000–100,000 tokens: roughly $0.0025–$0.005 per query on rerank-3. - Free allowances: Voyage gives each account 200 million free tokens on voyage-4, voyage-4-lite, voyage-4-large, voyage-context-4 and its current rerankers. Google’s free Gemini API tier covers Hydrogen and Embedding 2 but your data may be used to improve Google products.
How to choose
- Fix the embedding model first. It is the layer you change least often. Evaluate two candidates on 200 real queries from your logs; see best embedding models.
- Add a reranker before upgrading the chat model. A reranker on top 50–100 candidates usually lifts answer quality more per dollar than a bigger chat model — how to add a reranker and best reranker models.
- Keep chat behind a gateway so you can move between OpenAI, Anthropic and Google as prices change; Gemini 4 Argon and Carbon double to $4/$20 on December 1, 2026, and Gemini 3.8 Flash doubles on January 1, 2027.
- Check the contract, not just the price: zero data retention, regions, and whether the vendor offers VPC deployment (Cohere does for Embed and Rerank; Voyage offers VPC through its docs’ deployment section).
Last verified: November 15, 2026.