LLM Reference

Gemini 2.5 Pro Preview 06-05 vs Magistral Small 2506

Gemini 2.5 Pro Preview 06-05 (2025) and Magistral Small 2506 (2025) are frontier reasoning models from Google DeepMind and MistralAI. Gemini 2.5 Pro Preview 06-05 ships a 1m-token context window, while Magistral Small 2506 ships a 128k-token context window. This comparison covers specs, pricing, API access, capabilities, benchmarks, input and output token costs, and production fit for coding and agent workloads.

Gemini 2.5 Pro Preview 06-05 fits 8x more tokens; pick it for long-context work and Magistral Small 2506 for tighter calls.

Decision scorecard

Local evidence first
SignalGemini 2.5 Pro Preview 06-05Magistral Small 2506
Best formultimodal apps and long-context analysisreasoning-heavy apps
Decision fitCoding, RAG, and AgentsLong context
Context window1m128k
Cheapest output$10/1M tokens-
Provider routes1 tracked1 tracked
Shared benchmarks0 rows0 rows

Decision tradeoffs

Choose Gemini 2.5 Pro Preview 06-05 when...
  • Gemini 2.5 Pro Preview 06-05 has the larger context window for long prompts, retrieval packs, or transcript analysis.
  • Gemini 2.5 Pro Preview 06-05 uniquely exposes Vision, Multimodal, and Structured outputs in local model data.
  • Local decision data tags Gemini 2.5 Pro Preview 06-05 for Coding, RAG, and Agents.
Choose Magistral Small 2506 when...
  • Magistral Small 2506 uniquely exposes Reasoning in local model data.
  • Local decision data tags Magistral Small 2506 for Long context.

Monthly cost at traffic

Estimate token spend from the cheapest tracked input and output route or tier on this page.

Gemini 2.5 Pro Preview 06-05

$3,500

Cheapest tracked route/tier: OpenRouter

Magistral Small 2506

Unavailable

No complete token price in local provider data

Cost delta unavailable until both models have sourced input and output token prices.

Switch friction

Gemini 2.5 Pro Preview 06-05 -> Magistral Small 2506
  • No overlapping tracked provider route is sourced for Gemini 2.5 Pro Preview 06-05 and Magistral Small 2506; plan for SDK, billing, or endpoint changes.
  • Check replacement coverage for Vision, Multimodal, and Structured outputs before moving production traffic.
  • Magistral Small 2506 adds Reasoning in local capability data.
Magistral Small 2506 -> Gemini 2.5 Pro Preview 06-05
  • No overlapping tracked provider route is sourced for Magistral Small 2506 and Gemini 2.5 Pro Preview 06-05; plan for SDK, billing, or endpoint changes.
  • Check replacement coverage for Reasoning before moving production traffic.
  • Gemini 2.5 Pro Preview 06-05 adds Vision, Multimodal, and Structured outputs in local capability data.

Specs

Specification
Released2025-03-252025-06-10
Context window1m128k
Parameters24B
Architecturedecoder onlydecoder only
LicenseProprietaryApache 2.0(OSI)
OpennessProprietaryOpen source
Commercial useCommercial use with conditionsCommercial use allowed
Knowledge cutoff-2025-06

Pricing and availability

Pricing attributeGemini 2.5 Pro Preview 06-05Magistral Small 2506
Input price$1.25/1M tokens-
Output price$10/1M tokens-
Providers

Capabilities

CapabilityGemini 2.5 Pro Preview 06-05Magistral Small 2506
VisionYesNo
MultimodalYesNo
ReasoningNoYes
Function callingNoNo
Tool useNoNo
Structured outputsYesNo
Code executionYesNo
IDE integrationNoNo
Computer useNoNo
Parallel agentsNoNo

Benchmarks

No shared benchmark rows are currently sourced for this pair.

Deep dive

The capability footprint differs most on vision: Gemini 2.5 Pro Preview 06-05, multimodal input: Gemini 2.5 Pro Preview 06-05, reasoning mode: Magistral Small 2506, structured outputs: Gemini 2.5 Pro Preview 06-05, and code execution: Gemini 2.5 Pro Preview 06-05. Both models share the core language-model surface, so the practical split is not just feature count. Use those differences to decide whether the page is about raw model quality, agentic coding support, multimodal ingestion, or predictable structured API behavior.

Pricing coverage is uneven: Gemini 2.5 Pro Preview 06-05 has $1.25/1M input tokens and Magistral Small 2506 has no token price sourced yet. Provider availability is 1 tracked routes versus 1. Treat unknown pricing as an integration gap, then verify the route you will actually call before estimating production spend.

Choose Gemini 2.5 Pro Preview 06-05 when coding workflow support and larger context windows are central to the workload. Choose Magistral Small 2506 when reasoning depth are more important. For production, rerun your own prompts through the exact provider, region, and tool stack you plan to ship. This keeps the decision grounded in measurable tradeoffs instead of brand-level assumptions.

FAQ

Which has a larger context window, Gemini 2.5 Pro Preview 06-05 or Magistral Small 2506?

Gemini 2.5 Pro Preview 06-05 supports 1m tokens, while Magistral Small 2506 supports 128k tokens. That gap matters most for long documents, large codebases, retrieval-heavy agents, and conversations where earlier context must remain visible.

Is Gemini 2.5 Pro Preview 06-05 or Magistral Small 2506 open source?

Gemini 2.5 Pro Preview 06-05 is listed under Proprietary. Magistral Small 2506 is listed under Apache 2.0. License labels affect whether you can self-host, redistribute weights, or rely only on hosted APIs, so confirm the upstream license before deployment.

Which is better for vision, Gemini 2.5 Pro Preview 06-05 or Magistral Small 2506?

Gemini 2.5 Pro Preview 06-05 has the clearer documented vision signal in this comparison. If vision is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Which is better for multimodal input, Gemini 2.5 Pro Preview 06-05 or Magistral Small 2506?

Gemini 2.5 Pro Preview 06-05 has the clearer documented multimodal input signal in this comparison. If multimodal input is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Which is better for reasoning mode, Gemini 2.5 Pro Preview 06-05 or Magistral Small 2506?

Magistral Small 2506 has the clearer documented reasoning mode signal in this comparison. If reasoning mode is mission-critical, validate it against the provider endpoint because model-level support and API-level exposure can differ.

Where can I run Gemini 2.5 Pro Preview 06-05 and Magistral Small 2506?

Gemini 2.5 Pro Preview 06-05 is available on OpenRouter. Magistral Small 2506 is available on NVIDIA NIM. Provider coverage can affect latency, region availability, compliance posture, and fallback options. Use this as a quick comparison signal, then confirm the provider-specific limits before committing to production.

Continue comparing

Last reviewed: 2026-06-04. Data sourced from public model cards and provider documentation.